Skip to content

GitLab

"mmdet/structures/bbox/base_boxes.py" did not exist on "3e89e2569a866545f404bfd4c11cc9bfb12cad68"
Commit a7b29f47 authored by WANNA309's avatar WANNA309
Browse files

Update .dockerignore, .gitattributes, .gitignore, CONTRIBUTING.md, detect.py,... 

Update .dockerignore, .gitattributes, .gitignore, CONTRIBUTING.md, detect.py, Dockerfile, export.py, hubconf.py, LICENSE, model.properties, native bn.png, pycoco_false_result.png, pycocotools.png, README.md, requirements.txt, train.py, tutorial.ipynb, val.py, view_code.py, data/Argoverse.yaml, data/coco.yaml, data/coco128.yaml, data/GlobalWheat2020.yaml, data/Objects365.yaml, data/SKU-110K.yaml, data/VisDrone.yaml, data/VOC.yaml, data/xView.yaml, data/hyps/hyp.finetune.yaml, data/hyps/hyp.finetune_objects365.yaml, data/hyps/hyp.scratch.yaml, data/hyps/hyp.scratch-high.yaml, data/hyps/hyp.scratch-low.yaml, data/images/bus.jpg, data/images/zidane.jpg, data/scripts/download_weights.sh, data/scripts/get_coco.sh, data/scripts/get_coco128.sh, models/__init__.py, models/common.py, models/experimental.py, models/tf.py, models/yolo.py, models/yolov5l.yaml, models/yolov5m.yaml, models/yolov5n.yaml, models/yolov5s.yaml, models/yolov5x.yaml, models/hub/anchors.yaml, models/hub/yolov3.yaml, models/hub/yolov3-spp.yaml, models/hub/yolov3-tiny.yaml, models/hub/yolov5-bifpn.yaml, models/hub/yolov5-fpn.yaml, models/hub/yolov5l6.yaml, models/hub/yolov5m6.yaml, models/hub/yolov5n6.yaml, models/hub/yolov5-p2.yaml, models/hub/yolov5-p6.yaml, models/hub/yolov5-p7.yaml, models/hub/yolov5-panet.yaml, models/hub/yolov5s6.yaml, models/hub/yolov5s-ghost.yaml, models/hub/yolov5s-transformer.yaml, models/hub/yolov5x6.yaml, utils/__init__.py, utils/activations.py, utils/augmentations.py, utils/autoanchor.py, utils/callbacks.py, utils/datasets.py, utils/downloads.py, utils/general.py, utils/loss.py, utils/metrics.py, utils/plots.py, utils/torch_utils.py, utils/aws/__init__.py, utils/aws/mime.sh, utils/aws/resume.py, utils/aws/userdata.sh, utils/flask_rest_api/example_request.py, utils/flask_rest_api/README.md, utils/flask_rest_api/restapi.py, utils/google_app_engine/additional_requirements.txt, utils/google_app_engine/app.yaml, utils/google_app_engine/Dockerfile, utils/loggers/__init__.py, utils/loggers/wandb/__init__.py, utils/loggers/wandb/log_dataset.py, utils/loggers/wandb/README.md, utils/loggers/wandb/sweep.py, utils/loggers/wandb/sweep.yaml, utils/loggers/wandb/wandb_utils.py files
parents
Pipeline #461 failed with stages
in 0 seconds
Hide whitespace changes
Inline Side-by-side
Showing with 4526 additions and 0 deletions
requirements.txt 0 → 100644
View file @ a7b29f47
# pip install -r requirements.txt
# Base ----------------------------------------
matplotlib>=3.2.2
numpy>=1.18.5
opencv-python>=4.1.2
Pillow>=7.1.2
PyYAML>=5.3.1
requests>=2.23.0
scipy>=1.4.1
#torch>=1.7.0
#torchvision>=0.8.1
tqdm>=4.41.0
# Logging -------------------------------------
tensorboard>=2.4.1
# wandb
# Plotting ------------------------------------
pandas>=1.1.4
seaborn>=0.11.0
pycocotools
# Export --------------------------------------
# coremltools>=4.1 # CoreML export
# onnx>=1.9.0 # ONNX export
# onnx-simplifier>=0.3.6 # ONNX simplifier
# scikit-learn==0.19.2 # CoreML quantization
# tensorflow>=2.4.1 # TFLite export
# tensorflowjs>=3.9.0 # TF.js export
# Extras --------------------------------------
# albumentations>=1.0.3
# Cython # for pycocotools https://github.com/cocodataset/cocoapi/issues/172
# pycocotools>=2.0 # COCO mAP
# roboflow
thop # FLOPs computation
train.py 0 → 100644
View file @ a7b29f47
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
"""
Train a YOLOv5 model on a custom dataset
Usage:
$ python path/to/train.py --data coco128.yaml --weights yolov5s.pt --img 640
"""
import argparse
import logging
import math
import os
import random
import sys
import time
from copy import deepcopy
from pathlib import Path
import numpy as np
import torch
import torch.distributed as dist
import torch.nn as nn
import yaml
from torch.cuda import amp
from torch.nn.parallel import DistributedDataParallel as DDP
from torch.optim import Adam, SGD, lr_scheduler
from tqdm import tqdm
FILE = Path(__file__).resolve()
ROOT = FILE.parents[0] # YOLOv5 root directory
if str(ROOT) not in sys.path:
sys.path.append(str(ROOT)) # add ROOT to PATH
ROOT = Path(os.path.relpath(ROOT, Path.cwd())) # relative
import val # for end-of-epoch mAP
from models.experimental import attempt_load
from models.yolo import Model
from utils.autoanchor import check_anchors
from utils.datasets import create_dataloader
from utils.general import labels_to_class_weights, increment_path, labels_to_image_weights, init_seeds, \
strip_optimizer, get_latest_run, check_dataset, check_git_status, check_img_size, check_requirements, \
check_file, check_yaml, check_suffix, print_args, print_mutation, set_logging, one_cycle, colorstr, methods
from utils.downloads import attempt_download
from utils.loss import ComputeLoss
from utils.plots import plot_labels, plot_evolve
from utils.torch_utils import EarlyStopping, ModelEMA, de_parallel, intersect_dicts, select_device, \
torch_distributed_zero_first
from utils.loggers.wandb.wandb_utils import check_wandb_resume
from utils.metrics import fitness
from utils.loggers import Loggers
from utils.callbacks import Callbacks
LOGGER = logging.getLogger(__name__)
LOCAL_RANK = int(os.getenv('LOCAL_RANK', -1)) # https://pytorch.org/docs/stable/elastic/run.html
RANK = int(os.getenv('RANK', -1))
WORLD_SIZE = int(os.getenv('WORLD_SIZE', 1))
def train(hyp, # path/to/hyp.yaml or hyp dictionary
opt,
device,
callbacks
):
save_dir, epochs, batch_size, weights, single_cls, evolve, data, cfg, resume, noval, nosave, workers, freeze, = \
Path(opt.save_dir), opt.epochs, opt.batch_size, opt.weights, opt.single_cls, opt.evolve, opt.data, opt.cfg, \
opt.resume, opt.noval, opt.nosave, opt.workers, opt.freeze
# Directories
w = save_dir / 'weights' # weights dir
(w.parent if evolve else w).mkdir(parents=True, exist_ok=True) # make dir
last, best = w / 'last.pt', w / 'best.pt'
# Hyperparameters
if isinstance(hyp, str):
with open(hyp, errors='ignore') as f:
hyp = yaml.safe_load(f) # load hyps dict
LOGGER.info(colorstr('hyperparameters: ') + ', '.join(f'{k}={v}' for k, v in hyp.items()))
# Save run settings
with open(save_dir / 'hyp.yaml', 'w') as f:
yaml.safe_dump(hyp, f, sort_keys=False)
with open(save_dir / 'opt.yaml', 'w') as f:
yaml.safe_dump(vars(opt), f, sort_keys=False)
data_dict = None
# Loggers
if RANK in [-1, 0]:
loggers = Loggers(save_dir, weights, opt, hyp, LOGGER) # loggers instance
if loggers.wandb:
data_dict = loggers.wandb.data_dict
if resume:
weights, epochs, hyp = opt.weights, opt.epochs, opt.hyp
# Register actions
for k in methods(loggers):
callbacks.register_action(k, callback=getattr(loggers, k))
# Config
plots = not evolve # create plots
cuda = device.type != 'cpu'
init_seeds(1 + RANK)
with torch_distributed_zero_first(LOCAL_RANK):
data_dict = data_dict or check_dataset(data) # check if None
train_path, val_path = data_dict['train'], data_dict['val']
nc = 1 if single_cls else int(data_dict['nc']) # number of classes
names = ['item'] if single_cls and len(data_dict['names']) != 1 else data_dict['names'] # class names
assert len(names) == nc, f'{len(names)} names found for nc={nc} dataset in {data}' # check
is_coco = data.endswith('coco.yaml') and nc == 80 # COCO dataset
# Model
check_suffix(weights, '.pt') # check weights
pretrained = weights.endswith('.pt')
if pretrained:
with torch_distributed_zero_first(LOCAL_RANK):
weights = attempt_download(weights) # download if not found locally
ckpt = torch.load(weights, map_location=device) # load checkpoint
model = Model(cfg or ckpt['model'].yaml, ch=3, nc=nc, anchors=hyp.get('anchors')).to(device) # create
exclude = ['anchor'] if (cfg or hyp.get('anchors')) and not resume else [] # exclude keys
csd = ckpt['model'].float().state_dict() # checkpoint state_dict as FP32
csd = intersect_dicts(csd, model.state_dict(), exclude=exclude) # intersect
model.load_state_dict(csd, strict=False) # load
LOGGER.info(f'Transferred {len(csd)}/{len(model.state_dict())} items from {weights}') # report
else:
model = Model(cfg, ch=3, nc=nc, anchors=hyp.get('anchors')).to(device) # create
# Freeze
freeze = [f'model.{x}.' for x in range(freeze)] # layers to freeze
for k, v in model.named_parameters():
v.requires_grad = True # train all layers
if any(x in k for x in freeze):
print(f'freezing {k}')
v.requires_grad = False
# Optimizer
nbs = 64 # nominal batch size
accumulate = max(round(nbs / batch_size), 1) # accumulate loss before optimizing
hyp['weight_decay'] *= batch_size * accumulate / nbs # scale weight_decay
LOGGER.info(f"Scaled weight_decay = {hyp['weight_decay']}")
g0, g1, g2 = [], [], [] # optimizer parameter groups
for v in model.modules():
if hasattr(v, 'bias') and isinstance(v.bias, nn.Parameter): # bias
g2.append(v.bias)
if isinstance(v, nn.BatchNorm2d): # weight (no decay)
g0.append(v.weight)
elif hasattr(v, 'weight') and isinstance(v.weight, nn.Parameter): # weight (with decay)
g1.append(v.weight)
if opt.adam:
optimizer = Adam(g0, lr=hyp['lr0'], betas=(hyp['momentum'], 0.999)) # adjust beta1 to momentum
else:
optimizer = SGD(g0, lr=hyp['lr0'], momentum=hyp['momentum'], nesterov=True)
optimizer.add_param_group({'params': g1, 'weight_decay': hyp['weight_decay']}) # add g1 with weight_decay
optimizer.add_param_group({'params': g2}) # add g2 (biases)
LOGGER.info(f"{colorstr('optimizer:')} {type(optimizer).__name__} with parameter groups "
f"{len(g0)} weight, {len(g1)} weight (no decay), {len(g2)} bias")
del g0, g1, g2
# Scheduler
if opt.linear_lr:
lf = lambda x: (1 - x / (epochs - 1)) * (1.0 - hyp['lrf']) + hyp['lrf'] # linear
else:
lf = one_cycle(1, hyp['lrf'], epochs) # cosine 1->hyp['lrf']
scheduler = lr_scheduler.LambdaLR(optimizer, lr_lambda=lf) # plot_lr_scheduler(optimizer, scheduler, epochs)
# EMA
ema = ModelEMA(model) if RANK in [-1, 0] else None
# Resume
start_epoch, best_fitness = 0, 0.0
if pretrained:
# Optimizer
if ckpt['optimizer'] is not None:
optimizer.load_state_dict(ckpt['optimizer'])
best_fitness = ckpt['best_fitness']
# EMA
if ema and ckpt.get('ema'):
ema.ema.load_state_dict(ckpt['ema'].float().state_dict())
ema.updates = ckpt['updates']
# Epochs
start_epoch = ckpt['epoch'] + 1
if resume:
assert start_epoch > 0, f'{weights} training to {epochs} epochs is finished, nothing to resume.'
if epochs < start_epoch:
LOGGER.info(f"{weights} has been trained for {ckpt['epoch']} epochs. Fine-tuning for {epochs} more epochs.")
epochs += ckpt['epoch'] # finetune additional epochs
del ckpt, csd
# Image sizes
gs = max(int(model.stride.max()), 32) # grid size (max stride)
nl = model.model[-1].nl # number of detection layers (used for scaling hyp['obj'])
imgsz = check_img_size(opt.imgsz, gs, floor=gs * 2) # verify imgsz is gs-multiple
# DP mode
if cuda and RANK == -1 and torch.cuda.device_count() > 1:
logging.warning('DP not recommended, instead use torch.distributed.run for best DDP Multi-GPU results.\n'
'See Multi-GPU Tutorial at https://github.com/ultralytics/yolov5/issues/475 to get started.')
model = torch.nn.DataParallel(model)
# SyncBatchNorm
if opt.sync_bn and cuda and RANK != -1:
model = torch.nn.SyncBatchNorm.convert_sync_batchnorm(model).to(device)
LOGGER.info('Using SyncBatchNorm()')
# Trainloader
train_loader, dataset = create_dataloader(train_path, imgsz, batch_size // WORLD_SIZE, gs, single_cls,
hyp=hyp, augment=True, cache=opt.cache, rect=opt.rect, rank=LOCAL_RANK,
workers=workers, image_weights=opt.image_weights, quad=opt.quad,
prefix=colorstr('train: '))
mlc = int(np.concatenate(dataset.labels, 0)[:, 0].max()) # max label class
nb = len(train_loader) # number of batches
assert mlc < nc, f'Label class {mlc} exceeds nc={nc} in {data}. Possible class labels are 0-{nc - 1}'
# Process 0
if RANK in [-1, 0]:
val_loader = create_dataloader(val_path, imgsz, batch_size // WORLD_SIZE * 2, gs, single_cls,
hyp=hyp, cache=None if noval else opt.cache, rect=True, rank=-1,
workers=workers, pad=0.5,
prefix=colorstr('val: '))[0]
if not resume:
labels = np.concatenate(dataset.labels, 0)
# c = torch.tensor(labels[:, 0]) # classes
# cf = torch.bincount(c.long(), minlength=nc) + 1. # frequency
# model._initialize_biases(cf.to(device))
if plots:
plot_labels(labels, names, save_dir)
# Anchors
if not opt.noautoanchor:
check_anchors(dataset, model=model, thr=hyp['anchor_t'], imgsz=imgsz)
model.half().float() # pre-reduce anchor precision
callbacks.run('on_pretrain_routine_end')
# DDP mode
if cuda and RANK != -1:
model = DDP(model, device_ids=[LOCAL_RANK], output_device=LOCAL_RANK)
# Model parameters
hyp['box'] *= 3. / nl # scale to layers
hyp['cls'] *= nc / 80. * 3. / nl # scale to classes and layers
hyp['obj'] *= (imgsz / 640) ** 2 * 3. / nl # scale to image size and layers
hyp['label_smoothing'] = opt.label_smoothing
model.nc = nc # attach number of classes to model
model.hyp = hyp # attach hyperparameters to model
model.class_weights = labels_to_class_weights(dataset.labels, nc).to(device) * nc # attach class weights
model.names = names
# Start training
t0 = time.time()
nw = max(round(hyp['warmup_epochs'] * nb), 1000) # number of warmup iterations, max(3 epochs, 1k iterations)
# nw = min(nw, (epochs - start_epoch) / 2 * nb) # limit warmup to < 1/2 of training
last_opt_step = -1
maps = np.zeros(nc) # mAP per class
results = (0, 0, 0, 0, 0, 0, 0) # P, R, mAP@.5, mAP@.5-.95, val_loss(box, obj, cls)
scheduler.last_epoch = start_epoch - 1 # do not move
scaler = amp.GradScaler(enabled=cuda)
stopper = EarlyStopping(patience=opt.patience)
compute_loss = ComputeLoss(model) # init loss class
LOGGER.info(f'Image sizes {imgsz} train, {imgsz} val\n'
f'Using {train_loader.num_workers} dataloader workers\n'
f"Logging results to {colorstr('bold', save_dir)}\n"
f'Starting training for {epochs} epochs...')
for epoch in range(start_epoch, epochs): # epoch ------------------------------------------------------------------
model.train()
# Update image weights (optional, single-GPU only)
if opt.image_weights:
cw = model.class_weights.cpu().numpy() * (1 - maps) ** 2 / nc # class weights
iw = labels_to_image_weights(dataset.labels, nc=nc, class_weights=cw) # image weights
dataset.indices = random.choices(range(dataset.n), weights=iw, k=dataset.n) # rand weighted idx
# Update mosaic border (optional)
# b = int(random.uniform(0.25 * imgsz, 0.75 * imgsz + gs) // gs * gs)
# dataset.mosaic_border = [b - imgsz, -b] # height, width borders
mloss = torch.zeros(3, device=device) # mean losses
if RANK != -1:
train_loader.sampler.set_epoch(epoch)
pbar = enumerate(train_loader)
LOGGER.info(('\n' + '%10s' * 7) % ('Epoch', 'gpu_mem', 'box', 'obj', 'cls', 'labels', 'img_size'))
if RANK in [-1, 0]:
pbar = tqdm(pbar, total=nb) # progress bar
optimizer.zero_grad()
for i, (imgs, targets, paths, _) in pbar: # batch -------------------------------------------------------------
ni = i + nb * epoch # number integrated batches (since train start)
imgs = imgs.to(device, non_blocking=True).float() / 255.0 # uint8 to float32, 0-255 to 0.0-1.0
# Warmup
if ni <= nw:
xi = [0, nw] # x interp
# compute_loss.gr = np.interp(ni, xi, [0.0, 1.0]) # iou loss ratio (obj_loss = 1.0 or iou)
accumulate = max(1, np.interp(ni, xi, [1, nbs / batch_size]).round())
for j, x in enumerate(optimizer.param_groups):
# bias lr falls from 0.1 to lr0, all other lrs rise from 0.0 to lr0
x['lr'] = np.interp(ni, xi, [hyp['warmup_bias_lr'] if j == 2 else 0.0, x['initial_lr'] * lf(epoch)])
if 'momentum' in x:
x['momentum'] = np.interp(ni, xi, [hyp['warmup_momentum'], hyp['momentum']])
# Multi-scale
if opt.multi_scale:
sz = random.randrange(imgsz * 0.5, imgsz * 1.5 + gs) // gs * gs # size
sf = sz / max(imgs.shape[2:]) # scale factor
if sf != 1:
ns = [math.ceil(x * sf / gs) * gs for x in imgs.shape[2:]] # new shape (stretched to gs-multiple)
imgs = nn.functional.interpolate(imgs, size=ns, mode='bilinear', align_corners=False)
# Forward
with amp.autocast(enabled=cuda):
pred = model(imgs) # forward
loss, loss_items = compute_loss(pred, targets.to(device)) # loss scaled by batch_size
if RANK != -1:
loss *= WORLD_SIZE # gradient averaged between devices in DDP mode
if opt.quad:
loss *= 4.
# Backward
scaler.scale(loss).backward()
# Optimize
if ni - last_opt_step >= accumulate:
scaler.step(optimizer) # optimizer.step
scaler.update()
optimizer.zero_grad()
if ema:
ema.update(model)
last_opt_step = ni
# Log
if RANK in [-1, 0]:
mloss = (mloss * i + loss_items) / (i + 1) # update mean losses
mem = f'{torch.cuda.memory_reserved() / 1E9 if torch.cuda.is_available() else 0:.3g}G' # (GB)
pbar.set_description(('%10s' * 2 + '%10.4g' * 5) % (
f'{epoch}/{epochs - 1}', mem, *mloss, targets.shape[0], imgs.shape[-1]))
callbacks.run('on_train_batch_end', ni, model, imgs, targets, paths, plots, opt.sync_bn)
# end batch ------------------------------------------------------------------------------------------------
# Scheduler
lr = [x['lr'] for x in optimizer.param_groups] # for loggers
scheduler.step()
if RANK in [-1, 0]:
# mAP
callbacks.run('on_train_epoch_end', epoch=epoch)
ema.update_attr(model, include=['yaml', 'nc', 'hyp', 'names', 'stride', 'class_weights'])
final_epoch = (epoch + 1 == epochs) or stopper.possible_stop
if not noval or final_epoch: # Calculate mAP
results, maps, _ = val.run(data_dict,
batch_size=batch_size // WORLD_SIZE * 2,
imgsz=imgsz,
model=ema.ema,
single_cls=single_cls,
dataloader=val_loader,
save_dir=save_dir,
plots=False,
callbacks=callbacks,
compute_loss=compute_loss)
# Update best mAP
fi = fitness(np.array(results).reshape(1, -1)) # weighted combination of [P, R, mAP@.5, mAP@.5-.95]
if fi > best_fitness:
best_fitness = fi
log_vals = list(mloss) + list(results) + lr
callbacks.run('on_fit_epoch_end', log_vals, epoch, best_fitness, fi)
# Save model
if (not nosave) or (final_epoch and not evolve): # if save
ckpt = {'epoch': epoch,
'best_fitness': best_fitness,
'model': deepcopy(de_parallel(model)).half(),
'ema': deepcopy(ema.ema).half(),
'updates': ema.updates,
'optimizer': optimizer.state_dict(),
'wandb_id': loggers.wandb.wandb_run.id if loggers.wandb else None}
# Save last, best and delete
torch.save(ckpt, last)
if best_fitness == fi:
torch.save(ckpt, best)
if (epoch > 0) and (opt.save_period > 0) and (epoch % opt.save_period == 0):
torch.save(ckpt, w / f'epoch{epoch}.pt')
del ckpt
callbacks.run('on_model_save', last, epoch, final_epoch, best_fitness, fi)
# Stop Single-GPU
if RANK == -1 and stopper(epoch=epoch, fitness=fi):
break
# Stop DDP TODO: known issues shttps://github.com/ultralytics/yolov5/pull/4576
# stop = stopper(epoch=epoch, fitness=fi)
# if RANK == 0:
# dist.broadcast_object_list([stop], 0) # broadcast 'stop' to all ranks
# Stop DPP
# with torch_distributed_zero_first(RANK):
# if stop:
# break # must break all DDP ranks
# end epoch ----------------------------------------------------------------------------------------------------
# end training -----------------------------------------------------------------------------------------------------
if RANK in [-1, 0]:
LOGGER.info(f'\n{epoch - start_epoch + 1} epochs completed in {(time.time() - t0) / 3600:.3f} hours.')
for f in last, best:
if f.exists():
strip_optimizer(f) # strip optimizers
if f is best:
LOGGER.info(f'\nValidating {f}...')
results, _, _ = val.run(data_dict,
batch_size=batch_size // WORLD_SIZE * 2,
imgsz=imgsz,
model=attempt_load(f, device).half(),
iou_thres=0.65 if is_coco else 0.60, # best pycocotools results at 0.65
single_cls=single_cls,
dataloader=val_loader,
save_dir=save_dir,
save_json=is_coco,
verbose=True,
plots=True,
callbacks=callbacks,
compute_loss=compute_loss) # val best model with plots
callbacks.run('on_train_end', last, best, plots, epoch)
LOGGER.info(f"Results saved to {colorstr('bold', save_dir)}")
torch.cuda.empty_cache()
return results
def parse_opt(known=False):
parser = argparse.ArgumentParser()
parser.add_argument('--weights', type=str, default=ROOT / 'yolov5s.pt', help='initial weights path')
parser.add_argument('--cfg', type=str, default='', help='model.yaml path')
parser.add_argument('--data', type=str, default=ROOT / 'data/coco128.yaml', help='dataset.yaml path')
parser.add_argument('--hyp', type=str, default=ROOT / 'data/hyps/hyp.scratch.yaml', help='hyperparameters path')
parser.add_argument('--epochs', type=int, default=300)
parser.add_argument('--batch-size', type=int, default=16, help='total batch size for all GPUs')
parser.add_argument('--imgsz', '--img', '--img-size', type=int, default=640, help='train, val image size (pixels)')
parser.add_argument('--rect', action='store_true', help='rectangular training')
parser.add_argument('--resume', nargs='?', const=True, default=False, help='resume most recent training')
parser.add_argument('--nosave', action='store_true', help='only save final checkpoint')
parser.add_argument('--noval', action='store_true', help='only validate final epoch')
parser.add_argument('--noautoanchor', action='store_true', help='disable autoanchor check')
parser.add_argument('--evolve', type=int, nargs='?', const=300, help='evolve hyperparameters for x generations')
parser.add_argument('--bucket', type=str, default='', help='gsutil bucket')
parser.add_argument('--cache', type=str, nargs='?', const='ram', help='--cache images in "ram" (default) or "disk"')
parser.add_argument('--image-weights', action='store_true', help='use weighted image selection for training')
parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
parser.add_argument('--multi-scale', action='store_true', help='vary img-size +/- 50%%')
parser.add_argument('--single-cls', action='store_true', help='train multi-class data as single-class')
parser.add_argument('--adam', action='store_true', help='use torch.optim.Adam() optimizer')
parser.add_argument('--sync-bn', action='store_true', help='use SyncBatchNorm, only available in DDP mode')
parser.add_argument('--workers', type=int, default=8, help='maximum number of dataloader workers')
parser.add_argument('--project', default=ROOT / 'runs/train', help='save to project/name')
parser.add_argument('--name', default='exp', help='save to project/name')
parser.add_argument('--exist-ok', action='store_true', help='existing project/name ok, do not increment')
parser.add_argument('--quad', action='store_true', help='quad dataloader')
parser.add_argument('--linear-lr', action='store_true', help='linear LR')
parser.add_argument('--label-smoothing', type=float, default=0.0, help='Label smoothing epsilon')
parser.add_argument('--patience', type=int, default=100, help='EarlyStopping patience (epochs without improvement)')
parser.add_argument('--freeze', type=int, default=0, help='Number of layers to freeze. backbone=10, all=24')
parser.add_argument('--save-period', type=int, default=-1, help='Save checkpoint every x epochs (disabled if < 1)')
parser.add_argument('--local_rank', type=int, default=-1, help='DDP parameter, do not modify')
# Weights & Biases arguments
parser.add_argument('--entity', default=None, help='W&B: Entity')
parser.add_argument('--upload_dataset', action='store_true', help='W&B: Upload dataset as artifact table')
parser.add_argument('--bbox_interval', type=int, default=-1, help='W&B: Set bounding-box image logging interval')
parser.add_argument('--artifact_alias', type=str, default='latest', help='W&B: Version of dataset artifact to use')
opt = parser.parse_known_args()[0] if known else parser.parse_args()
return opt
def main(opt, callbacks=Callbacks()):
# Checks
set_logging(RANK)
if RANK in [-1, 0]:
print_args(FILE.stem, opt)
check_git_status()
check_requirements(exclude=['thop'])
# Resume
if opt.resume and not check_wandb_resume(opt) and not opt.evolve: # resume an interrupted run
ckpt = opt.resume if isinstance(opt.resume, str) else get_latest_run() # specified or most recent path
assert os.path.isfile(ckpt), 'ERROR: --resume checkpoint does not exist'
with open(Path(ckpt).parent.parent / 'opt.yaml', errors='ignore') as f:
opt = argparse.Namespace(**yaml.safe_load(f)) # replace
opt.cfg, opt.weights, opt.resume = '', ckpt, True # reinstate
LOGGER.info(f'Resuming training from {ckpt}')
else:
opt.data, opt.cfg, opt.hyp, opt.weights, opt.project = \
check_file(opt.data), check_yaml(opt.cfg), check_yaml(opt.hyp), str(opt.weights), str(opt.project) # checks
assert len(opt.cfg) or len(opt.weights), 'either --cfg or --weights must be specified'
if opt.evolve:
opt.project = str(ROOT / 'runs/evolve')
opt.exist_ok, opt.resume = opt.resume, False # pass resume to exist_ok and disable resume
opt.save_dir = str(increment_path(Path(opt.project) / opt.name, exist_ok=opt.exist_ok))
# DDP mode
device = select_device(opt.device, batch_size=opt.batch_size)
if LOCAL_RANK != -1:
assert torch.cuda.device_count() > LOCAL_RANK, 'insufficient CUDA devices for DDP command'
assert opt.batch_size % WORLD_SIZE == 0, '--batch-size must be multiple of CUDA device count'
assert not opt.image_weights, '--image-weights argument is not compatible with DDP training'
assert not opt.evolve, '--evolve argument is not compatible with DDP training'
torch.cuda.set_device(LOCAL_RANK)
device = torch.device('cuda', LOCAL_RANK)
dist.init_process_group(backend="nccl" if dist.is_nccl_available() else "gloo")
# Train
if not opt.evolve:
train(opt.hyp, opt, device, callbacks)
if WORLD_SIZE > 1 and RANK == 0:
LOGGER.info('Destroying process group... ')
dist.destroy_process_group()
# Evolve hyperparameters (optional)
else:
# Hyperparameter evolution metadata (mutation scale 0-1, lower_limit, upper_limit)
meta = {'lr0': (1, 1e-5, 1e-1), # initial learning rate (SGD=1E-2, Adam=1E-3)
'lrf': (1, 0.01, 1.0), # final OneCycleLR learning rate (lr0 * lrf)
'momentum': (0.3, 0.6, 0.98), # SGD momentum/Adam beta1
'weight_decay': (1, 0.0, 0.001), # optimizer weight decay
'warmup_epochs': (1, 0.0, 5.0), # warmup epochs (fractions ok)
'warmup_momentum': (1, 0.0, 0.95), # warmup initial momentum
'warmup_bias_lr': (1, 0.0, 0.2), # warmup initial bias lr
'box': (1, 0.02, 0.2), # box loss gain
'cls': (1, 0.2, 4.0), # cls loss gain
'cls_pw': (1, 0.5, 2.0), # cls BCELoss positive_weight
'obj': (1, 0.2, 4.0), # obj loss gain (scale with pixels)
'obj_pw': (1, 0.5, 2.0), # obj BCELoss positive_weight
'iou_t': (0, 0.1, 0.7), # IoU training threshold
'anchor_t': (1, 2.0, 8.0), # anchor-multiple threshold
'anchors': (2, 2.0, 10.0), # anchors per output grid (0 to ignore)
'fl_gamma': (0, 0.0, 2.0), # focal loss gamma (efficientDet default gamma=1.5)
'hsv_h': (1, 0.0, 0.1), # image HSV-Hue augmentation (fraction)
'hsv_s': (1, 0.0, 0.9), # image HSV-Saturation augmentation (fraction)
'hsv_v': (1, 0.0, 0.9), # image HSV-Value augmentation (fraction)
'degrees': (1, 0.0, 45.0), # image rotation (+/- deg)
'translate': (1, 0.0, 0.9), # image translation (+/- fraction)
'scale': (1, 0.0, 0.9), # image scale (+/- gain)
'shear': (1, 0.0, 10.0), # image shear (+/- deg)
'perspective': (0, 0.0, 0.001), # image perspective (+/- fraction), range 0-0.001
'flipud': (1, 0.0, 1.0), # image flip up-down (probability)
'fliplr': (0, 0.0, 1.0), # image flip left-right (probability)
'mosaic': (1, 0.0, 1.0), # image mixup (probability)
'mixup': (1, 0.0, 1.0), # image mixup (probability)
'copy_paste': (1, 0.0, 1.0)} # segment copy-paste (probability)
with open(opt.hyp, errors='ignore') as f:
hyp = yaml.safe_load(f) # load hyps dict
if 'anchors' not in hyp: # anchors commented in hyp.yaml
hyp['anchors'] = 3
opt.noval, opt.nosave, save_dir = True, True, Path(opt.save_dir) # only val/save final epoch
# ei = [isinstance(x, (int, float)) for x in hyp.values()] # evolvable indices
evolve_yaml, evolve_csv = save_dir / 'hyp_evolve.yaml', save_dir / 'evolve.csv'
if opt.bucket:
os.system(f'gsutil cp gs://{opt.bucket}/evolve.csv {save_dir}') # download evolve.csv if exists
for _ in range(opt.evolve): # generations to evolve
if evolve_csv.exists(): # if evolve.csv exists: select best hyps and mutate
# Select parent(s)
parent = 'single' # parent selection method: 'single' or 'weighted'
x = np.loadtxt(evolve_csv, ndmin=2, delimiter=',', skiprows=1)
n = min(5, len(x)) # number of previous results to consider
x = x[np.argsort(-fitness(x))][:n] # top n mutations
w = fitness(x) - fitness(x).min() + 1E-6 # weights (sum > 0)
if parent == 'single' or len(x) == 1:
# x = x[random.randint(0, n - 1)] # random selection
x = x[random.choices(range(n), weights=w)[0]] # weighted selection
elif parent == 'weighted':
x = (x * w.reshape(n, 1)).sum(0) / w.sum() # weighted combination
# Mutate
mp, s = 0.8, 0.2 # mutation probability, sigma
npr = np.random
npr.seed(int(time.time()))
g = np.array([meta[k][0] for k in hyp.keys()]) # gains 0-1
ng = len(meta)
v = np.ones(ng)
while all(v == 1): # mutate until a change occurs (prevent duplicates)
v = (g * (npr.random(ng) < mp) * npr.randn(ng) * npr.random() * s + 1).clip(0.3, 3.0)
for i, k in enumerate(hyp.keys()): # plt.hist(v.ravel(), 300)
hyp[k] = float(x[i + 7] * v[i]) # mutate
# Constrain to limits
for k, v in meta.items():
hyp[k] = max(hyp[k], v[1]) # lower limit
hyp[k] = min(hyp[k], v[2]) # upper limit
hyp[k] = round(hyp[k], 5) # significant digits
# Train mutation
results = train(hyp.copy(), opt, device, callbacks)
# Write mutation results
print_mutation(results, hyp.copy(), save_dir, opt.bucket)
# Plot results
plot_evolve(evolve_csv)
print(f'Hyperparameter evolution finished\n'
f"Results saved to {colorstr('bold', save_dir)}\n"
f'Use best hyperparameters example: $ python train.py --hyp {evolve_yaml}')
def run(**kwargs):
# Usage: import train; train.run(data='coco128.yaml', imgsz=320, weights='yolov5m.pt')
opt = parse_opt(True)
for k, v in kwargs.items():
setattr(opt, k, v)
main(opt)
if __name__ == "__main__":
opt = parse_opt()
main(opt)
tutorial.ipynb 0 → 100644
View file @ a7b29f47
{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"name": "YOLOv5 Tutorial",
"provenance": [],
"collapsed_sections": [],
"include_colab_link": true
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
},
"accelerator": "GPU",
"widgets": {
"application/vnd.jupyter.widget-state+json": {
"484511f272e64eab8b42e68dac5f7a66": {
"model_module": "@jupyter-widgets/controls",
"model_name": "HBoxModel",
"model_module_version": "1.5.0",
"state": {
"_view_name": "HBoxView",
"_dom_classes": [],
"_model_name": "HBoxModel",
"_view_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_view_count": null,
"_view_module_version": "1.5.0",
"box_style": "",
"layout": "IPY_MODEL_78cceec059784f2bb36988d3336e4d56",
"_model_module": "@jupyter-widgets/controls",
"children": [
"IPY_MODEL_ab93d8b65c134605934ff9ec5efb1bb6",
"IPY_MODEL_30df865ded4c434191bce772c9a82f3a",
"IPY_MODEL_20cdc61eb3404f42a12b37901b0d85fb"
]
}
},
"78cceec059784f2bb36988d3336e4d56": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"model_module_version": "1.2.0",
"state": {
"_view_name": "LayoutView",
"grid_template_rows": null,
"right": null,
"justify_content": null,
"_view_module": "@jupyter-widgets/base",
"overflow": null,
"_model_module_version": "1.2.0",
"_view_count": null,
"flex_flow": null,
"width": null,
"min_width": null,
"border": null,
"align_items": null,
"bottom": null,
"_model_module": "@jupyter-widgets/base",
"top": null,
"grid_column": null,
"overflow_y": null,
"overflow_x": null,
"grid_auto_flow": null,
"grid_area": null,
"grid_template_columns": null,
"flex": null,
"_model_name": "LayoutModel",
"justify_items": null,
"grid_row": null,
"max_height": null,
"align_content": null,
"visibility": null,
"align_self": null,
"height": null,
"min_height": null,
"padding": null,
"grid_auto_rows": null,
"grid_gap": null,
"max_width": null,
"order": null,
"_view_module_version": "1.2.0",
"grid_template_areas": null,
"object_position": null,
"object_fit": null,
"grid_auto_columns": null,
"margin": null,
"display": null,
"left": null
}
},
"ab93d8b65c134605934ff9ec5efb1bb6": {
"model_module": "@jupyter-widgets/controls",
"model_name": "HTMLModel",
"model_module_version": "1.5.0",
"state": {
"_view_name": "HTMLView",
"style": "IPY_MODEL_2d7239993a9645b09b221405ac682743",
"_dom_classes": [],
"description": "",
"_model_name": "HTMLModel",
"placeholder": "​",
"_view_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"value": "100%",
"_view_count": null,
"_view_module_version": "1.5.0",
"description_tooltip": null,
"_model_module": "@jupyter-widgets/controls",
"layout": "IPY_MODEL_17b5a87f92104ec7ab96bf507637d0d2"
}
},
"30df865ded4c434191bce772c9a82f3a": {
"model_module": "@jupyter-widgets/controls",
"model_name": "FloatProgressModel",
"model_module_version": "1.5.0",
"state": {
"_view_name": "ProgressView",
"style": "IPY_MODEL_2358bfb2270247359e94b066b3cc3d1f",
"_dom_classes": [],
"description": "",
"_model_name": "FloatProgressModel",
"bar_style": "success",
"max": 818322941,
"_view_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"value": 818322941,
"_view_count": null,
"_view_module_version": "1.5.0",
"orientation": "horizontal",
"min": 0,
"description_tooltip": null,
"_model_module": "@jupyter-widgets/controls",
"layout": "IPY_MODEL_3e984405db654b0b83b88b2db08baffd"
}
},
"20cdc61eb3404f42a12b37901b0d85fb": {
"model_module": "@jupyter-widgets/controls",
"model_name": "HTMLModel",
"model_module_version": "1.5.0",
"state": {
"_view_name": "HTMLView",
"style": "IPY_MODEL_654d8a19b9f949c6bbdaf8b0875c931e",
"_dom_classes": [],
"description": "",
"_model_name": "HTMLModel",
"placeholder": "​",
"_view_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"value": " 780M/780M [00:33&lt;00:00, 24.4MB/s]",
"_view_count": null,
"_view_module_version": "1.5.0",
"description_tooltip": null,
"_model_module": "@jupyter-widgets/controls",
"layout": "IPY_MODEL_896030c5d13b415aaa05032818d81a6e"
}
},
"2d7239993a9645b09b221405ac682743": {
"model_module": "@jupyter-widgets/controls",
"model_name": "DescriptionStyleModel",
"model_module_version": "1.5.0",
"state": {
"_view_name": "StyleView",
"_model_name": "DescriptionStyleModel",
"description_width": "",
"_view_module": "@jupyter-widgets/base",
"_model_module_version": "1.5.0",
"_view_count": null,
"_view_module_version": "1.2.0",
"_model_module": "@jupyter-widgets/controls"
}
},
"17b5a87f92104ec7ab96bf507637d0d2": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"model_module_version": "1.2.0",
"state": {
"_view_name": "LayoutView",
"grid_template_rows": null,
"right": null,
"justify_content": null,
"_view_module": "@jupyter-widgets/base",
"overflow": null,
"_model_module_version": "1.2.0",
"_view_count": null,
"flex_flow": null,
"width": null,
"min_width": null,
"border": null,
"align_items": null,
"bottom": null,
"_model_module": "@jupyter-widgets/base",
"top": null,
"grid_column": null,
"overflow_y": null,
"overflow_x": null,
"grid_auto_flow": null,
"grid_area": null,
"grid_template_columns": null,
"flex": null,
"_model_name": "LayoutModel",
"justify_items": null,
"grid_row": null,
"max_height": null,
"align_content": null,
"visibility": null,
"align_self": null,
"height": null,
"min_height": null,
"padding": null,
"grid_auto_rows": null,
"grid_gap": null,
"max_width": null,
"order": null,
"_view_module_version": "1.2.0",
"grid_template_areas": null,
"object_position": null,
"object_fit": null,
"grid_auto_columns": null,
"margin": null,
"display": null,
"left": null
}
},
"2358bfb2270247359e94b066b3cc3d1f": {
"model_module": "@jupyter-widgets/controls",
"model_name": "ProgressStyleModel",
"model_module_version": "1.5.0",
"state": {
"_view_name": "StyleView",
"_model_name": "ProgressStyleModel",
"description_width": "",
"_view_module": "@jupyter-widgets/base",
"_model_module_version": "1.5.0",
"_view_count": null,
"_view_module_version": "1.2.0",
"bar_color": null,
"_model_module": "@jupyter-widgets/controls"
}
},
"3e984405db654b0b83b88b2db08baffd": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"model_module_version": "1.2.0",
"state": {
"_view_name": "LayoutView",
"grid_template_rows": null,
"right": null,
"justify_content": null,
"_view_module": "@jupyter-widgets/base",
"overflow": null,
"_model_module_version": "1.2.0",
"_view_count": null,
"flex_flow": null,
"width": null,
"min_width": null,
"border": null,
"align_items": null,
"bottom": null,
"_model_module": "@jupyter-widgets/base",
"top": null,
"grid_column": null,
"overflow_y": null,
"overflow_x": null,
"grid_auto_flow": null,
"grid_area": null,
"grid_template_columns": null,
"flex": null,
"_model_name": "LayoutModel",
"justify_items": null,
"grid_row": null,
"max_height": null,
"align_content": null,
"visibility": null,
"align_self": null,
"height": null,
"min_height": null,
"padding": null,
"grid_auto_rows": null,
"grid_gap": null,
"max_width": null,
"order": null,
"_view_module_version": "1.2.0",
"grid_template_areas": null,
"object_position": null,
"object_fit": null,
"grid_auto_columns": null,
"margin": null,
"display": null,
"left": null
}
},
"654d8a19b9f949c6bbdaf8b0875c931e": {
"model_module": "@jupyter-widgets/controls",
"model_name": "DescriptionStyleModel",
"model_module_version": "1.5.0",
"state": {
"_view_name": "StyleView",
"_model_name": "DescriptionStyleModel",
"description_width": "",
"_view_module": "@jupyter-widgets/base",
"_model_module_version": "1.5.0",
"_view_count": null,
"_view_module_version": "1.2.0",
"_model_module": "@jupyter-widgets/controls"
}
},
"896030c5d13b415aaa05032818d81a6e": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"model_module_version": "1.2.0",
"state": {
"_view_name": "LayoutView",
"grid_template_rows": null,
"right": null,
"justify_content": null,
"_view_module": "@jupyter-widgets/base",
"overflow": null,
"_model_module_version": "1.2.0",
"_view_count": null,
"flex_flow": null,
"width": null,
"min_width": null,
"border": null,
"align_items": null,
"bottom": null,
"_model_module": "@jupyter-widgets/base",
"top": null,
"grid_column": null,
"overflow_y": null,
"overflow_x": null,
"grid_auto_flow": null,
"grid_area": null,
"grid_template_columns": null,
"flex": null,
"_model_name": "LayoutModel",
"justify_items": null,
"grid_row": null,
"max_height": null,
"align_content": null,
"visibility": null,
"align_self": null,
"height": null,
"min_height": null,
"padding": null,
"grid_auto_rows": null,
"grid_gap": null,
"max_width": null,
"order": null,
"_view_module_version": "1.2.0",
"grid_template_areas": null,
"object_position": null,
"object_fit": null,
"grid_auto_columns": null,
"margin": null,
"display": null,
"left": null
}
}
}
}
},
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "view-in-github",
"colab_type": "text"
},
"source": [
"<a href=\"https://colab.research.google.com/github/ultralytics/yolov5/blob/master/tutorial.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "t6MPjfT5NrKQ"
},
"source": [
"<a align=\"left\" href=\"https://ultralytics.com/yolov5\" target=\"_blank\">\n",
"<img width=\"1024\", src=\"https://user-images.githubusercontent.com/26833433/125273437-35b3fc00-e30d-11eb-9079-46f313325424.png\"></a>\n",
"\n",
"This is the **official YOLOv5 🚀 notebook** by **Ultralytics**, and is freely available for redistribution under the [GPL-3.0 license](https://choosealicense.com/licenses/gpl-3.0/). \n",
"For more information please visit https://github.com/ultralytics/yolov5 and https://ultralytics.com. Thank you!"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "7mGmQbAO5pQb"
},
"source": [
"# Setup\n",
"\n",
"Clone repo, install dependencies and check PyTorch and GPU."
]
},
{
"cell_type": "code",
"metadata": {
"id": "wbvMlHd_QwMG",
"colab": {
"base_uri": "https://localhost:8080/"
},
"outputId": "4d67116a-43e9-4d84-d19e-1edd83f23a04"
},
"source": [
"!git clone https://github.com/ultralytics/yolov5 # clone repo\n",
"%cd yolov5\n",
"%pip install -qr requirements.txt # install dependencies\n",
"\n",
"import torch\n",
"from IPython.display import Image, clear_output # to display images\n",
"\n",
"clear_output()\n",
"print(f\"Setup complete. Using torch {torch.__version__} ({torch.cuda.get_device_properties(0).name if torch.cuda.is_available() else 'CPU'})\")"
],
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"text": [
"Setup complete. Using torch 1.9.0+cu102 (Tesla V100-SXM2-16GB)\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "4JnkELT0cIJg"
},
"source": [
"# 1. Inference\n",
"\n",
"`detect.py` runs YOLOv5 inference on a variety of sources, downloading models automatically from the [latest YOLOv5 release](https://github.com/ultralytics/yolov5/releases), and saving results to `runs/detect`. Example inference sources are:\n",
"\n",
"```shell\n",
"python detect.py --source 0 # webcam\n",
" file.jpg # image \n",
" file.mp4 # video\n",
" path/ # directory\n",
" path/*.jpg # glob\n",
" 'https://youtu.be/NUsoVlDFqZg' # YouTube\n",
" 'rtsp://example.com/media.mp4' # RTSP, RTMP, HTTP stream\n",
"```"
]
},
{
"cell_type": "code",
"metadata": {
"id": "zR9ZbuQCH7FX",
"colab": {
"base_uri": "https://localhost:8080/"
},
"outputId": "8b728908-81ab-4861-edb0-4d0c46c439fb"
},
"source": [
"!python detect.py --weights yolov5s.pt --img 640 --conf 0.25 --source data/images/\n",
"Image(filename='runs/detect/exp/zidane.jpg', width=600)"
],
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"text": [
"\u001b[34m\u001b[1mdetect: \u001b[0mweights=['yolov5s.pt'], source=data/images/, imgsz=640, conf_thres=0.25, iou_thres=0.45, max_det=1000, device=, view_img=False, save_txt=False, save_conf=False, save_crop=False, nosave=False, classes=None, agnostic_nms=False, augment=False, visualize=False, update=False, project=runs/detect, name=exp, exist_ok=False, line_thickness=3, hide_labels=False, hide_conf=False, half=False\n",
"YOLOv5 🚀 v5.0-367-g01cdb76 torch 1.9.0+cu102 CUDA:0 (Tesla V100-SXM2-16GB, 16160.5MB)\n",
"\n",
"Fusing layers... \n",
"Model Summary: 224 layers, 7266973 parameters, 0 gradients\n",
"image 1/2 /content/yolov5/data/images/bus.jpg: 640x480 4 persons, 1 bus, 1 fire hydrant, Done. (0.007s)\n",
"image 2/2 /content/yolov5/data/images/zidane.jpg: 384x640 2 persons, 2 ties, Done. (0.007s)\n",
"Results saved to \u001b[1mruns/detect/exp\u001b[0m\n",
"Done. (0.091s)\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "hkAzDWJ7cWTr"
},
"source": [
"&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;\n",
"<img align=\"left\" src=\"https://user-images.githubusercontent.com/26833433/127574988-6a558aa1-d268-44b9-bf6b-62d4c605cc72.jpg\" width=\"600\">"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "0eq1SMWl6Sfn"
},
"source": [
"# 2. Validate\n",
"Validate a model's accuracy on [COCO](https://cocodataset.org/#home) val or test-dev datasets. Models are downloaded automatically from the [latest YOLOv5 release](https://github.com/ultralytics/yolov5/releases). To show results by class use the `--verbose` flag. Note that `pycocotools` metrics may be ~1% better than the equivalent repo metrics, as is visible below, due to slight differences in mAP computation."
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "eyTZYGgRjnMc"
},
"source": [
"## COCO val2017\n",
"Download [COCO val 2017](https://github.com/ultralytics/yolov5/blob/74b34872fdf41941cddcf243951cdb090fbac17b/data/coco.yaml#L14) dataset (1GB - 5000 images), and test model accuracy."
]
},
{
"cell_type": "code",
"metadata": {
"id": "WQPtK1QYVaD_",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 48,
"referenced_widgets": [
"484511f272e64eab8b42e68dac5f7a66",
"78cceec059784f2bb36988d3336e4d56",
"ab93d8b65c134605934ff9ec5efb1bb6",
"30df865ded4c434191bce772c9a82f3a",
"20cdc61eb3404f42a12b37901b0d85fb",
"2d7239993a9645b09b221405ac682743",
"17b5a87f92104ec7ab96bf507637d0d2",
"2358bfb2270247359e94b066b3cc3d1f",
"3e984405db654b0b83b88b2db08baffd",
"654d8a19b9f949c6bbdaf8b0875c931e",
"896030c5d13b415aaa05032818d81a6e"
]
},
"outputId": "7e6f5c96-c819-43e1-cd03-d3b9878cf8de"
},
"source": [
"# Download COCO val2017\n",
"torch.hub.download_url_to_file('https://github.com/ultralytics/yolov5/releases/download/v1.0/coco2017val.zip', 'tmp.zip')\n",
"!unzip -q tmp.zip -d ../datasets && rm tmp.zip"
],
"execution_count": null,
"outputs": [
{
"output_type": "display_data",
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "484511f272e64eab8b42e68dac5f7a66",
"version_minor": 0,
"version_major": 2
},
"text/plain": [
" 0%| | 0.00/780M [00:00<?, ?B/s]"
]
},
"metadata": {
"tags": []
}
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "X58w8JLpMnjH",
"colab": {
"base_uri": "https://localhost:8080/"
},
"outputId": "3dd0e2fc-aecf-4108-91b1-6392da1863cb"
},
"source": [
"# Run YOLOv5x on COCO val2017\n",
"!python val.py --weights yolov5x.pt --data coco.yaml --img 640 --iou 0.65 --half"
],
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"text": [
"\u001b[34m\u001b[1mval: \u001b[0mdata=./data/coco.yaml, weights=['yolov5x.pt'], batch_size=32, imgsz=640, conf_thres=0.001, iou_thres=0.65, task=val, device=, single_cls=False, augment=False, verbose=False, save_txt=False, save_hybrid=False, save_conf=False, save_json=True, project=runs/val, name=exp, exist_ok=False, half=True\n",
"YOLOv5 🚀 v5.0-367-g01cdb76 torch 1.9.0+cu102 CUDA:0 (Tesla V100-SXM2-16GB, 16160.5MB)\n",
"\n",
"Downloading https://github.com/ultralytics/yolov5/releases/download/v5.0/yolov5x.pt to yolov5x.pt...\n",
"100% 168M/168M [00:08<00:00, 20.6MB/s]\n",
"\n",
"Fusing layers... \n",
"Model Summary: 476 layers, 87730285 parameters, 0 gradients\n",
"\u001b[34m\u001b[1mval: \u001b[0mScanning '../datasets/coco/val2017' images and labels...4952 found, 48 missing, 0 empty, 0 corrupted: 100% 5000/5000 [00:01<00:00, 2749.96it/s]\n",
"\u001b[34m\u001b[1mval: \u001b[0mNew cache created: ../datasets/coco/val2017.cache\n",
" Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 157/157 [01:08<00:00, 2.28it/s]\n",
" all 5000 36335 0.746 0.626 0.68 0.49\n",
"Speed: 0.1ms pre-process, 5.1ms inference, 1.6ms NMS per image at shape (32, 3, 640, 640)\n",
"\n",
"Evaluating pycocotools mAP... saving runs/val/exp/yolov5x_predictions.json...\n",
"loading annotations into memory...\n",
"Done (t=0.46s)\n",
"creating index...\n",
"index created!\n",
"Loading and preparing results...\n",
"DONE (t=4.94s)\n",
"creating index...\n",
"index created!\n",
"Running per image evaluation...\n",
"Evaluate annotation type *bbox*\n",
"DONE (t=83.60s).\n",
"Accumulating evaluation results...\n",
"DONE (t=13.22s).\n",
" Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.504\n",
" Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.688\n",
" Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.546\n",
" Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.351\n",
" Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.551\n",
" Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.644\n",
" Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.382\n",
" Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.629\n",
" Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.681\n",
" Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.524\n",
" Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.735\n",
" Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.827\n",
"Results saved to \u001b[1mruns/val/exp\u001b[0m\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "rc_KbFk0juX2"
},
"source": [
"## COCO test-dev2017\n",
"Download [COCO test2017](https://github.com/ultralytics/yolov5/blob/74b34872fdf41941cddcf243951cdb090fbac17b/data/coco.yaml#L15) dataset (7GB - 40,000 images), to test model accuracy on test-dev set (**20,000 images, no labels**). Results are saved to a `*.json` file which should be **zipped** and submitted to the evaluation server at https://competitions.codalab.org/competitions/20794."
]
},
{
"cell_type": "code",
"metadata": {
"id": "V0AJnSeCIHyJ"
},
"source": [
"# Download COCO test-dev2017\n",
"torch.hub.download_url_to_file('https://github.com/ultralytics/yolov5/releases/download/v1.0/coco2017labels.zip', 'tmp.zip')\n",
"!unzip -q tmp.zip -d ../ && rm tmp.zip # unzip labels\n",
"!f=\"test2017.zip\" && curl http://images.cocodataset.org/zips/$f -o $f && unzip -q $f && rm $f # 7GB, 41k images\n",
"%mv ./test2017 ../coco/images # move to /coco"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "29GJXAP_lPrt"
},
"source": [
"# Run YOLOv5s on COCO test-dev2017 using --task test\n",
"!python val.py --weights yolov5s.pt --data coco.yaml --task test"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {
"id": "ZY2VXXXu74w5"
},
"source": [
"# 3. Train\n",
"\n",
"<p align=\"\"><a href=\"https://roboflow.com/?ref=ultralytics\"><img width=\"1000\" src=\"https://uploads-ssl.webflow.com/5f6bc60e665f54545a1e52a5/615627e5824c9c6195abfda9_computer-vision-cycle.png\"/></a></p>\n",
"Close the active learning loop by sampling images from your inference conditions with the `roboflow` pip package\n",
"<br><br>\n",
"\n",
"Train a YOLOv5s model on the [COCO128](https://www.kaggle.com/ultralytics/coco128) dataset with `--data coco128.yaml`, starting from pretrained `--weights yolov5s.pt`, or from randomly initialized `--weights '' --cfg yolov5s.yaml`.\n",
"\n",
"- **Pretrained [Models](https://github.com/ultralytics/yolov5/tree/master/models)** are downloaded\n",
"automatically from the [latest YOLOv5 release](https://github.com/ultralytics/yolov5/releases)\n",
"- **[Datasets](https://github.com/ultralytics/yolov5/tree/master/data)** available for autodownload include: [COCO](https://github.com/ultralytics/yolov5/blob/master/data/coco.yaml), [COCO128](https://github.com/ultralytics/yolov5/blob/master/data/coco128.yaml), [VOC](https://github.com/ultralytics/yolov5/blob/master/data/VOC.yaml), [Argoverse](https://github.com/ultralytics/yolov5/blob/master/data/Argoverse.yaml), [VisDrone](https://github.com/ultralytics/yolov5/blob/master/data/VisDrone.yaml), [GlobalWheat](https://github.com/ultralytics/yolov5/blob/master/data/GlobalWheat2020.yaml), [xView](https://github.com/ultralytics/yolov5/blob/master/data/xView.yaml), [Objects365](https://github.com/ultralytics/yolov5/blob/master/data/Objects365.yaml), [SKU-110K](https://github.com/ultralytics/yolov5/blob/master/data/SKU-110K.yaml).\n",
"- **Training Results** are saved to `runs/train/` with incrementing run directories, i.e. `runs/train/exp2`, `runs/train/exp3` etc.\n",
"<br><br>\n",
"\n",
"## Train on Custom Data with Roboflow 🌟 NEW\n",
"\n",
"[Roboflow](https://roboflow.com/?ref=ultralytics) enables you to easily **organize, label, and prepare** a high quality dataset with your own custom data. Roboflow also makes it easy to establish an active learning pipeline, collaborate with your team on dataset improvement, and integrate directly into your model building workflow with the `roboflow` pip package.\n",
"\n",
"- Custom Training Example: [https://blog.roboflow.com/how-to-train-yolov5-on-a-custom-dataset/](https://blog.roboflow.com/how-to-train-yolov5-on-a-custom-dataset/?ref=ultralytics)\n",
"- Custom Training Notebook: [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/roboflow-ai/yolov5-custom-training-tutorial/blob/main/yolov5-custom-training.ipynb)\n",
"<br>\n",
"\n",
"<p align=\"\"><a href=\"https://roboflow.com/?ref=ultralytics\"><img width=\"480\" src=\"https://uploads-ssl.webflow.com/5f6bc60e665f54545a1e52a5/6152a275ad4b4ac20cd2e21a_roboflow-annotate.gif\"/></a></p>Label images lightning fast (including with model-assisted labeling)"
]
},
{
"cell_type": "code",
"metadata": {
"id": "bOy5KI2ncnWd"
},
"source": [
"# Tensorboard (optional)\n",
"%load_ext tensorboard\n",
"%tensorboard --logdir runs/train"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "2fLAV42oNb7M"
},
"source": [
"# Weights & Biases (optional)\n",
"%pip install -q wandb\n",
"import wandb\n",
"wandb.login()"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "1NcFxRcFdJ_O",
"colab": {
"base_uri": "https://localhost:8080/"
},
"outputId": "00ea4b14-a75c-44a2-a913-03b431b69de5"
},
"source": [
"# Train YOLOv5s on COCO128 for 3 epochs\n",
"!python train.py --img 640 --batch 16 --epochs 3 --data coco128.yaml --weights yolov5s.pt --cache"
],
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"text": [
"\u001b[34m\u001b[1mtrain: \u001b[0mweights=yolov5s.pt, cfg=, data=coco128.yaml, hyp=data/hyps/hyp.scratch.yaml, epochs=3, batch_size=16, imgsz=640, rect=False, resume=False, nosave=False, noval=False, noautoanchor=False, evolve=None, bucket=, cache=ram, image_weights=False, device=, multi_scale=False, single_cls=False, adam=False, sync_bn=False, workers=8, project=runs/train, entity=None, name=exp, exist_ok=False, quad=False, linear_lr=False, label_smoothing=0.0, upload_dataset=False, bbox_interval=-1, save_period=-1, artifact_alias=latest, local_rank=-1, freeze=0\n",
"\u001b[34m\u001b[1mgithub: \u001b[0mup to date with https://github.com/ultralytics/yolov5 ✅\n",
"YOLOv5 🚀 v5.0-367-g01cdb76 torch 1.9.0+cu102 CUDA:0 (Tesla V100-SXM2-16GB, 16160.5MB)\n",
"\n",
"\u001b[34m\u001b[1mhyperparameters: \u001b[0mlr0=0.01, lrf=0.2, momentum=0.937, weight_decay=0.0005, warmup_epochs=3.0, warmup_momentum=0.8, warmup_bias_lr=0.1, box=0.05, cls=0.5, cls_pw=1.0, obj=1.0, obj_pw=1.0, iou_t=0.2, anchor_t=4.0, fl_gamma=0.0, hsv_h=0.015, hsv_s=0.7, hsv_v=0.4, degrees=0.0, translate=0.1, scale=0.5, shear=0.0, perspective=0.0, flipud=0.0, fliplr=0.5, mosaic=1.0, mixup=0.0, copy_paste=0.0\n",
"\u001b[34m\u001b[1mWeights & Biases: \u001b[0mrun 'pip install wandb' to automatically track and visualize YOLOv5 🚀 runs (RECOMMENDED)\n",
"\u001b[34m\u001b[1mTensorBoard: \u001b[0mStart with 'tensorboard --logdir runs/train', view at http://localhost:6006/\n",
"2021-08-15 14:40:43.449642: I tensorflow/stream_executor/platform/default/dso_loader.cc:53] Successfully opened dynamic library libcudart.so.11.0\n",
"\n",
" from n params module arguments \n",
" 0 -1 1 3520 models.common.Focus [3, 32, 3] \n",
" 1 -1 1 18560 models.common.Conv [32, 64, 3, 2] \n",
" 2 -1 1 18816 models.common.C3 [64, 64, 1] \n",
" 3 -1 1 73984 models.common.Conv [64, 128, 3, 2] \n",
" 4 -1 3 156928 models.common.C3 [128, 128, 3] \n",
" 5 -1 1 295424 models.common.Conv [128, 256, 3, 2] \n",
" 6 -1 3 625152 models.common.C3 [256, 256, 3] \n",
" 7 -1 1 1180672 models.common.Conv [256, 512, 3, 2] \n",
" 8 -1 1 656896 models.common.SPP [512, 512, [5, 9, 13]] \n",
" 9 -1 1 1182720 models.common.C3 [512, 512, 1, False] \n",
" 10 -1 1 131584 models.common.Conv [512, 256, 1, 1] \n",
" 11 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest'] \n",
" 12 [-1, 6] 1 0 models.common.Concat [1] \n",
" 13 -1 1 361984 models.common.C3 [512, 256, 1, False] \n",
" 14 -1 1 33024 models.common.Conv [256, 128, 1, 1] \n",
" 15 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest'] \n",
" 16 [-1, 4] 1 0 models.common.Concat [1] \n",
" 17 -1 1 90880 models.common.C3 [256, 128, 1, False] \n",
" 18 -1 1 147712 models.common.Conv [128, 128, 3, 2] \n",
" 19 [-1, 14] 1 0 models.common.Concat [1] \n",
" 20 -1 1 296448 models.common.C3 [256, 256, 1, False] \n",
" 21 -1 1 590336 models.common.Conv [256, 256, 3, 2] \n",
" 22 [-1, 10] 1 0 models.common.Concat [1] \n",
" 23 -1 1 1182720 models.common.C3 [512, 512, 1, False] \n",
" 24 [17, 20, 23] 1 229245 models.yolo.Detect [80, [[10, 13, 16, 30, 33, 23], [30, 61, 62, 45, 59, 119], [116, 90, 156, 198, 373, 326]], [128, 256, 512]]\n",
"Model Summary: 283 layers, 7276605 parameters, 7276605 gradients, 17.1 GFLOPs\n",
"\n",
"Transferred 362/362 items from yolov5s.pt\n",
"Scaled weight_decay = 0.0005\n",
"\u001b[34m\u001b[1moptimizer:\u001b[0m SGD with parameter groups 59 weight, 62 weight (no decay), 62 bias\n",
"\u001b[34m\u001b[1malbumentations: \u001b[0mversion 1.0.3 required by YOLOv5, but version 0.1.12 is currently installed\n",
"\u001b[34m\u001b[1mtrain: \u001b[0mScanning '../datasets/coco128/labels/train2017' images and labels...128 found, 0 missing, 2 empty, 0 corrupted: 100% 128/128 [00:00<00:00, 2440.28it/s]\n",
"\u001b[34m\u001b[1mtrain: \u001b[0mNew cache created: ../datasets/coco128/labels/train2017.cache\n",
"\u001b[34m\u001b[1mtrain: \u001b[0mCaching images (0.1GB ram): 100% 128/128 [00:00<00:00, 302.61it/s]\n",
"\u001b[34m\u001b[1mval: \u001b[0mScanning '../datasets/coco128/labels/train2017.cache' images and labels... 128 found, 0 missing, 2 empty, 0 corrupted: 100% 128/128 [00:00<?, ?it/s]\n",
"\u001b[34m\u001b[1mval: \u001b[0mCaching images (0.1GB ram): 100% 128/128 [00:00<00:00, 142.55it/s]\n",
"[W pthreadpool-cpp.cc:90] Warning: Leaking Caffe2 thread-pool after fork. (function pthreadpool)\n",
"[W pthreadpool-cpp.cc:90] Warning: Leaking Caffe2 thread-pool after fork. (function pthreadpool)\n",
"Plotting labels... \n",
"\n",
"\u001b[34m\u001b[1mautoanchor: \u001b[0mAnalyzing anchors... anchors/target = 4.27, Best Possible Recall (BPR) = 0.9935\n",
"Image sizes 640 train, 640 val\n",
"Using 2 dataloader workers\n",
"Logging results to runs/train/exp\n",
"Starting training for 3 epochs...\n",
"\n",
" Epoch gpu_mem box obj cls labels img_size\n",
" 0/2 3.64G 0.04492 0.0674 0.02213 298 640: 100% 8/8 [00:03<00:00, 2.05it/s]\n",
" Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:00<00:00, 4.70it/s]\n",
" all 128 929 0.686 0.565 0.642 0.421\n",
"\n",
" Epoch gpu_mem box obj cls labels img_size\n",
" 1/2 5.04G 0.04403 0.0611 0.01986 232 640: 100% 8/8 [00:01<00:00, 5.59it/s]\n",
" Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:00<00:00, 4.46it/s]\n",
" all 128 929 0.694 0.563 0.654 0.425\n",
"\n",
" Epoch gpu_mem box obj cls labels img_size\n",
" 2/2 5.04G 0.04616 0.07056 0.02071 214 640: 100% 8/8 [00:01<00:00, 5.94it/s]\n",
" Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00, 1.52it/s]\n",
" all 128 929 0.711 0.562 0.66 0.431\n",
"\n",
"3 epochs completed in 0.005 hours.\n",
"Optimizer stripped from runs/train/exp/weights/last.pt, 14.8MB\n",
"Optimizer stripped from runs/train/exp/weights/best.pt, 14.8MB\n",
"Results saved to \u001b[1mruns/train/exp\u001b[0m\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "15glLzbQx5u0"
},
"source": [
"# 4. Visualize"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "DLI1JmHU7B0l"
},
"source": [
"## Weights & Biases Logging 🌟 NEW\n",
"\n",
"[Weights & Biases](https://wandb.ai/site?utm_campaign=repo_yolo_notebook) (W&B) is now integrated with YOLOv5 for real-time visualization and cloud logging of training runs. This allows for better run comparison and introspection, as well improved visibility and collaboration for teams. To enable W&B `pip install wandb`, and then train normally (you will be guided through setup on first use). \n",
"\n",
"During training you will see live updates at [https://wandb.ai/home](https://wandb.ai/home?utm_campaign=repo_yolo_notebook), and you can create and share detailed [Reports](https://wandb.ai/glenn-jocher/yolov5_tutorial/reports/YOLOv5-COCO128-Tutorial-Results--VmlldzozMDI5OTY) of your results. For more information see the [YOLOv5 Weights & Biases Tutorial](https://github.com/ultralytics/yolov5/issues/1289). \n",
"\n",
"<p align=\"left\"><img width=\"900\" alt=\"Weights & Biases dashboard\" src=\"https://user-images.githubusercontent.com/26833433/135390767-c28b050f-8455-4004-adb0-3b730386e2b2.png\"></p>"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "-WPvRbS5Swl6"
},
"source": [
"## Local Logging\n",
"\n",
"All results are logged by default to `runs/train`, with a new experiment directory created for each new training as `runs/train/exp2`, `runs/train/exp3`, etc. View train and val jpgs to see mosaics, labels, predictions and augmentation effects. Note an Ultralytics **Mosaic Dataloader** is used for training (shown below), which combines 4 images into 1 mosaic during training.\n",
"\n",
"> <img src=\"https://user-images.githubusercontent.com/26833433/131255960-b536647f-7c61-4f60-bbc5-cb2544d71b2a.jpg\" width=\"700\"> \n",
"`train_batch0.jpg` shows train batch 0 mosaics and labels\n",
"\n",
"> <img src=\"https://user-images.githubusercontent.com/26833433/131256748-603cafc7-55d1-4e58-ab26-83657761aed9.jpg\" width=\"700\"> \n",
"`test_batch0_labels.jpg` shows val batch 0 labels\n",
"\n",
"> <img src=\"https://user-images.githubusercontent.com/26833433/131256752-3f25d7a5-7b0f-4bb3-ab78-46343c3800fe.jpg\" width=\"700\"> \n",
"`test_batch0_pred.jpg` shows val batch 0 _predictions_\n",
"\n",
"Training results are automatically logged to [Tensorboard](https://www.tensorflow.org/tensorboard) and [CSV](https://github.com/ultralytics/yolov5/pull/4148) as `results.csv`, which is plotted as `results.png` (below) after training completes. You can also plot any `results.csv` file manually:\n",
"\n",
"```python\n",
"from utils.plots import plot_results \n",
"plot_results('path/to/results.csv') # plot 'results.csv' as 'results.png'\n",
"```\n",
"\n",
"<img align=\"left\" width=\"800\" alt=\"COCO128 Training Results\" src=\"https://user-images.githubusercontent.com/26833433/126906780-8c5e2990-6116-4de6-b78a-367244a33ccf.png\">"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "Zelyeqbyt3GD"
},
"source": [
"# Environments\n",
"\n",
"YOLOv5 may be run in any of the following up-to-date verified environments (with all dependencies including [CUDA](https://developer.nvidia.com/cuda)/[CUDNN](https://developer.nvidia.com/cudnn), [Python](https://www.python.org/) and [PyTorch](https://pytorch.org/) preinstalled):\n",
"\n",
"- **Google Colab and Kaggle** notebooks with free GPU: <a href=\"https://colab.research.google.com/github/ultralytics/yolov5/blob/master/tutorial.ipynb\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"></a> <a href=\"https://www.kaggle.com/ultralytics/yolov5\"><img src=\"https://kaggle.com/static/images/open-in-kaggle.svg\" alt=\"Open In Kaggle\"></a>\n",
"- **Google Cloud** Deep Learning VM. See [GCP Quickstart Guide](https://github.com/ultralytics/yolov5/wiki/GCP-Quickstart)\n",
"- **Amazon** Deep Learning AMI. See [AWS Quickstart Guide](https://github.com/ultralytics/yolov5/wiki/AWS-Quickstart)\n",
"- **Docker Image**. See [Docker Quickstart Guide](https://github.com/ultralytics/yolov5/wiki/Docker-Quickstart) <a href=\"https://hub.docker.com/r/ultralytics/yolov5\"><img src=\"https://img.shields.io/docker/pulls/ultralytics/yolov5?logo=docker\" alt=\"Docker Pulls\"></a>\n"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "6Qu7Iesl0p54"
},
"source": [
"# Status\n",
"\n",
"![CI CPU testing](https://github.com/ultralytics/yolov5/workflows/CI%20CPU%20testing/badge.svg)\n",
"\n",
"If this badge is green, all [YOLOv5 GitHub Actions](https://github.com/ultralytics/yolov5/actions) Continuous Integration (CI) tests are currently passing. CI tests verify correct operation of YOLOv5 training ([train.py](https://github.com/ultralytics/yolov5/blob/master/train.py)), testing ([val.py](https://github.com/ultralytics/yolov5/blob/master/val.py)), inference ([detect.py](https://github.com/ultralytics/yolov5/blob/master/detect.py)) and export ([export.py](https://github.com/ultralytics/yolov5/blob/master/export.py)) on MacOS, Windows, and Ubuntu every 24 hours and on every commit.\n"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "IEijrePND_2I"
},
"source": [
"# Appendix\n",
"\n",
"Optional extras below. Unit tests validate repo functionality and should be run on any PRs submitted.\n"
]
},
{
"cell_type": "code",
"metadata": {
"id": "mcKoSIK2WSzj"
},
"source": [
"# Reproduce\n",
"for x in 'yolov5s', 'yolov5m', 'yolov5l', 'yolov5x':\n",
" !python val.py --weights {x}.pt --data coco.yaml --img 640 --conf 0.25 --iou 0.45 # speed\n",
" !python val.py --weights {x}.pt --data coco.yaml --img 640 --conf 0.001 --iou 0.65 # mAP"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "GMusP4OAxFu6"
},
"source": [
"# PyTorch Hub\n",
"import torch\n",
"\n",
"# Model\n",
"model = torch.hub.load('ultralytics/yolov5', 'yolov5s')\n",
"\n",
"# Images\n",
"dir = 'https://ultralytics.com/images/'\n",
"imgs = [dir + f for f in ('zidane.jpg', 'bus.jpg')] # batch of images\n",
"\n",
"# Inference\n",
"results = model(imgs)\n",
"results.print() # or .show(), .save()"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "FGH0ZjkGjejy"
},
"source": [
"# CI Checks\n",
"%%shell\n",
"export PYTHONPATH=\"$PWD\" # to run *.py. files in subdirectories\n",
"rm -rf runs # remove runs/\n",
"for m in yolov5s; do # models\n",
" python train.py --weights $m.pt --epochs 3 --img 320 --device 0 # train pretrained\n",
" python train.py --weights '' --cfg $m.yaml --epochs 3 --img 320 --device 0 # train scratch\n",
" for d in 0 cpu; do # devices\n",
" python detect.py --weights $m.pt --device $d # detect official\n",
" python detect.py --weights runs/train/exp/weights/best.pt --device $d # detect custom\n",
" python val.py --weights $m.pt --device $d # val official\n",
" python val.py --weights runs/train/exp/weights/best.pt --device $d # val custom\n",
" done\n",
"python hubconf.py # hub\n",
"python models/yolo.py --cfg $m.yaml # build PyTorch model\n",
"python models/tf.py --weights $m.pt # build TensorFlow model\n",
"python export.py --img 128 --batch 1 --weights $m.pt --include torchscript onnx # export\n",
"done"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "gogI-kwi3Tye"
},
"source": [
"# Profile\n",
"from utils.torch_utils import profile\n",
"\n",
"m1 = lambda x: x * torch.sigmoid(x)\n",
"m2 = torch.nn.SiLU()\n",
"results = profile(input=torch.randn(16, 3, 640, 640), ops=[m1, m2], n=100)"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "RVRSOhEvUdb5"
},
"source": [
"# Evolve\n",
"!python train.py --img 640 --batch 64 --epochs 100 --data coco128.yaml --weights yolov5s.pt --cache --noautoanchor --evolve\n",
"!d=runs/train/evolve && cp evolve.* $d && zip -r evolve.zip $d && gsutil mv evolve.zip gs://bucket # upload results (optional)"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "BSgFCAcMbk1R"
},
"source": [
"# VOC\n",
"for b, m in zip([64, 48, 32, 16], ['yolov5s', 'yolov5m', 'yolov5l', 'yolov5x']): # zip(batch_size, model)\n",
" !python train.py --batch {b} --weights {m}.pt --data VOC.yaml --epochs 50 --cache --img 512 --nosave --hyp hyp.finetune.yaml --project VOC --name {m}"
],
"execution_count": null,
"outputs": []
}
]
}
\ No newline at end of file
utils/activations.py 0 → 100644
View file @ a7b29f47
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
"""
Activation functions
"""
import torch
import torch.nn as nn
import torch.nn.functional as F
# SiLU https://arxiv.org/pdf/1606.08415.pdf ----------------------------------------------------------------------------
class SiLU(nn.Module): # export-friendly version of nn.SiLU()
@staticmethod
def forward(x):
return x * torch.sigmoid(x)
class Hardswish(nn.Module): # export-friendly version of nn.Hardswish()
@staticmethod
def forward(x):
# return x * F.hardsigmoid(x) # for torchscript and CoreML
return x * F.hardtanh(x + 3, 0., 6.) / 6. # for torchscript, CoreML and ONNX
# Mish https://github.com/digantamisra98/Mish --------------------------------------------------------------------------
class Mish(nn.Module):
@staticmethod
def forward(x):
return x * F.softplus(x).tanh()
class MemoryEfficientMish(nn.Module):
class F(torch.autograd.Function):
@staticmethod
def forward(ctx, x):
ctx.save_for_backward(x)
return x.mul(torch.tanh(F.softplus(x))) # x * tanh(ln(1 + exp(x)))
@staticmethod
def backward(ctx, grad_output):
x = ctx.saved_tensors[0]
sx = torch.sigmoid(x)
fx = F.softplus(x).tanh()
return grad_output * (fx + x * sx * (1 - fx * fx))
def forward(self, x):
return self.F.apply(x)
# FReLU https://arxiv.org/abs/2007.11824 -------------------------------------------------------------------------------
class FReLU(nn.Module):
def __init__(self, c1, k=3): # ch_in, kernel
super().__init__()
self.conv = nn.Conv2d(c1, c1, k, 1, 1, groups=c1, bias=False)
self.bn = nn.BatchNorm2d(c1)
def forward(self, x):
return torch.max(x, self.bn(self.conv(x)))
# ACON https://arxiv.org/pdf/2009.04759.pdf ----------------------------------------------------------------------------
class AconC(nn.Module):
r""" ACON activation (activate or not).
AconC: (p1*x-p2*x) * sigmoid(beta*(p1*x-p2*x)) + p2*x, beta is a learnable parameter
according to "Activate or Not: Learning Customized Activation" <https://arxiv.org/pdf/2009.04759.pdf>.
"""
def __init__(self, c1):
super().__init__()
self.p1 = nn.Parameter(torch.randn(1, c1, 1, 1))
self.p2 = nn.Parameter(torch.randn(1, c1, 1, 1))
self.beta = nn.Parameter(torch.ones(1, c1, 1, 1))
def forward(self, x):
dpx = (self.p1 - self.p2) * x
return dpx * torch.sigmoid(self.beta * dpx) + self.p2 * x
class MetaAconC(nn.Module):
r""" ACON activation (activate or not).
MetaAconC: (p1*x-p2*x) * sigmoid(beta*(p1*x-p2*x)) + p2*x, beta is generated by a small network
according to "Activate or Not: Learning Customized Activation" <https://arxiv.org/pdf/2009.04759.pdf>.
"""
def __init__(self, c1, k=1, s=1, r=16): # ch_in, kernel, stride, r
super().__init__()
c2 = max(r, c1 // r)
self.p1 = nn.Parameter(torch.randn(1, c1, 1, 1))
self.p2 = nn.Parameter(torch.randn(1, c1, 1, 1))
self.fc1 = nn.Conv2d(c1, c2, k, s, bias=True)
self.fc2 = nn.Conv2d(c2, c1, k, s, bias=True)
# self.bn1 = nn.BatchNorm2d(c2)
# self.bn2 = nn.BatchNorm2d(c1)
def forward(self, x):
y = x.mean(dim=2, keepdims=True).mean(dim=3, keepdims=True)
# batch-size 1 bug/instabilities https://github.com/ultralytics/yolov5/issues/2891
# beta = torch.sigmoid(self.bn2(self.fc2(self.bn1(self.fc1(y))))) # bug/unstable
beta = torch.sigmoid(self.fc2(self.fc1(y))) # bug patch BN layers removed
dpx = (self.p1 - self.p2) * x
return dpx * torch.sigmoid(beta * dpx) + self.p2 * x
utils/augmentations.py 0 → 100644
View file @ a7b29f47
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
"""
Image augmentation functions
"""
import logging
import math
import random
import cv2
import numpy as np
from utils.general import colorstr, segment2box, resample_segments, check_version
from utils.metrics import bbox_ioa
class Albumentations:
# YOLOv5 Albumentations class (optional, only used if package is installed)
def __init__(self):
self.transform = None
try:
import albumentations as A
check_version(A.__version__, '1.0.3') # version requirement
self.transform = A.Compose([
A.Blur(p=0.01),
A.MedianBlur(p=0.01),
A.ToGray(p=0.01),
A.CLAHE(p=0.01),
A.RandomBrightnessContrast(p=0.0),
A.RandomGamma(p=0.0),
A.ImageCompression(quality_lower=75, p=0.0)],
bbox_params=A.BboxParams(format='yolo', label_fields=['class_labels']))
logging.info(colorstr('albumentations: ') + ', '.join(f'{x}' for x in self.transform.transforms if x.p))
except ImportError: # package not installed, skip
pass
except Exception as e:
logging.info(colorstr('albumentations: ') + f'{e}')
def __call__(self, im, labels, p=1.0):
if self.transform and random.random() < p:
new = self.transform(image=im, bboxes=labels[:, 1:], class_labels=labels[:, 0]) # transformed
im, labels = new['image'], np.array([[c, *b] for c, b in zip(new['class_labels'], new['bboxes'])])
return im, labels
def augment_hsv(im, hgain=0.5, sgain=0.5, vgain=0.5):
# HSV color-space augmentation
if hgain or sgain or vgain:
r = np.random.uniform(-1, 1, 3) * [hgain, sgain, vgain] + 1 # random gains
hue, sat, val = cv2.split(cv2.cvtColor(im, cv2.COLOR_BGR2HSV))
dtype = im.dtype # uint8
x = np.arange(0, 256, dtype=r.dtype)
lut_hue = ((x * r[0]) % 180).astype(dtype)
lut_sat = np.clip(x * r[1], 0, 255).astype(dtype)
lut_val = np.clip(x * r[2], 0, 255).astype(dtype)
im_hsv = cv2.merge((cv2.LUT(hue, lut_hue), cv2.LUT(sat, lut_sat), cv2.LUT(val, lut_val)))
cv2.cvtColor(im_hsv, cv2.COLOR_HSV2BGR, dst=im) # no return needed
def hist_equalize(im, clahe=True, bgr=False):
# Equalize histogram on BGR image 'im' with im.shape(n,m,3) and range 0-255
yuv = cv2.cvtColor(im, cv2.COLOR_BGR2YUV if bgr else cv2.COLOR_RGB2YUV)
if clahe:
c = cv2.createCLAHE(clipLimit=2.0, tileGridSize=(8, 8))
yuv[:, :, 0] = c.apply(yuv[:, :, 0])
else:
yuv[:, :, 0] = cv2.equalizeHist(yuv[:, :, 0]) # equalize Y channel histogram
return cv2.cvtColor(yuv, cv2.COLOR_YUV2BGR if bgr else cv2.COLOR_YUV2RGB) # convert YUV image to RGB
def replicate(im, labels):
# Replicate labels
h, w = im.shape[:2]
boxes = labels[:, 1:].astype(int)
x1, y1, x2, y2 = boxes.T
s = ((x2 - x1) + (y2 - y1)) / 2 # side length (pixels)
for i in s.argsort()[:round(s.size * 0.5)]: # smallest indices
x1b, y1b, x2b, y2b = boxes[i]
bh, bw = y2b - y1b, x2b - x1b
yc, xc = int(random.uniform(0, h - bh)), int(random.uniform(0, w - bw)) # offset x, y
x1a, y1a, x2a, y2a = [xc, yc, xc + bw, yc + bh]
im[y1a:y2a, x1a:x2a] = im[y1b:y2b, x1b:x2b] # im4[ymin:ymax, xmin:xmax]
labels = np.append(labels, [[labels[i, 0], x1a, y1a, x2a, y2a]], axis=0)
return im, labels
def letterbox(im, new_shape=(640, 640), color=(114, 114, 114), auto=True, scaleFill=False, scaleup=True, stride=32):
# Resize and pad image while meeting stride-multiple constraints
shape = im.shape[:2] # current shape [height, width]
if isinstance(new_shape, int):
new_shape = (new_shape, new_shape)
# Scale ratio (new / old)
r = min(new_shape[0] / shape[0], new_shape[1] / shape[1])
if not scaleup: # only scale down, do not scale up (for better val mAP)
r = min(r, 1.0)
# Compute padding
ratio = r, r # width, height ratios
new_unpad = int(round(shape[1] * r)), int(round(shape[0] * r))
dw, dh = new_shape[1] - new_unpad[0], new_shape[0] - new_unpad[1] # wh padding
if auto: # minimum rectangle
dw, dh = np.mod(dw, stride), np.mod(dh, stride) # wh padding
elif scaleFill: # stretch
dw, dh = 0.0, 0.0
new_unpad = (new_shape[1], new_shape[0])
ratio = new_shape[1] / shape[1], new_shape[0] / shape[0] # width, height ratios
dw /= 2 # divide padding into 2 sides
dh /= 2
if shape[::-1] != new_unpad: # resize
im = cv2.resize(im, new_unpad, interpolation=cv2.INTER_LINEAR)
top, bottom = int(round(dh - 0.1)), int(round(dh + 0.1))
left, right = int(round(dw - 0.1)), int(round(dw + 0.1))
im = cv2.copyMakeBorder(im, top, bottom, left, right, cv2.BORDER_CONSTANT, value=color) # add border
return im, ratio, (dw, dh)
def random_perspective(im, targets=(), segments=(), degrees=10, translate=.1, scale=.1, shear=10, perspective=0.0,
border=(0, 0)):
# torchvision.transforms.RandomAffine(degrees=(-10, 10), translate=(.1, .1), scale=(.9, 1.1), shear=(-10, 10))
# targets = [cls, xyxy]
height = im.shape[0] + border[0] * 2 # shape(h,w,c)
width = im.shape[1] + border[1] * 2
# Center
C = np.eye(3)
C[0, 2] = -im.shape[1] / 2 # x translation (pixels)
C[1, 2] = -im.shape[0] / 2 # y translation (pixels)
# Perspective
P = np.eye(3)
P[2, 0] = random.uniform(-perspective, perspective) # x perspective (about y)
P[2, 1] = random.uniform(-perspective, perspective) # y perspective (about x)
# Rotation and Scale
R = np.eye(3)
a = random.uniform(-degrees, degrees)
# a += random.choice([-180, -90, 0, 90]) # add 90deg rotations to small rotations
s = random.uniform(1 - scale, 1 + scale)
# s = 2 ** random.uniform(-scale, scale)
R[:2] = cv2.getRotationMatrix2D(angle=a, center=(0, 0), scale=s)
# Shear
S = np.eye(3)
S[0, 1] = math.tan(random.uniform(-shear, shear) * math.pi / 180) # x shear (deg)
S[1, 0] = math.tan(random.uniform(-shear, shear) * math.pi / 180) # y shear (deg)
# Translation
T = np.eye(3)
T[0, 2] = random.uniform(0.5 - translate, 0.5 + translate) * width # x translation (pixels)
T[1, 2] = random.uniform(0.5 - translate, 0.5 + translate) * height # y translation (pixels)
# Combined rotation matrix
M = T @ S @ R @ P @ C # order of operations (right to left) is IMPORTANT
if (border[0] != 0) or (border[1] != 0) or (M != np.eye(3)).any(): # image changed
if perspective:
im = cv2.warpPerspective(im, M, dsize=(width, height), borderValue=(114, 114, 114))
else: # affine
im = cv2.warpAffine(im, M[:2], dsize=(width, height), borderValue=(114, 114, 114))
# Visualize
# import matplotlib.pyplot as plt
# ax = plt.subplots(1, 2, figsize=(12, 6))[1].ravel()
# ax[0].imshow(im[:, :, ::-1]) # base
# ax[1].imshow(im2[:, :, ::-1]) # warped
# Transform label coordinates
n = len(targets)
if n:
use_segments = any(x.any() for x in segments)
new = np.zeros((n, 4))
if use_segments: # warp segments
segments = resample_segments(segments) # upsample
for i, segment in enumerate(segments):
xy = np.ones((len(segment), 3))
xy[:, :2] = segment
xy = xy @ M.T # transform
xy = xy[:, :2] / xy[:, 2:3] if perspective else xy[:, :2] # perspective rescale or affine
# clip
new[i] = segment2box(xy, width, height)
else: # warp boxes
xy = np.ones((n * 4, 3))
xy[:, :2] = targets[:, [1, 2, 3, 4, 1, 4, 3, 2]].reshape(n * 4, 2) # x1y1, x2y2, x1y2, x2y1
xy = xy @ M.T # transform
xy = (xy[:, :2] / xy[:, 2:3] if perspective else xy[:, :2]).reshape(n, 8) # perspective rescale or affine
# create new boxes
x = xy[:, [0, 2, 4, 6]]
y = xy[:, [1, 3, 5, 7]]
new = np.concatenate((x.min(1), y.min(1), x.max(1), y.max(1))).reshape(4, n).T
# clip
new[:, [0, 2]] = new[:, [0, 2]].clip(0, width)
new[:, [1, 3]] = new[:, [1, 3]].clip(0, height)
# filter candidates
i = box_candidates(box1=targets[:, 1:5].T * s, box2=new.T, area_thr=0.01 if use_segments else 0.10)
targets = targets[i]
targets[:, 1:5] = new[i]
return im, targets
def copy_paste(im, labels, segments, p=0.5):
# Implement Copy-Paste augmentation https://arxiv.org/abs/2012.07177, labels as nx5 np.array(cls, xyxy)
n = len(segments)
if p and n:
h, w, c = im.shape # height, width, channels
im_new = np.zeros(im.shape, np.uint8)
for j in random.sample(range(n), k=round(p * n)):
l, s = labels[j], segments[j]
box = w - l[3], l[2], w - l[1], l[4]
ioa = bbox_ioa(box, labels[:, 1:5]) # intersection over area
if (ioa < 0.30).all(): # allow 30% obscuration of existing labels
labels = np.concatenate((labels, [[l[0], *box]]), 0)
segments.append(np.concatenate((w - s[:, 0:1], s[:, 1:2]), 1))
cv2.drawContours(im_new, [segments[j].astype(np.int32)], -1, (255, 255, 255), cv2.FILLED)
result = cv2.bitwise_and(src1=im, src2=im_new)
result = cv2.flip(result, 1) # augment segments (flip left-right)
i = result > 0 # pixels to replace
# i[:, :] = result.max(2).reshape(h, w, 1) # act over ch
im[i] = result[i] # cv2.imwrite('debug.jpg', im) # debug
return im, labels, segments
def cutout(im, labels, p=0.5):
# Applies image cutout augmentation https://arxiv.org/abs/1708.04552
if random.random() < p:
h, w = im.shape[:2]
scales = [0.5] * 1 + [0.25] * 2 + [0.125] * 4 + [0.0625] * 8 + [0.03125] * 16 # image size fraction
for s in scales:
mask_h = random.randint(1, int(h * s)) # create random masks
mask_w = random.randint(1, int(w * s))
# box
xmin = max(0, random.randint(0, w) - mask_w // 2)
ymin = max(0, random.randint(0, h) - mask_h // 2)
xmax = min(w, xmin + mask_w)
ymax = min(h, ymin + mask_h)
# apply random color mask
im[ymin:ymax, xmin:xmax] = [random.randint(64, 191) for _ in range(3)]
# return unobscured labels
if len(labels) and s > 0.03:
box = np.array([xmin, ymin, xmax, ymax], dtype=np.float32)
ioa = bbox_ioa(box, labels[:, 1:5]) # intersection over area
labels = labels[ioa < 0.60] # remove >60% obscured labels
return labels
def mixup(im, labels, im2, labels2):
# Applies MixUp augmentation https://arxiv.org/pdf/1710.09412.pdf
r = np.random.beta(32.0, 32.0) # mixup ratio, alpha=beta=32.0
im = (im * r + im2 * (1 - r)).astype(np.uint8)
labels = np.concatenate((labels, labels2), 0)
return im, labels
def box_candidates(box1, box2, wh_thr=2, ar_thr=20, area_thr=0.1, eps=1e-16): # box1(4,n), box2(4,n)
# Compute candidate boxes: box1 before augment, box2 after augment, wh_thr (pixels), aspect_ratio_thr, area_ratio
w1, h1 = box1[2] - box1[0], box1[3] - box1[1]
w2, h2 = box2[2] - box2[0], box2[3] - box2[1]
ar = np.maximum(w2 / (h2 + eps), h2 / (w2 + eps)) # aspect ratio
return (w2 > wh_thr) & (h2 > wh_thr) & (w2 * h2 / (w1 * h1 + eps) > area_thr) & (ar < ar_thr) # candidates
utils/autoanchor.py 0 → 100644
View file @ a7b29f47
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
"""
Auto-anchor utils
"""
import random
import numpy as np
import torch
import yaml
from tqdm import tqdm
from utils.general import colorstr
def check_anchor_order(m):
# Check anchor order against stride order for YOLOv5 Detect() module m, and correct if necessary
a = m.anchors.prod(-1).view(-1) # anchor area
da = a[-1] - a[0] # delta a
ds = m.stride[-1] - m.stride[0] # delta s
if da.sign() != ds.sign(): # same order
print('Reversing anchor order')
m.anchors[:] = m.anchors.flip(0)
def check_anchors(dataset, model, thr=4.0, imgsz=640):
# Check anchor fit to data, recompute if necessary
prefix = colorstr('autoanchor: ')
print(f'\n{prefix}Analyzing anchors... ', end='')
m = model.module.model[-1] if hasattr(model, 'module') else model.model[-1] # Detect()
shapes = imgsz * dataset.shapes / dataset.shapes.max(1, keepdims=True)
scale = np.random.uniform(0.9, 1.1, size=(shapes.shape[0], 1)) # augment scale
wh = torch.tensor(np.concatenate([l[:, 3:5] * s for s, l in zip(shapes * scale, dataset.labels)])).float() # wh
def metric(k): # compute metric
r = wh[:, None] / k[None]
x = torch.min(r, 1. / r).min(2)[0] # ratio metric
best = x.max(1)[0] # best_x
aat = (x > 1. / thr).float().sum(1).mean() # anchors above threshold
bpr = (best > 1. / thr).float().mean() # best possible recall
return bpr, aat
anchors = m.anchors.clone() * m.stride.to(m.anchors.device).view(-1, 1, 1) # current anchors
bpr, aat = metric(anchors.cpu().view(-1, 2))
print(f'anchors/target = {aat:.2f}, Best Possible Recall (BPR) = {bpr:.4f}', end='')
if bpr < 0.98: # threshold to recompute
print('. Attempting to improve anchors, please wait...')
na = m.anchors.numel() // 2 # number of anchors
try:
anchors = kmean_anchors(dataset, n=na, img_size=imgsz, thr=thr, gen=1000, verbose=False)
except Exception as e:
print(f'{prefix}ERROR: {e}')
new_bpr = metric(anchors)[0]
if new_bpr > bpr: # replace anchors
anchors = torch.tensor(anchors, device=m.anchors.device).type_as(m.anchors)
m.anchors[:] = anchors.clone().view_as(m.anchors) / m.stride.to(m.anchors.device).view(-1, 1, 1) # loss
check_anchor_order(m)
print(f'{prefix}New anchors saved to model. Update model *.yaml to use these anchors in the future.')
else:
print(f'{prefix}Original anchors better than new anchors. Proceeding with original anchors.')
print('') # newline
def kmean_anchors(dataset='./data/coco128.yaml', n=9, img_size=640, thr=4.0, gen=1000, verbose=True):
""" Creates kmeans-evolved anchors from training dataset
Arguments:
dataset: path to data.yaml, or a loaded dataset
n: number of anchors
img_size: image size used for training
thr: anchor-label wh ratio threshold hyperparameter hyp['anchor_t'] used for training, default=4.0
gen: generations to evolve anchors using genetic algorithm
verbose: print all results
Return:
k: kmeans evolved anchors
Usage:
from utils.autoanchor import *; _ = kmean_anchors()
"""
from scipy.cluster.vq import kmeans
thr = 1. / thr
prefix = colorstr('autoanchor: ')
def metric(k, wh): # compute metrics
r = wh[:, None] / k[None]
x = torch.min(r, 1. / r).min(2)[0] # ratio metric
# x = wh_iou(wh, torch.tensor(k)) # iou metric
return x, x.max(1)[0] # x, best_x
def anchor_fitness(k): # mutation fitness
_, best = metric(torch.tensor(k, dtype=torch.float32), wh)
return (best * (best > thr).float()).mean() # fitness
def print_results(k):
k = k[np.argsort(k.prod(1))] # sort small to large
x, best = metric(k, wh0)
bpr, aat = (best > thr).float().mean(), (x > thr).float().mean() * n # best possible recall, anch > thr
print(f'{prefix}thr={thr:.2f}: {bpr:.4f} best possible recall, {aat:.2f} anchors past thr')
print(f'{prefix}n={n}, img_size={img_size}, metric_all={x.mean():.3f}/{best.mean():.3f}-mean/best, '
f'past_thr={x[x > thr].mean():.3f}-mean: ', end='')
for i, x in enumerate(k):
print('%i,%i' % (round(x[0]), round(x[1])), end=', ' if i < len(k) - 1 else '\n') # use in *.cfg
return k
if isinstance(dataset, str): # *.yaml file
with open(dataset, errors='ignore') as f:
data_dict = yaml.safe_load(f) # model dict
from utils.datasets import LoadImagesAndLabels
dataset = LoadImagesAndLabels(data_dict['train'], augment=True, rect=True)
# Get label wh
shapes = img_size * dataset.shapes / dataset.shapes.max(1, keepdims=True)
wh0 = np.concatenate([l[:, 3:5] * s for s, l in zip(shapes, dataset.labels)]) # wh
# Filter
i = (wh0 < 3.0).any(1).sum()
if i:
print(f'{prefix}WARNING: Extremely small objects found. {i} of {len(wh0)} labels are < 3 pixels in size.')
wh = wh0[(wh0 >= 2.0).any(1)] # filter > 2 pixels
# wh = wh * (np.random.rand(wh.shape[0], 1) * 0.9 + 0.1) # multiply by random scale 0-1
# Kmeans calculation
print(f'{prefix}Running kmeans for {n} anchors on {len(wh)} points...')
s = wh.std(0) # sigmas for whitening
k, dist = kmeans(wh / s, n, iter=30) # points, mean distance
assert len(k) == n, f'{prefix}ERROR: scipy.cluster.vq.kmeans requested {n} points but returned only {len(k)}'
k *= s
wh = torch.tensor(wh, dtype=torch.float32) # filtered
wh0 = torch.tensor(wh0, dtype=torch.float32) # unfiltered
k = print_results(k)
# Plot
# k, d = [None] * 20, [None] * 20
# for i in tqdm(range(1, 21)):
# k[i-1], d[i-1] = kmeans(wh / s, i) # points, mean distance
# fig, ax = plt.subplots(1, 2, figsize=(14, 7), tight_layout=True)
# ax = ax.ravel()
# ax[0].plot(np.arange(1, 21), np.array(d) ** 2, marker='.')
# fig, ax = plt.subplots(1, 2, figsize=(14, 7)) # plot wh
# ax[0].hist(wh[wh[:, 0]<100, 0],400)
# ax[1].hist(wh[wh[:, 1]<100, 1],400)
# fig.savefig('wh.png', dpi=200)
# Evolve
npr = np.random
f, sh, mp, s = anchor_fitness(k), k.shape, 0.9, 0.1 # fitness, generations, mutation prob, sigma
pbar = tqdm(range(gen), desc=f'{prefix}Evolving anchors with Genetic Algorithm:') # progress bar
for _ in pbar:
v = np.ones(sh)
while (v == 1).all(): # mutate until a change occurs (prevent duplicates)
v = ((npr.random(sh) < mp) * random.random() * npr.randn(*sh) * s + 1).clip(0.3, 3.0)
kg = (k.copy() * v).clip(min=2.0)
fg = anchor_fitness(kg)
if fg > f:
f, k = fg, kg.copy()
pbar.desc = f'{prefix}Evolving anchors with Genetic Algorithm: fitness = {f:.4f}'
if verbose:
print_results(k)
return print_results(k)
utils/aws/mime.sh 0 → 100644
View file @ a7b29f47
# AWS EC2 instance startup 'MIME' script https://aws.amazon.com/premiumsupport/knowledge-center/execute-user-data-ec2/
# This script will run on every instance restart, not only on first start
# --- DO NOT COPY ABOVE COMMENTS WHEN PASTING INTO USERDATA ---
Content-Type: multipart/mixed; boundary="//"
MIME-Version: 1.0
--//
Content-Type: text/cloud-config; charset="us-ascii"
MIME-Version: 1.0
Content-Transfer-Encoding: 7bit
Content-Disposition: attachment; filename="cloud-config.txt"
#cloud-config
cloud_final_modules:
- [scripts-user, always]
--//
Content-Type: text/x-shellscript; charset="us-ascii"
MIME-Version: 1.0
Content-Transfer-Encoding: 7bit
Content-Disposition: attachment; filename="userdata.txt"
#!/bin/bash
# --- paste contents of userdata.sh here ---
--//
utils/aws/resume.py 0 → 100644
View file @ a7b29f47
# Resume all interrupted trainings in yolov5/ dir including DDP trainings
# Usage: $ python utils/aws/resume.py
import os
import sys
from pathlib import Path
import torch
import yaml
FILE = Path(__file__).resolve()
ROOT = FILE.parents[2] # YOLOv5 root directory
if str(ROOT) not in sys.path:
sys.path.append(str(ROOT)) # add ROOT to PATH
port = 0 # --master_port
path = Path('').resolve()
for last in path.rglob('*/**/last.pt'):
ckpt = torch.load(last)
if ckpt['optimizer'] is None:
continue
# Load opt.yaml
with open(last.parent.parent / 'opt.yaml', errors='ignore') as f:
opt = yaml.safe_load(f)
# Get device count
d = opt['device'].split(',') # devices
nd = len(d) # number of devices
ddp = nd > 1 or (nd == 0 and torch.cuda.device_count() > 1) # distributed data parallel
if ddp: # multi-GPU
port += 1
cmd = f'python -m torch.distributed.run --nproc_per_node {nd} --master_port {port} train.py --resume {last}'
else: # single-GPU
cmd = f'python train.py --resume {last}'
cmd += ' > /dev/null 2>&1 &' # redirect output to dev/null and run in daemon thread
print(cmd)
os.system(cmd)
utils/aws/userdata.sh 0 → 100644
View file @ a7b29f47
#!/bin/bash
# AWS EC2 instance startup script https://docs.aws.amazon.com/AWSEC2/latest/UserGuide/user-data.html
# This script will run only once on first instance start (for a re-start script see mime.sh)
# /home/ubuntu (ubuntu) or /home/ec2-user (amazon-linux) is working dir
# Use >300 GB SSD
cd home/ubuntu
if [ ! -d yolov5 ]; then
echo "Running first-time script." # install dependencies, download COCO, pull Docker
git clone https://github.com/ultralytics/yolov5 -b master && sudo chmod -R 777 yolov5
cd yolov5
bash data/scripts/get_coco.sh && echo "COCO done." &
sudo docker pull ultralytics/yolov5:latest && echo "Docker done." &
python -m pip install --upgrade pip && pip install -r requirements.txt && python detect.py && echo "Requirements done." &
wait && echo "All tasks done." # finish background tasks
else
echo "Running re-start script." # resume interrupted runs
i=0
list=$(sudo docker ps -qa) # container list i.e. $'one\ntwo\nthree\nfour'
while IFS= read -r id; do
((i++))
echo "restarting container $i: $id"
sudo docker start $id
# sudo docker exec -it $id python train.py --resume # single-GPU
sudo docker exec -d $id python utils/aws/resume.py # multi-scenario
done <<<"$list"
fi
utils/callbacks.py 0 → 100644
View file @ a7b29f47
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
"""
Callback utils
"""
class Callbacks:
""""
Handles all registered callbacks for YOLOv5 Hooks
"""
# Define the available callbacks
_callbacks = {
'on_pretrain_routine_start': [],
'on_pretrain_routine_end': [],
'on_train_start': [],
'on_train_epoch_start': [],
'on_train_batch_start': [],
'optimizer_step': [],
'on_before_zero_grad': [],
'on_train_batch_end': [],
'on_train_epoch_end': [],
'on_val_start': [],
'on_val_batch_start': [],
'on_val_image_end': [],
'on_val_batch_end': [],
'on_val_end': [],
'on_fit_epoch_end': [], # fit = train + val
'on_model_save': [],
'on_train_end': [],
'teardown': [],
}
def register_action(self, hook, name='', callback=None):
"""
Register a new action to a callback hook
Args:
hook The callback hook name to register the action to
name The name of the action for later reference
callback The callback to fire
"""
assert hook in self._callbacks, f"hook '{hook}' not found in callbacks {self._callbacks}"
assert callable(callback), f"callback '{callback}' is not callable"
self._callbacks[hook].append({'name': name, 'callback': callback})
def get_registered_actions(self, hook=None):
""""
Returns all the registered actions by callback hook
Args:
hook The name of the hook to check, defaults to all
"""
if hook:
return self._callbacks[hook]
else:
return self._callbacks
def run(self, hook, *args, **kwargs):
"""
Loop through the registered actions and fire all callbacks
Args:
hook The name of the hook to check, defaults to all
args Arguments to receive from YOLOv5
kwargs Keyword Arguments to receive from YOLOv5
"""
assert hook in self._callbacks, f"hook '{hook}' not found in callbacks {self._callbacks}"
for logger in self._callbacks[hook]:
logger['callback'](*args, **kwargs)
utils/datasets.py 0 → 100644
View file @ a7b29f47
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
"""
Dataloaders and dataset utils
"""
import glob
import hashlib
import json
import logging
import os
import random
import shutil
import time
from itertools import repeat
from multiprocessing.pool import ThreadPool, Pool
from pathlib import Path
from threading import Thread
from zipfile import ZipFile
import cv2
import numpy as np
import torch
import torch.nn.functional as F
import yaml
from PIL import Image, ExifTags
from torch.utils.data import Dataset
from tqdm import tqdm
from utils.augmentations import Albumentations, augment_hsv, copy_paste, letterbox, mixup, random_perspective
from utils.general import check_dataset, check_requirements, check_yaml, clean_str, segments2boxes, \
xywh2xyxy, xywhn2xyxy, xyxy2xywhn, xyn2xy
from utils.torch_utils import torch_distributed_zero_first
# Parameters
HELP_URL = 'https://github.com/ultralytics/yolov5/wiki/Train-Custom-Data'
IMG_FORMATS = ['bmp', 'jpg', 'jpeg', 'png', 'tif', 'tiff', 'dng', 'webp', 'mpo'] # acceptable image suffixes
VID_FORMATS = ['mov', 'avi', 'mp4', 'mpg', 'mpeg', 'm4v', 'wmv', 'mkv'] # acceptable video suffixes
NUM_THREADS = min(8, os.cpu_count()) # number of multiprocessing threads
# Get orientation exif tag
for orientation in ExifTags.TAGS.keys():
if ExifTags.TAGS[orientation] == 'Orientation':
break
def get_hash(paths):
# Returns a single hash value of a list of paths (files or dirs)
size = sum(os.path.getsize(p) for p in paths if os.path.exists(p)) # sizes
h = hashlib.md5(str(size).encode()) # hash sizes
h.update(''.join(paths).encode()) # hash paths
return h.hexdigest() # return hash
def exif_size(img):
# Returns exif-corrected PIL size
s = img.size # (width, height)
try:
rotation = dict(img._getexif().items())[orientation]
if rotation == 6: # rotation 270
s = (s[1], s[0])
elif rotation == 8: # rotation 90
s = (s[1], s[0])
except:
pass
return s
def exif_transpose(image):
"""
Transpose a PIL image accordingly if it has an EXIF Orientation tag.
From https://github.com/python-pillow/Pillow/blob/master/src/PIL/ImageOps.py
:param image: The image to transpose.
:return: An image.
"""
exif = image.getexif()
orientation = exif.get(0x0112, 1) # default 1
if orientation > 1:
method = {2: Image.FLIP_LEFT_RIGHT,
3: Image.ROTATE_180,
4: Image.FLIP_TOP_BOTTOM,
5: Image.TRANSPOSE,
6: Image.ROTATE_270,
7: Image.TRANSVERSE,
8: Image.ROTATE_90,
}.get(orientation)
if method is not None:
image = image.transpose(method)
del exif[0x0112]
image.info["exif"] = exif.tobytes()
return image
def create_dataloader(path, imgsz, batch_size, stride, single_cls=False, hyp=None, augment=False, cache=False, pad=0.0,
rect=False, rank=-1, workers=8, image_weights=False, quad=False, prefix=''):
# Make sure only the first process in DDP process the dataset first, and the following others can use the cache
with torch_distributed_zero_first(rank):
dataset = LoadImagesAndLabels(path, imgsz, batch_size,
augment=augment, # augment images
hyp=hyp, # augmentation hyperparameters
rect=rect, # rectangular training
cache_images=cache,
single_cls=single_cls,
stride=int(stride),
pad=pad,
image_weights=image_weights,
prefix=prefix)
batch_size = min(batch_size, len(dataset))
nw = min([os.cpu_count(), batch_size if batch_size > 1 else 0, workers]) # number of workers
sampler = torch.utils.data.distributed.DistributedSampler(dataset) if rank != -1 else None
loader = torch.utils.data.DataLoader if image_weights else InfiniteDataLoader
# Use torch.utils.data.DataLoader() if dataset.properties will update during training else InfiniteDataLoader()
dataloader = loader(dataset,
batch_size=batch_size,
num_workers=nw,
sampler=sampler,
pin_memory=True,
collate_fn=LoadImagesAndLabels.collate_fn4 if quad else LoadImagesAndLabels.collate_fn)
return dataloader, dataset
class InfiniteDataLoader(torch.utils.data.dataloader.DataLoader):
""" Dataloader that reuses workers
Uses same syntax as vanilla DataLoader
"""
def __init__(self, *args, **kwargs):
super().__init__(*args, **kwargs)
object.__setattr__(self, 'batch_sampler', _RepeatSampler(self.batch_sampler))
self.iterator = super().__iter__()
def __len__(self):
return len(self.batch_sampler.sampler)
def __iter__(self):
for i in range(len(self)):
yield next(self.iterator)
class _RepeatSampler(object):
""" Sampler that repeats forever
Args:
sampler (Sampler)
"""
def __init__(self, sampler):
self.sampler = sampler
def __iter__(self):
while True:
yield from iter(self.sampler)
class LoadImages:
# YOLOv5 image/video dataloader, i.e. `python detect.py --source image.jpg/vid.mp4`
def __init__(self, path, img_size=640, stride=32, auto=True):
p = str(Path(path).resolve()) # os-agnostic absolute path
if '*' in p:
files = sorted(glob.glob(p, recursive=True)) # glob
elif os.path.isdir(p):
files = sorted(glob.glob(os.path.join(p, '*.*'))) # dir
elif os.path.isfile(p):
files = [p] # files
else:
raise Exception(f'ERROR: {p} does not exist')
images = [x for x in files if x.split('.')[-1].lower() in IMG_FORMATS]
videos = [x for x in files if x.split('.')[-1].lower() in VID_FORMATS]
ni, nv = len(images), len(videos)
self.img_size = img_size
self.stride = stride
self.files = images + videos
self.nf = ni + nv # number of files
self.video_flag = [False] * ni + [True] * nv
self.mode = 'image'
self.auto = auto
if any(videos):
self.new_video(videos[0]) # new video
else:
self.cap = None
assert self.nf > 0, f'No images or videos found in {p}. ' \
f'Supported formats are:\nimages: {IMG_FORMATS}\nvideos: {VID_FORMATS}'
def __iter__(self):
self.count = 0
return self
def __next__(self):
if self.count == self.nf:
raise StopIteration
path = self.files[self.count]
if self.video_flag[self.count]:
# Read video
self.mode = 'video'
ret_val, img0 = self.cap.read()
if not ret_val:
self.count += 1
self.cap.release()
if self.count == self.nf: # last video
raise StopIteration
else:
path = self.files[self.count]
self.new_video(path)
ret_val, img0 = self.cap.read()
self.frame += 1
print(f'video {self.count + 1}/{self.nf} ({self.frame}/{self.frames}) {path}: ', end='')
else:
# Read image
self.count += 1
img0 = cv2.imread(path) # BGR
assert img0 is not None, 'Image Not Found ' + path
print(f'image {self.count}/{self.nf} {path}: ', end='')
# Padded resize
img = letterbox(img0, self.img_size, stride=self.stride, auto=self.auto)[0]
# Convert
img = img.transpose((2, 0, 1))[::-1] # HWC to CHW, BGR to RGB
img = np.ascontiguousarray(img)
return path, img, img0, self.cap
def new_video(self, path):
self.frame = 0
self.cap = cv2.VideoCapture(path)
self.frames = int(self.cap.get(cv2.CAP_PROP_FRAME_COUNT))
def __len__(self):
return self.nf # number of files
class LoadWebcam: # for inference
# YOLOv5 local webcam dataloader, i.e. `python detect.py --source 0`
def __init__(self, pipe='0', img_size=640, stride=32):
self.img_size = img_size
self.stride = stride
self.pipe = eval(pipe) if pipe.isnumeric() else pipe
self.cap = cv2.VideoCapture(self.pipe) # video capture object
self.cap.set(cv2.CAP_PROP_BUFFERSIZE, 3) # set buffer size
def __iter__(self):
self.count = -1
return self
def __next__(self):
self.count += 1
if cv2.waitKey(1) == ord('q'): # q to quit
self.cap.release()
cv2.destroyAllWindows()
raise StopIteration
# Read frame
ret_val, img0 = self.cap.read()
img0 = cv2.flip(img0, 1) # flip left-right
# Print
assert ret_val, f'Camera Error {self.pipe}'
img_path = 'webcam.jpg'
print(f'webcam {self.count}: ', end='')
# Padded resize
img = letterbox(img0, self.img_size, stride=self.stride)[0]
# Convert
img = img.transpose((2, 0, 1))[::-1] # HWC to CHW, BGR to RGB
img = np.ascontiguousarray(img)
return img_path, img, img0, None
def __len__(self):
return 0
class LoadStreams:
# YOLOv5 streamloader, i.e. `python detect.py --source 'rtsp://example.com/media.mp4' # RTSP, RTMP, HTTP streams`
def __init__(self, sources='streams.txt', img_size=640, stride=32, auto=True):
self.mode = 'stream'
self.img_size = img_size
self.stride = stride
if os.path.isfile(sources):
with open(sources, 'r') as f:
sources = [x.strip() for x in f.read().strip().splitlines() if len(x.strip())]
else:
sources = [sources]
n = len(sources)
self.imgs, self.fps, self.frames, self.threads = [None] * n, [0] * n, [0] * n, [None] * n
self.sources = [clean_str(x) for x in sources] # clean source names for later
self.auto = auto
for i, s in enumerate(sources): # index, source
# Start thread to read frames from video stream
print(f'{i + 1}/{n}: {s}... ', end='')
if 'youtube.com/' in s or 'youtu.be/' in s: # if source is YouTube video
check_requirements(('pafy', 'youtube_dl'))
import pafy
s = pafy.new(s).getbest(preftype="mp4").url # YouTube URL
s = eval(s) if s.isnumeric() else s # i.e. s = '0' local webcam
cap = cv2.VideoCapture(s)
assert cap.isOpened(), f'Failed to open {s}'
w = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
h = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
self.fps[i] = max(cap.get(cv2.CAP_PROP_FPS) % 100, 0) or 30.0 # 30 FPS fallback
self.frames[i] = max(int(cap.get(cv2.CAP_PROP_FRAME_COUNT)), 0) or float('inf') # infinite stream fallback
_, self.imgs[i] = cap.read() # guarantee first frame
self.threads[i] = Thread(target=self.update, args=([i, cap, s]), daemon=True)
print(f" success ({self.frames[i]} frames {w}x{h} at {self.fps[i]:.2f} FPS)")
self.threads[i].start()
print('') # newline
# check for common shapes
s = np.stack([letterbox(x, self.img_size, stride=self.stride, auto=self.auto)[0].shape for x in self.imgs])
self.rect = np.unique(s, axis=0).shape[0] == 1 # rect inference if all shapes equal
if not self.rect:
print('WARNING: Different stream shapes detected. For optimal performance supply similarly-shaped streams.')
def update(self, i, cap, stream):
# Read stream `i` frames in daemon thread
n, f, read = 0, self.frames[i], 1 # frame number, frame array, inference every 'read' frame
while cap.isOpened() and n < f:
n += 1
# _, self.imgs[index] = cap.read()
cap.grab()
if n % read == 0:
success, im = cap.retrieve()
if success:
self.imgs[i] = im
else:
print('WARNING: Video stream unresponsive, please check your IP camera connection.')
self.imgs[i] *= 0
cap.open(stream) # re-open stream if signal was lost
time.sleep(1 / self.fps[i]) # wait time
def __iter__(self):
self.count = -1
return self
def __next__(self):
self.count += 1
if not all(x.is_alive() for x in self.threads) or cv2.waitKey(1) == ord('q'): # q to quit
cv2.destroyAllWindows()
raise StopIteration
# Letterbox
img0 = self.imgs.copy()
img = [letterbox(x, self.img_size, stride=self.stride, auto=self.rect and self.auto)[0] for x in img0]
# Stack
img = np.stack(img, 0)
# Convert
img = img[..., ::-1].transpose((0, 3, 1, 2)) # BGR to RGB, BHWC to BCHW
img = np.ascontiguousarray(img)
return self.sources, img, img0, None
def __len__(self):
return len(self.sources) # 1E12 frames = 32 streams at 30 FPS for 30 years
def img2label_paths(img_paths):
# Define label paths as a function of image paths
sa, sb = os.sep + 'images' + os.sep, os.sep + 'labels' + os.sep # /images/, /labels/ substrings
return [sb.join(x.rsplit(sa, 1)).rsplit('.', 1)[0] + '.txt' for x in img_paths]
class LoadImagesAndLabels(Dataset):
# YOLOv5 train_loader/val_loader, loads images and labels for training and validation
cache_version = 0.5 # dataset labels *.cache version
def __init__(self, path, img_size=640, batch_size=16, augment=False, hyp=None, rect=False, image_weights=False,
cache_images=False, single_cls=False, stride=32, pad=0.0, prefix=''):
self.img_size = img_size
self.augment = augment
self.hyp = hyp
self.image_weights = image_weights
self.rect = False if image_weights else rect
self.mosaic = self.augment and not self.rect # load 4 images at a time into a mosaic (only during training)
self.mosaic_border = [-img_size // 2, -img_size // 2]
self.stride = stride
self.path = path
self.albumentations = Albumentations() if augment else None
try:
f = [] # image files
for p in path if isinstance(path, list) else [path]:
p = Path(p) # os-agnostic
if p.is_dir(): # dir
f += glob.glob(str(p / '**' / '*.*'), recursive=True)
# f = list(p.rglob('**/*.*')) # pathlib
elif p.is_file(): # file
with open(p, 'r') as t:
t = t.read().strip().splitlines()
parent = str(p.parent) + os.sep
f += [x.replace('./', parent) if x.startswith('./') else x for x in t] # local to global path
# f += [p.parent / x.lstrip(os.sep) for x in t] # local to global path (pathlib)
else:
raise Exception(f'{prefix}{p} does not exist')
self.img_files = sorted([x.replace('/', os.sep) for x in f if x.split('.')[-1].lower() in IMG_FORMATS])
# self.img_files = sorted([x for x in f if x.suffix[1:].lower() in img_formats]) # pathlib
assert self.img_files, f'{prefix}No images found'
except Exception as e:
raise Exception(f'{prefix}Error loading data from {path}: {e}\nSee {HELP_URL}')
# Check cache
self.label_files = img2label_paths(self.img_files) # labels
cache_path = (p if p.is_file() else Path(self.label_files[0]).parent).with_suffix('.cache')
try:
cache, exists = np.load(cache_path, allow_pickle=True).item(), True # load dict
assert cache['version'] == self.cache_version # same version
assert cache['hash'] == get_hash(self.label_files + self.img_files) # same hash
except:
cache, exists = self.cache_labels(cache_path, prefix), False # cache
# Display cache
nf, nm, ne, nc, n = cache.pop('results') # found, missing, empty, corrupted, total
if exists:
d = f"Scanning '{cache_path}' images and labels... {nf} found, {nm} missing, {ne} empty, {nc} corrupted"
tqdm(None, desc=prefix + d, total=n, initial=n) # display cache results
if cache['msgs']:
logging.info('\n'.join(cache['msgs'])) # display warnings
assert nf > 0 or not augment, f'{prefix}No labels in {cache_path}. Can not train without labels. See {HELP_URL}'
# Read cache
[cache.pop(k) for k in ('hash', 'version', 'msgs')] # remove items
labels, shapes, self.segments = zip(*cache.values())
self.labels = list(labels)
self.shapes = np.array(shapes, dtype=np.float64)
self.img_files = list(cache.keys()) # update
self.label_files = img2label_paths(cache.keys()) # update
if single_cls:
for x in self.labels:
x[:, 0] = 0
n = len(shapes) # number of images
bi = np.floor(np.arange(n) / batch_size).astype(np.int_) # batch index
nb = bi[-1] + 1 # number of batches
self.batch = bi # batch index of image
self.n = n
self.indices = range(n)
# Rectangular Training
if self.rect:
# Sort by aspect ratio
s = self.shapes # wh
ar = s[:, 1] / s[:, 0] # aspect ratio
irect = ar.argsort()
self.img_files = [self.img_files[i] for i in irect]
self.label_files = [self.label_files[i] for i in irect]
self.labels = [self.labels[i] for i in irect]
self.shapes = s[irect] # wh
ar = ar[irect]
# Set training image shapes
shapes = [[1, 1]] * nb
for i in range(nb):
ari = ar[bi == i]
mini, maxi = ari.min(), ari.max()
if maxi < 1:
shapes[i] = [maxi, 1]
elif mini > 1:
shapes[i] = [1, 1 / mini]
self.batch_shapes = np.ceil(np.array(shapes) * img_size / stride + pad).astype(np.int_) * stride
# Cache images into memory for faster training (WARNING: large datasets may exceed system RAM)
self.imgs, self.img_npy = [None] * n, [None] * n
if cache_images:
if cache_images == 'disk':
self.im_cache_dir = Path(Path(self.img_files[0]).parent.as_posix() + '_npy')
self.img_npy = [self.im_cache_dir / Path(f).with_suffix('.npy').name for f in self.img_files]
self.im_cache_dir.mkdir(parents=True, exist_ok=True)
gb = 0 # Gigabytes of cached images
self.img_hw0, self.img_hw = [None] * n, [None] * n
results = ThreadPool(NUM_THREADS).imap(lambda x: load_image(*x), zip(repeat(self), range(n)))
pbar = tqdm(enumerate(results), total=n)
for i, x in pbar:
if cache_images == 'disk':
if not self.img_npy[i].exists():
np.save(self.img_npy[i].as_posix(), x[0])
gb += self.img_npy[i].stat().st_size
else:
self.imgs[i], self.img_hw0[i], self.img_hw[i] = x # im, hw_orig, hw_resized = load_image(self, i)
gb += self.imgs[i].nbytes
pbar.desc = f'{prefix}Caching images ({gb / 1E9:.1f}GB {cache_images})'
pbar.close()
def cache_labels(self, path=Path('./labels.cache'), prefix=''):
# Cache dataset labels, check images and read shapes
x = {} # dict
nm, nf, ne, nc, msgs = 0, 0, 0, 0, [] # number missing, found, empty, corrupt, messages
desc = f"{prefix}Scanning '{path.parent / path.stem}' images and labels..."
with Pool(NUM_THREADS) as pool:
pbar = tqdm(pool.imap(verify_image_label, zip(self.img_files, self.label_files, repeat(prefix))),
desc=desc, total=len(self.img_files))
for im_file, l, shape, segments, nm_f, nf_f, ne_f, nc_f, msg in pbar:
nm += nm_f
nf += nf_f
ne += ne_f
nc += nc_f
if im_file:
x[im_file] = [l, shape, segments]
if msg:
msgs.append(msg)
pbar.desc = f"{desc}{nf} found, {nm} missing, {ne} empty, {nc} corrupted"
pbar.close()
if msgs:
logging.info('\n'.join(msgs))
if nf == 0:
logging.info(f'{prefix}WARNING: No labels found in {path}. See {HELP_URL}')
x['hash'] = get_hash(self.label_files + self.img_files)
x['results'] = nf, nm, ne, nc, len(self.img_files)
x['msgs'] = msgs # warnings
x['version'] = self.cache_version # cache version
try:
np.save(path, x) # save cache for next time
path.with_suffix('.cache.npy').rename(path) # remove .npy suffix
logging.info(f'{prefix}New cache created: {path}')
except Exception as e:
logging.info(f'{prefix}WARNING: Cache directory {path.parent} is not writeable: {e}') # path not writeable
return x
def __len__(self):
return len(self.img_files)
# def __iter__(self):
# self.count = -1
# print('ran dataset iter')
# #self.shuffled_vector = np.random.permutation(self.nF) if self.augment else np.arange(self.nF)
# return self
def __getitem__(self, index):
index = self.indices[index] # linear, shuffled, or image_weights
hyp = self.hyp
mosaic = self.mosaic and random.random() < hyp['mosaic']
if mosaic:
# Load mosaic
img, labels = load_mosaic(self, index)
shapes = None
# MixUp augmentation
if random.random() < hyp['mixup']:
img, labels = mixup(img, labels, *load_mosaic(self, random.randint(0, self.n - 1)))
else:
# Load image
img, (h0, w0), (h, w) = load_image(self, index)
# Letterbox
shape = self.batch_shapes[self.batch[index]] if self.rect else self.img_size # final letterboxed shape
img, ratio, pad = letterbox(img, shape, auto=False, scaleup=self.augment)
shapes = (h0, w0), ((h / h0, w / w0), pad) # for COCO mAP rescaling
labels = self.labels[index].copy()
if labels.size: # normalized xywh to pixel xyxy format
labels[:, 1:] = xywhn2xyxy(labels[:, 1:], ratio[0] * w, ratio[1] * h, padw=pad[0], padh=pad[1])
if self.augment:
img, labels = random_perspective(img, labels,
degrees=hyp['degrees'],
translate=hyp['translate'],
scale=hyp['scale'],
shear=hyp['shear'],
perspective=hyp['perspective'])
nl = len(labels) # number of labels
if nl:
labels[:, 1:5] = xyxy2xywhn(labels[:, 1:5], w=img.shape[1], h=img.shape[0], clip=True, eps=1E-3)
if self.augment:
# Albumentations
img, labels = self.albumentations(img, labels)
nl = len(labels) # update after albumentations
# HSV color-space
augment_hsv(img, hgain=hyp['hsv_h'], sgain=hyp['hsv_s'], vgain=hyp['hsv_v'])
# Flip up-down
if random.random() < hyp['flipud']:
img = np.flipud(img)
if nl:
labels[:, 2] = 1 - labels[:, 2]
# Flip left-right
if random.random() < hyp['fliplr']:
img = np.fliplr(img)
if nl:
labels[:, 1] = 1 - labels[:, 1]
# Cutouts
# labels = cutout(img, labels, p=0.5)
labels_out = torch.zeros((nl, 6))
if nl:
labels_out[:, 1:] = torch.from_numpy(labels)
# Convert
img = img.transpose((2, 0, 1))[::-1] # HWC to CHW, BGR to RGB
img = np.ascontiguousarray(img)
return torch.from_numpy(img), labels_out, self.img_files[index], shapes
@staticmethod
def collate_fn(batch):
img, label, path, shapes = zip(*batch) # transposed
for i, l in enumerate(label):
l[:, 0] = i # add target image index for build_targets()
return torch.stack(img, 0), torch.cat(label, 0), path, shapes
@staticmethod
def collate_fn4(batch):
img, label, path, shapes = zip(*batch) # transposed
n = len(shapes) // 4
img4, label4, path4, shapes4 = [], [], path[:n], shapes[:n]
ho = torch.tensor([[0., 0, 0, 1, 0, 0]])
wo = torch.tensor([[0., 0, 1, 0, 0, 0]])
s = torch.tensor([[1, 1, .5, .5, .5, .5]]) # scale
for i in range(n): # zidane torch.zeros(16,3,720,1280) # BCHW
i *= 4
if random.random() < 0.5:
im = F.interpolate(img[i].unsqueeze(0).float(), scale_factor=2., mode='bilinear', align_corners=False)[
0].type(img[i].type())
l = label[i]
else:
im = torch.cat((torch.cat((img[i], img[i + 1]), 1), torch.cat((img[i + 2], img[i + 3]), 1)), 2)
l = torch.cat((label[i], label[i + 1] + ho, label[i + 2] + wo, label[i + 3] + ho + wo), 0) * s
img4.append(im)
label4.append(l)
for i, l in enumerate(label4):
l[:, 0] = i # add target image index for build_targets()
return torch.stack(img4, 0), torch.cat(label4, 0), path4, shapes4
# Ancillary functions --------------------------------------------------------------------------------------------------
def load_image(self, i):
# loads 1 image from dataset index 'i', returns im, original hw, resized hw
im = self.imgs[i]
if im is None: # not cached in ram
npy = self.img_npy[i]
if npy and npy.exists(): # load npy
im = np.load(npy)
else: # read image
path = self.img_files[i]
im = cv2.imread(path) # BGR
assert im is not None, 'Image Not Found ' + path
h0, w0 = im.shape[:2] # orig hw
r = self.img_size / max(h0, w0) # ratio
if r != 1: # if sizes are not equal
im = cv2.resize(im, (int(w0 * r), int(h0 * r)),
interpolation=cv2.INTER_AREA if r < 1 and not self.augment else cv2.INTER_LINEAR)
return im, (h0, w0), im.shape[:2] # im, hw_original, hw_resized
else:
return self.imgs[i], self.img_hw0[i], self.img_hw[i] # im, hw_original, hw_resized
def load_mosaic(self, index):
# YOLOv5 4-mosaic loader. Loads 1 image + 3 random images into a 4-image mosaic
labels4, segments4 = [], []
s = self.img_size
yc, xc = [int(random.uniform(-x, 2 * s + x)) for x in self.mosaic_border] # mosaic center x, y
indices = [index] + random.choices(self.indices, k=3) # 3 additional image indices
random.shuffle(indices)
for i, index in enumerate(indices):
# Load image
img, _, (h, w) = load_image(self, index)
# place img in img4
if i == 0: # top left
img4 = np.full((s * 2, s * 2, img.shape[2]), 114, dtype=np.uint8) # base image with 4 tiles
x1a, y1a, x2a, y2a = max(xc - w, 0), max(yc - h, 0), xc, yc # xmin, ymin, xmax, ymax (large image)
x1b, y1b, x2b, y2b = w - (x2a - x1a), h - (y2a - y1a), w, h # xmin, ymin, xmax, ymax (small image)
elif i == 1: # top right
x1a, y1a, x2a, y2a = xc, max(yc - h, 0), min(xc + w, s * 2), yc
x1b, y1b, x2b, y2b = 0, h - (y2a - y1a), min(w, x2a - x1a), h
elif i == 2: # bottom left
x1a, y1a, x2a, y2a = max(xc - w, 0), yc, xc, min(s * 2, yc + h)
x1b, y1b, x2b, y2b = w - (x2a - x1a), 0, w, min(y2a - y1a, h)
elif i == 3: # bottom right
x1a, y1a, x2a, y2a = xc, yc, min(xc + w, s * 2), min(s * 2, yc + h)
x1b, y1b, x2b, y2b = 0, 0, min(w, x2a - x1a), min(y2a - y1a, h)
img4[y1a:y2a, x1a:x2a] = img[y1b:y2b, x1b:x2b] # img4[ymin:ymax, xmin:xmax]
padw = x1a - x1b
padh = y1a - y1b
# Labels
labels, segments = self.labels[index].copy(), self.segments[index].copy()
if labels.size:
labels[:, 1:] = xywhn2xyxy(labels[:, 1:], w, h, padw, padh) # normalized xywh to pixel xyxy format
segments = [xyn2xy(x, w, h, padw, padh) for x in segments]
labels4.append(labels)
segments4.extend(segments)
# Concat/clip labels
labels4 = np.concatenate(labels4, 0)
for x in (labels4[:, 1:], *segments4):
np.clip(x, 0, 2 * s, out=x) # clip when using random_perspective()
# img4, labels4 = replicate(img4, labels4) # replicate
# Augment
img4, labels4, segments4 = copy_paste(img4, labels4, segments4, p=self.hyp['copy_paste'])
img4, labels4 = random_perspective(img4, labels4, segments4,
degrees=self.hyp['degrees'],
translate=self.hyp['translate'],
scale=self.hyp['scale'],
shear=self.hyp['shear'],
perspective=self.hyp['perspective'],
border=self.mosaic_border) # border to remove
return img4, labels4
def load_mosaic9(self, index):
# YOLOv5 9-mosaic loader. Loads 1 image + 8 random images into a 9-image mosaic
labels9, segments9 = [], []
s = self.img_size
indices = [index] + random.choices(self.indices, k=8) # 8 additional image indices
random.shuffle(indices)
for i, index in enumerate(indices):
# Load image
img, _, (h, w) = load_image(self, index)
# place img in img9
if i == 0: # center
img9 = np.full((s * 3, s * 3, img.shape[2]), 114, dtype=np.uint8) # base image with 4 tiles
h0, w0 = h, w
c = s, s, s + w, s + h # xmin, ymin, xmax, ymax (base) coordinates
elif i == 1: # top
c = s, s - h, s + w, s
elif i == 2: # top right
c = s + wp, s - h, s + wp + w, s
elif i == 3: # right
c = s + w0, s, s + w0 + w, s + h
elif i == 4: # bottom right
c = s + w0, s + hp, s + w0 + w, s + hp + h
elif i == 5: # bottom
c = s + w0 - w, s + h0, s + w0, s + h0 + h
elif i == 6: # bottom left
c = s + w0 - wp - w, s + h0, s + w0 - wp, s + h0 + h
elif i == 7: # left
c = s - w, s + h0 - h, s, s + h0
elif i == 8: # top left
c = s - w, s + h0 - hp - h, s, s + h0 - hp
padx, pady = c[:2]
x1, y1, x2, y2 = [max(x, 0) for x in c] # allocate coords
# Labels
labels, segments = self.labels[index].copy(), self.segments[index].copy()
if labels.size:
labels[:, 1:] = xywhn2xyxy(labels[:, 1:], w, h, padx, pady) # normalized xywh to pixel xyxy format
segments = [xyn2xy(x, w, h, padx, pady) for x in segments]
labels9.append(labels)
segments9.extend(segments)
# Image
img9[y1:y2, x1:x2] = img[y1 - pady:, x1 - padx:] # img9[ymin:ymax, xmin:xmax]
hp, wp = h, w # height, width previous
# Offset
yc, xc = [int(random.uniform(0, s)) for _ in self.mosaic_border] # mosaic center x, y
img9 = img9[yc:yc + 2 * s, xc:xc + 2 * s]
# Concat/clip labels
labels9 = np.concatenate(labels9, 0)
labels9[:, [1, 3]] -= xc
labels9[:, [2, 4]] -= yc
c = np.array([xc, yc]) # centers
segments9 = [x - c for x in segments9]
for x in (labels9[:, 1:], *segments9):
np.clip(x, 0, 2 * s, out=x) # clip when using random_perspective()
# img9, labels9 = replicate(img9, labels9) # replicate
# Augment
img9, labels9 = random_perspective(img9, labels9, segments9,
degrees=self.hyp['degrees'],
translate=self.hyp['translate'],
scale=self.hyp['scale'],
shear=self.hyp['shear'],
perspective=self.hyp['perspective'],
border=self.mosaic_border) # border to remove
return img9, labels9
def create_folder(path='./new'):
# Create folder
if os.path.exists(path):
shutil.rmtree(path) # delete output folder
os.makedirs(path) # make new output folder
def flatten_recursive(path='../datasets/coco128'):
# Flatten a recursive directory by bringing all files to top level
new_path = Path(path + '_flat')
create_folder(new_path)
for file in tqdm(glob.glob(str(Path(path)) + '/**/*.*', recursive=True)):
shutil.copyfile(file, new_path / Path(file).name)
def extract_boxes(path='../datasets/coco128'): # from utils.datasets import *; extract_boxes()
# Convert detection dataset into classification dataset, with one directory per class
path = Path(path) # images dir
shutil.rmtree(path / 'classifier') if (path / 'classifier').is_dir() else None # remove existing
files = list(path.rglob('*.*'))
n = len(files) # number of files
for im_file in tqdm(files, total=n):
if im_file.suffix[1:] in IMG_FORMATS:
# image
im = cv2.imread(str(im_file))[..., ::-1] # BGR to RGB
h, w = im.shape[:2]
# labels
lb_file = Path(img2label_paths([str(im_file)])[0])
if Path(lb_file).exists():
with open(lb_file, 'r') as f:
lb = np.array([x.split() for x in f.read().strip().splitlines()], dtype=np.float32) # labels
for j, x in enumerate(lb):
c = int(x[0]) # class
f = (path / 'classifier') / f'{c}' / f'{path.stem}_{im_file.stem}_{j}.jpg' # new filename
if not f.parent.is_dir():
f.parent.mkdir(parents=True)
b = x[1:] * [w, h, w, h] # box
# b[2:] = b[2:].max() # rectangle to square
b[2:] = b[2:] * 1.2 + 3 # pad
b = xywh2xyxy(b.reshape(-1, 4)).ravel().astype(np.int_)
b[[0, 2]] = np.clip(b[[0, 2]], 0, w) # clip boxes outside of image
b[[1, 3]] = np.clip(b[[1, 3]], 0, h)
assert cv2.imwrite(str(f), im[b[1]:b[3], b[0]:b[2]]), f'box failure in {f}'
def autosplit(path='../datasets/coco128/images', weights=(0.9, 0.1, 0.0), annotated_only=False):
""" Autosplit a dataset into train/val/test splits and save path/autosplit_*.txt files
Usage: from utils.datasets import *; autosplit()
Arguments
path: Path to images directory
weights: Train, val, test weights (list, tuple)
annotated_only: Only use images with an annotated txt file
"""
path = Path(path) # images dir
files = sum([list(path.rglob(f"*.{img_ext}")) for img_ext in IMG_FORMATS], []) # image files only
n = len(files) # number of files
random.seed(0) # for reproducibility
indices = random.choices([0, 1, 2], weights=weights, k=n) # assign each image to a split
txt = ['autosplit_train.txt', 'autosplit_val.txt', 'autosplit_test.txt'] # 3 txt files
[(path.parent / x).unlink(missing_ok=True) for x in txt] # remove existing
print(f'Autosplitting images from {path}' + ', using *.txt labeled images only' * annotated_only)
for i, img in tqdm(zip(indices, files), total=n):
if not annotated_only or Path(img2label_paths([str(img)])[0]).exists(): # check label
with open(path.parent / txt[i], 'a') as f:
f.write('./' + img.relative_to(path.parent).as_posix() + '\n') # add image to txt file
def verify_image_label(args):
# Verify one image-label pair
im_file, lb_file, prefix = args
nm, nf, ne, nc, msg, segments = 0, 0, 0, 0, '', [] # number (missing, found, empty, corrupt), message, segments
try:
# verify images
im = Image.open(im_file)
im.verify() # PIL verify
shape = exif_size(im) # image size
assert (shape[0] > 9) & (shape[1] > 9), f'image size {shape} <10 pixels'
assert im.format.lower() in IMG_FORMATS, f'invalid image format {im.format}'
if im.format.lower() in ('jpg', 'jpeg'):
with open(im_file, 'rb') as f:
f.seek(-2, 2)
if f.read() != b'\xff\xd9': # corrupt JPEG
Image.open(im_file).save(im_file, format='JPEG', subsampling=0, quality=100) # re-save image
msg = f'{prefix}WARNING: corrupt JPEG restored and saved {im_file}'
# verify labels
if os.path.isfile(lb_file):
nf = 1 # label found
with open(lb_file, 'r') as f:
l = [x.split() for x in f.read().strip().splitlines() if len(x)]
if any([len(x) > 8 for x in l]): # is segment
classes = np.array([x[0] for x in l], dtype=np.float32)
segments = [np.array(x[1:], dtype=np.float32).reshape(-1, 2) for x in l] # (cls, xy1...)
l = np.concatenate((classes.reshape(-1, 1), segments2boxes(segments)), 1) # (cls, xywh)
l = np.array(l, dtype=np.float32)
if len(l):
assert l.shape[1] == 5, 'labels require 5 columns each'
assert (l >= 0).all(), 'negative labels'
assert (l[:, 1:] <= 1).all(), 'non-normalized or out of bounds coordinate labels'
assert np.unique(l, axis=0).shape[0] == l.shape[0], 'duplicate labels'
else:
ne = 1 # label empty
l = np.zeros((0, 5), dtype=np.float32)
else:
nm = 1 # label missing
l = np.zeros((0, 5), dtype=np.float32)
return im_file, l, shape, segments, nm, nf, ne, nc, msg
except Exception as e:
nc = 1
msg = f'{prefix}WARNING: Ignoring corrupted image and/or label {im_file}: {e}'
return [None, None, None, None, nm, nf, ne, nc, msg]
def dataset_stats(path='coco128.yaml', autodownload=False, verbose=False, profile=False, hub=False):
""" Return dataset statistics dictionary with images and instances counts per split per class
To run in parent directory: export PYTHONPATH="$PWD/yolov5"
Usage1: from utils.datasets import *; dataset_stats('coco128.yaml', autodownload=True)
Usage2: from utils.datasets import *; dataset_stats('../datasets/coco128_with_yaml.zip')
Arguments
path: Path to data.yaml or data.zip (with data.yaml inside data.zip)
autodownload: Attempt to download dataset if not found locally
verbose: Print stats dictionary
"""
def round_labels(labels):
# Update labels to integer class and 6 decimal place floats
return [[int(c), *[round(x, 4) for x in points]] for c, *points in labels]
def unzip(path):
# Unzip data.zip TODO: CONSTRAINT: path/to/abc.zip MUST unzip to 'path/to/abc/'
if str(path).endswith('.zip'): # path is data.zip
assert Path(path).is_file(), f'Error unzipping {path}, file not found'
ZipFile(path).extractall(path=path.parent) # unzip
dir = path.with_suffix('') # dataset directory == zip name
return True, str(dir), next(dir.rglob('*.yaml')) # zipped, data_dir, yaml_path
else: # path is data.yaml
return False, None, path
def hub_ops(f, max_dim=1920):
# HUB ops for 1 image 'f': resize and save at reduced quality in /dataset-hub for web/app viewing
f_new = im_dir / Path(f).name # dataset-hub image filename
try: # use PIL
im = Image.open(f)
r = max_dim / max(im.height, im.width) # ratio
if r < 1.0: # image too large
im = im.resize((int(im.width * r), int(im.height * r)))
im.save(f_new, quality=75) # save
except Exception as e: # use OpenCV
print(f'WARNING: HUB ops PIL failure {f}: {e}')
im = cv2.imread(f)
im_height, im_width = im.shape[:2]
r = max_dim / max(im_height, im_width) # ratio
if r < 1.0: # image too large
im = cv2.resize(im, (int(im_width * r), int(im_height * r)), interpolation=cv2.INTER_LINEAR)
cv2.imwrite(str(f_new), im)
zipped, data_dir, yaml_path = unzip(Path(path))
with open(check_yaml(yaml_path), errors='ignore') as f:
data = yaml.safe_load(f) # data dict
if zipped:
data['path'] = data_dir # TODO: should this be dir.resolve()?
check_dataset(data, autodownload) # download dataset if missing
hub_dir = Path(data['path'] + ('-hub' if hub else ''))
stats = {'nc': data['nc'], 'names': data['names']} # statistics dictionary
for split in 'train', 'val', 'test':
if data.get(split) is None:
stats[split] = None # i.e. no test set
continue
x = []
dataset = LoadImagesAndLabels(data[split]) # load dataset
for label in tqdm(dataset.labels, total=dataset.n, desc='Statistics'):
x.append(np.bincount(label[:, 0].astype(int), minlength=data['nc']))
x = np.array(x) # shape(128x80)
stats[split] = {'instance_stats': {'total': int(x.sum()), 'per_class': x.sum(0).tolist()},
'image_stats': {'total': dataset.n, 'unlabelled': int(np.all(x == 0, 1).sum()),
'per_class': (x > 0).sum(0).tolist()},
'labels': [{str(Path(k).name): round_labels(v.tolist())} for k, v in
zip(dataset.img_files, dataset.labels)]}
if hub:
im_dir = hub_dir / 'images'
im_dir.mkdir(parents=True, exist_ok=True)
for _ in tqdm(ThreadPool(NUM_THREADS).imap(hub_ops, dataset.img_files), total=dataset.n, desc='HUB Ops'):
pass
# Profile
stats_path = hub_dir / 'stats.json'
if profile:
for _ in range(1):
file = stats_path.with_suffix('.npy')
t1 = time.time()
np.save(file, stats)
t2 = time.time()
x = np.load(file, allow_pickle=True)
print(f'stats.npy times: {time.time() - t2:.3f}s read, {t2 - t1:.3f}s write')
file = stats_path.with_suffix('.json')
t1 = time.time()
with open(file, 'w') as f:
json.dump(stats, f) # save stats *.json
t2 = time.time()
with open(file, 'r') as f:
x = json.load(f) # load hyps dict
print(f'stats.json times: {time.time() - t2:.3f}s read, {t2 - t1:.3f}s write')
# Save, print and return
if hub:
print(f'Saving {stats_path.resolve()}...')
with open(stats_path, 'w') as f:
json.dump(stats, f) # save stats.json
if verbose:
print(json.dumps(stats, indent=2, sort_keys=False))
return stats
utils/downloads.py 0 → 100644
View file @ a7b29f47
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
"""
Download utils
"""
import os
import platform
import subprocess
import time
import urllib
from pathlib import Path
from zipfile import ZipFile
import requests
import torch
def gsutil_getsize(url=''):
# gs://bucket/file size https://cloud.google.com/storage/docs/gsutil/commands/du
s = subprocess.check_output(f'gsutil du {url}', shell=True).decode('utf-8')
return eval(s.split(' ')[0]) if len(s) else 0 # bytes
def safe_download(file, url, url2=None, min_bytes=1E0, error_msg=''):
# Attempts to download file from url or url2, checks and removes incomplete downloads < min_bytes
file = Path(file)
assert_msg = f"Downloaded file '{file}' does not exist or size is < min_bytes={min_bytes}"
try: # url1
print(f'Downloading {url} to {file}...')
torch.hub.download_url_to_file(url, str(file))
assert file.exists() and file.stat().st_size > min_bytes, assert_msg # check
except Exception as e: # url2
file.unlink(missing_ok=True) # remove partial downloads
print(f'ERROR: {e}\nRe-attempting {url2 or url} to {file}...')
os.system(f"curl -L '{url2 or url}' -o '{file}' --retry 3 -C -") # curl download, retry and resume on fail
finally:
if not file.exists() or file.stat().st_size < min_bytes: # check
file.unlink(missing_ok=True) # remove partial downloads
print(f"ERROR: {assert_msg}\n{error_msg}")
print('')
def attempt_download(file, repo='ultralytics/yolov5'): # from utils.downloads import *; attempt_download()
# Attempt file download if does not exist
file = Path(str(file).strip().replace("'", ''))
if not file.exists():
# URL specified
name = Path(urllib.parse.unquote(str(file))).name # decode '%2F' to '/' etc.
if str(file).startswith(('http:/', 'https:/')): # download
url = str(file).replace(':/', '://') # Pathlib turns :// -> :/
name = name.split('?')[0] # parse authentication https://url.com/file.txt?auth...
safe_download(file=name, url=url, min_bytes=1E5)
return name
# GitHub assets
file.parent.mkdir(parents=True, exist_ok=True) # make parent dir (if required)
try:
response = requests.get(f'https://api.github.com/repos/{repo}/releases/latest').json() # github api
assets = [x['name'] for x in response['assets']] # release assets, i.e. ['yolov5s.pt', 'yolov5m.pt', ...]
tag = response['tag_name'] # i.e. 'v1.0'
except: # fallback plan
assets = ['yolov5s.pt', 'yolov5m.pt', 'yolov5l.pt', 'yolov5x.pt',
'yolov5s6.pt', 'yolov5m6.pt', 'yolov5l6.pt', 'yolov5x6.pt']
try:
tag = subprocess.check_output('git tag', shell=True, stderr=subprocess.STDOUT).decode().split()[-1]
except:
tag = 'v5.0' # current release
if name in assets:
safe_download(file,
url=f'https://github.com/{repo}/releases/download/{tag}/{name}',
# url2=f'https://storage.googleapis.com/{repo}/ckpt/{name}', # backup url (optional)
min_bytes=1E5,
error_msg=f'{file} missing, try downloading from https://github.com/{repo}/releases/')
return str(file)
def gdrive_download(id='16TiPfZj7htmTyhntwcZyEEAejOUxuT6m', file='tmp.zip'):
# Downloads a file from Google Drive. from yolov5.utils.downloads import *; gdrive_download()
t = time.time()
file = Path(file)
cookie = Path('cookie') # gdrive cookie
print(f'Downloading https://drive.google.com/uc?export=download&id={id} as {file}... ', end='')
file.unlink(missing_ok=True) # remove existing file
cookie.unlink(missing_ok=True) # remove existing cookie
# Attempt file download
out = "NUL" if platform.system() == "Windows" else "/dev/null"
os.system(f'curl -c ./cookie -s -L "drive.google.com/uc?export=download&id={id}" > {out}')
if os.path.exists('cookie'): # large file
s = f'curl -Lb ./cookie "drive.google.com/uc?export=download&confirm={get_token()}&id={id}" -o {file}'
else: # small file
s = f'curl -s -L -o {file} "drive.google.com/uc?export=download&id={id}"'
r = os.system(s) # execute, capture return
cookie.unlink(missing_ok=True) # remove existing cookie
# Error check
if r != 0:
file.unlink(missing_ok=True) # remove partial
print('Download error ') # raise Exception('Download error')
return r
# Unzip if archive
if file.suffix == '.zip':
print('unzipping... ', end='')
ZipFile(file).extractall(path=file.parent) # unzip
file.unlink() # remove zip
print(f'Done ({time.time() - t:.1f}s)')
return r
def get_token(cookie="./cookie"):
with open(cookie) as f:
for line in f:
if "download" in line:
return line.split()[-1]
return ""
# Google utils: https://cloud.google.com/storage/docs/reference/libraries ----------------------------------------------
#
#
# def upload_blob(bucket_name, source_file_name, destination_blob_name):
# # Uploads a file to a bucket
# # https://cloud.google.com/storage/docs/uploading-objects#storage-upload-object-python
#
# storage_client = storage.Client()
# bucket = storage_client.get_bucket(bucket_name)
# blob = bucket.blob(destination_blob_name)
#
# blob.upload_from_filename(source_file_name)
#
# print('File {} uploaded to {}.'.format(
# source_file_name,
# destination_blob_name))
#
#
# def download_blob(bucket_name, source_blob_name, destination_file_name):
# # Uploads a blob from a bucket
# storage_client = storage.Client()
# bucket = storage_client.get_bucket(bucket_name)
# blob = bucket.blob(source_blob_name)
#
# blob.download_to_filename(destination_file_name)
#
# print('Blob {} downloaded to {}.'.format(
# source_blob_name,
# destination_file_name))
utils/flask_rest_api/README.md 0 → 100644
View file @ a7b29f47
# Flask REST API
[REST](https://en.wikipedia.org/wiki/Representational_state_transfer) [API](https://en.wikipedia.org/wiki/API)s are
commonly used to expose Machine Learning (ML) models to other services. This folder contains an example REST API
created using Flask to expose the YOLOv5s model from [PyTorch Hub](https://pytorch.org/hub/ultralytics_yolov5/).
## Requirements
[Flask](https://palletsprojects.com/p/flask/) is required. Install with:
```shell
$ pip install Flask
```
## Run
After Flask installation run:
```shell
$ python3 restapi.py --port 5000
```
Then use [curl](https://curl.se/) to perform a request:
```shell
$ curl -X POST -F image=@zidane.jpg 'http://localhost:5000/v1/object-detection/yolov5s'
```
The model inference results are returned as a JSON response:
```json
[
{
"class": 0,
"confidence": 0.8900438547,
"height": 0.9318675399,
"name": "person",
"width": 0.3264600933,
"xcenter": 0.7438579798,
"ycenter": 0.5207948685
},
{
"class": 0,
"confidence": 0.8440024257,
"height": 0.7155083418,
"name": "person",
"width": 0.6546785235,
"xcenter": 0.427829951,
"ycenter": 0.6334488392
},
{
"class": 27,
"confidence": 0.3771208823,
"height": 0.3902671337,
"name": "tie",
"width": 0.0696444362,
"xcenter": 0.3675483763,
"ycenter": 0.7991207838
},
{
"class": 27,
"confidence": 0.3527112305,
"height": 0.1540903747,
"name": "tie",
"width": 0.0336618312,
"xcenter": 0.7814827561,
"ycenter": 0.5065554976
}
]
```
An example python script to perform inference using [requests](https://docs.python-requests.org/en/master/) is given
in `example_request.py`
utils/flask_rest_api/example_request.py 0 → 100644
View file @ a7b29f47
"""Perform test request"""
import pprint
import requests
DETECTION_URL = "http://localhost:5000/v1/object-detection/yolov5s"
TEST_IMAGE = "zidane.jpg"
image_data = open(TEST_IMAGE, "rb").read()
response = requests.post(DETECTION_URL, files={"image": image_data}).json()
pprint.pprint(response)
utils/flask_rest_api/restapi.py 0 → 100644
View file @ a7b29f47
"""
Run a rest API exposing the yolov5s object detection model
"""
import argparse
import io
import torch
from PIL import Image
from flask import Flask, request
app = Flask(__name__)
DETECTION_URL = "/v1/object-detection/yolov5s"
@app.route(DETECTION_URL, methods=["POST"])
def predict():
if not request.method == "POST":
return
if request.files.get("image"):
image_file = request.files["image"]
image_bytes = image_file.read()
img = Image.open(io.BytesIO(image_bytes))
results = model(img, size=640) # reduce size=320 for faster inference
return results.pandas().xyxy[0].to_json(orient="records")
if __name__ == "__main__":
parser = argparse.ArgumentParser(description="Flask API exposing YOLOv5 model")
parser.add_argument("--port", default=5000, type=int, help="port number")
args = parser.parse_args()
model = torch.hub.load("ultralytics/yolov5", "yolov5s", force_reload=True) # force_reload to recache
app.run(host="0.0.0.0", port=args.port) # debug=True causes Restarting with stat
utils/general.py 0 → 100644
View file @ a7b29f47
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
"""
General utils
"""
import contextlib
import glob
import logging
import math
import os
import platform
import random
import re
import signal
import time
import urllib
from itertools import repeat
from multiprocessing.pool import ThreadPool
from pathlib import Path
from subprocess import check_output
from zipfile import ZipFile
import cv2
import numpy as np
import pandas as pd
import pkg_resources as pkg
import torch
import torchvision
import yaml
from utils.downloads import gsutil_getsize
from utils.metrics import box_iou, fitness
# Settings
torch.set_printoptions(linewidth=320, precision=5, profile='long')
np.set_printoptions(linewidth=320, formatter={'float_kind': '{:11.5g}'.format}) # format short g, %precision=5
pd.options.display.max_columns = 10
cv2.setNumThreads(0) # prevent OpenCV from multithreading (incompatible with PyTorch DataLoader)
os.environ['NUMEXPR_MAX_THREADS'] = str(min(os.cpu_count(), 8)) # NumExpr max threads
FILE = Path(__file__).resolve()
ROOT = FILE.parents[1] # YOLOv5 root directory
class Profile(contextlib.ContextDecorator):
# Usage: @Profile() decorator or 'with Profile():' context manager
def __enter__(self):
self.start = time.time()
def __exit__(self, type, value, traceback):
print(f'Profile results: {time.time() - self.start:.5f}s')
class Timeout(contextlib.ContextDecorator):
# Usage: @Timeout(seconds) decorator or 'with Timeout(seconds):' context manager
def __init__(self, seconds, *, timeout_msg='', suppress_timeout_errors=True):
self.seconds = int(seconds)
self.timeout_message = timeout_msg
self.suppress = bool(suppress_timeout_errors)
def _timeout_handler(self, signum, frame):
raise TimeoutError(self.timeout_message)
def __enter__(self):
signal.signal(signal.SIGALRM, self._timeout_handler) # Set handler for SIGALRM
signal.alarm(self.seconds) # start countdown for SIGALRM to be raised
def __exit__(self, exc_type, exc_val, exc_tb):
signal.alarm(0) # Cancel SIGALRM if it's scheduled
if self.suppress and exc_type is TimeoutError: # Suppress TimeoutError
return True
def try_except(func):
# try-except function. Usage: @try_except decorator
def handler(*args, **kwargs):
try:
func(*args, **kwargs)
except Exception as e:
print(e)
return handler
def methods(instance):
# Get class/instance methods
return [f for f in dir(instance) if callable(getattr(instance, f)) and not f.startswith("__")]
def set_logging(rank=-1, verbose=True):
logging.basicConfig(
format="%(message)s",
level=logging.INFO if (verbose and rank in [-1, 0]) else logging.WARN)
def print_args(name, opt):
# Print argparser arguments
print(colorstr(f'{name}: ') + ', '.join(f'{k}={v}' for k, v in vars(opt).items()))
def init_seeds(seed=0):
# Initialize random number generator (RNG) seeds https://pytorch.org/docs/stable/notes/randomness.html
# cudnn seed 0 settings are slower and more reproducible, else faster and less reproducible
import torch.backends.cudnn as cudnn
random.seed(seed)
np.random.seed(seed)
torch.manual_seed(seed)
cudnn.benchmark, cudnn.deterministic = (False, True) if seed == 0 else (True, False)
def get_latest_run(search_dir='.'):
# Return path to most recent 'last.pt' in /runs (i.e. to --resume from)
last_list = glob.glob(f'{search_dir}/**/last*.pt', recursive=True)
return max(last_list, key=os.path.getctime) if last_list else ''
def user_config_dir(dir='Ultralytics', env_var='YOLOV5_CONFIG_DIR'):
# Return path of user configuration directory. Prefer environment variable if exists. Make dir if required.
env = os.getenv(env_var)
if env:
path = Path(env) # use environment variable
else:
cfg = {'Windows': 'AppData/Roaming', 'Linux': '.config', 'Darwin': 'Library/Application Support'} # 3 OS dirs
path = Path.home() / cfg.get(platform.system(), '') # OS-specific config dir
path = (path if is_writeable(path) else Path('/tmp')) / dir # GCP and AWS lambda fix, only /tmp is writeable
path.mkdir(exist_ok=True) # make if required
return path
def is_writeable(dir, test=False):
# Return True if directory has write permissions, test opening a file with write permissions if test=True
if test: # method 1
file = Path(dir) / 'tmp.txt'
try:
with open(file, 'w'): # open file with write permissions
pass
file.unlink() # remove file
return True
except IOError:
return False
else: # method 2
return os.access(dir, os.R_OK) # possible issues on Windows
def is_docker():
# Is environment a Docker container?
return Path('/workspace').exists() # or Path('/.dockerenv').exists()
def is_colab():
# Is environment a Google Colab instance?
try:
import google.colab
return True
except ImportError:
return False
def is_pip():
# Is file in a pip package?
return 'site-packages' in Path(__file__).resolve().parts
def is_ascii(s=''):
# Is string composed of all ASCII (no UTF) characters? (note str().isascii() introduced in python 3.7)
s = str(s) # convert list, tuple, None, etc. to str
return len(s.encode().decode('ascii', 'ignore')) == len(s)
def is_chinese(s='人工智能'):
# Is string composed of any Chinese characters?
return re.search('[\u4e00-\u9fff]', s)
def emojis(str=''):
# Return platform-dependent emoji-safe version of string
return str.encode().decode('ascii', 'ignore') if platform.system() == 'Windows' else str
def file_size(path):
# Return file/dir size (MB)
path = Path(path)
if path.is_file():
return path.stat().st_size / 1E6
elif path.is_dir():
return sum(f.stat().st_size for f in path.glob('**/*') if f.is_file()) / 1E6
else:
return 0.0
def check_online():
# Check internet connectivity
import socket
try:
socket.create_connection(("1.1.1.1", 443), 5) # check host accessibility
return True
except OSError:
return False
@try_except
def check_git_status():
# Recommend 'git pull' if code is out of date
msg = ', for updates see https://github.com/ultralytics/yolov5'
print(colorstr('github: '), end='')
assert Path('.git').exists(), 'skipping check (not a git repository)' + msg
assert not is_docker(), 'skipping check (Docker image)' + msg
assert check_online(), 'skipping check (offline)' + msg
cmd = 'git fetch && git config --get remote.origin.url'
url = check_output(cmd, shell=True, timeout=5).decode().strip().rstrip('.git') # git fetch
branch = check_output('git rev-parse --abbrev-ref HEAD', shell=True).decode().strip() # checked out
n = int(check_output(f'git rev-list {branch}..origin/master --count', shell=True)) # commits behind
if n > 0:
s = f"⚠️ YOLOv5 is out of date by {n} commit{'s' * (n > 1)}. Use `git pull` or `git clone {url}` to update."
else:
s = f'up to date with {url} ✅'
print(emojis(s)) # emoji-safe
def check_python(minimum='3.6.2'):
# Check current python version vs. required python version
check_version(platform.python_version(), minimum, name='Python ')
def check_version(current='0.0.0', minimum='0.0.0', name='version ', pinned=False):
# Check version vs. required version
current, minimum = (pkg.parse_version(x) for x in (current, minimum))
result = (current == minimum) if pinned else (current >= minimum)
assert result, f'{name}{minimum} required by YOLOv5, but {name}{current} is currently installed'
@try_except
def check_requirements(requirements=ROOT / 'requirements.txt', exclude=(), install=True):
# Check installed dependencies meet requirements (pass *.txt file or list of packages)
prefix = colorstr('red', 'bold', 'requirements:')
check_python() # check python version
if isinstance(requirements, (str, Path)): # requirements.txt file
file = Path(requirements)
assert file.exists(), f"{prefix} {file.resolve()} not found, check failed."
requirements = [f'{x.name}{x.specifier}' for x in pkg.parse_requirements(file.open()) if x.name not in exclude]
else: # list or tuple of packages
requirements = [x for x in requirements if x not in exclude]
n = 0 # number of packages updates
for r in requirements:
try:
pkg.require(r)
except Exception as e: # DistributionNotFound or VersionConflict if requirements not met
s = f"{prefix} {r} not found and is required by YOLOv5"
if install:
print(f"{s}, attempting auto-update...")
try:
assert check_online(), f"'pip install {r}' skipped (offline)"
print(check_output(f"pip install '{r}'", shell=True).decode())
n += 1
except Exception as e:
print(f'{prefix} {e}')
else:
print(f'{s}. Please install and rerun your command.')
if n: # if packages updated
source = file.resolve() if 'file' in locals() else requirements
s = f"{prefix} {n} package{'s' * (n > 1)} updated per {source}\n" \
f"{prefix} ⚠️ {colorstr('bold', 'Restart runtime or rerun command for updates to take effect')}\n"
print(emojis(s))
def check_img_size(imgsz, s=32, floor=0):
# Verify image size is a multiple of stride s in each dimension
if isinstance(imgsz, int): # integer i.e. img_size=640
new_size = max(make_divisible(imgsz, int(s)), floor)
else: # list i.e. img_size=[640, 480]
new_size = [max(make_divisible(x, int(s)), floor) for x in imgsz]
if new_size != imgsz:
print(f'WARNING: --img-size {imgsz} must be multiple of max stride {s}, updating to {new_size}')
return new_size
def check_imshow():
# Check if environment supports image displays
try:
assert not is_docker(), 'cv2.imshow() is disabled in Docker environments'
assert not is_colab(), 'cv2.imshow() is disabled in Google Colab environments'
cv2.imshow('test', np.zeros((1, 1, 3)))
cv2.waitKey(1)
cv2.destroyAllWindows()
cv2.waitKey(1)
return True
except Exception as e:
print(f'WARNING: Environment does not support cv2.imshow() or PIL Image.show() image displays\n{e}')
return False
def check_suffix(file='yolov5s.pt', suffix=('.pt',), msg=''):
# Check file(s) for acceptable suffixes
if file and suffix:
if isinstance(suffix, str):
suffix = [suffix]
for f in file if isinstance(file, (list, tuple)) else [file]:
assert Path(f).suffix.lower() in suffix, f"{msg}{f} acceptable suffix is {suffix}"
def check_yaml(file, suffix=('.yaml', '.yml')):
# Search/download YAML file (if necessary) and return path, checking suffix
return check_file(file, suffix)
def check_file(file, suffix=''):
# Search/download file (if necessary) and return path
check_suffix(file, suffix) # optional
file = str(file) # convert to str()
if Path(file).is_file() or file == '': # exists
return file
elif file.startswith(('http:/', 'https:/')): # download
url = str(Path(file)).replace(':/', '://') # Pathlib turns :// -> :/
file = Path(urllib.parse.unquote(file).split('?')[0]).name # '%2F' to '/', split https://url.com/file.txt?auth
print(f'Downloading {url} to {file}...')
torch.hub.download_url_to_file(url, file)
assert Path(file).exists() and Path(file).stat().st_size > 0, f'File download failed: {url}' # check
return file
else: # search
files = []
for d in 'data', 'models', 'utils': # search directories
files.extend(glob.glob(str(ROOT / d / '**' / file), recursive=True)) # find file
assert len(files), f'File not found: {file}' # assert file was found
assert len(files) == 1, f"Multiple files match '{file}', specify exact path: {files}" # assert unique
return files[0] # return file
def check_dataset(data, autodownload=True):
# Download and/or unzip dataset if not found locally
# Usage: https://github.com/ultralytics/yolov5/releases/download/v1.0/coco128_with_yaml.zip
# Download (optional)
extract_dir = ''
if isinstance(data, (str, Path)) and str(data).endswith('.zip'): # i.e. gs://bucket/dir/coco128.zip
download(data, dir='../datasets', unzip=True, delete=False, curl=False, threads=1)
data = next((Path('../datasets') / Path(data).stem).rglob('*.yaml'))
extract_dir, autodownload = data.parent, False
# Read yaml (optional)
if isinstance(data, (str, Path)):
with open(data, errors='ignore') as f:
data = yaml.safe_load(f) # dictionary
# Parse yaml
path = extract_dir or Path(data.get('path') or '') # optional 'path' default to '.'
for k in 'train', 'val', 'test':
if data.get(k): # prepend path
data[k] = str(path / data[k]) if isinstance(data[k], str) else [str(path / x) for x in data[k]]
assert 'nc' in data, "Dataset 'nc' key missing."
if 'names' not in data:
data['names'] = [f'class{i}' for i in range(data['nc'])] # assign class names if missing
train, val, test, s = [data.get(x) for x in ('train', 'val', 'test', 'download')]
if val:
val = [Path(x).resolve() for x in (val if isinstance(val, list) else [val])] # val path
if not all(x.exists() for x in val):
print('\nWARNING: Dataset not found, nonexistent paths: %s' % [str(x) for x in val if not x.exists()])
if s and autodownload: # download script
root = path.parent if 'path' in data else '..' # unzip directory i.e. '../'
if s.startswith('http') and s.endswith('.zip'): # URL
f = Path(s).name # filename
print(f'Downloading {s} to {f}...')
torch.hub.download_url_to_file(s, f)
Path(root).mkdir(parents=True, exist_ok=True) # create root
ZipFile(f).extractall(path=root) # unzip
Path(f).unlink() # remove zip
r = None # success
elif s.startswith('bash '): # bash script
print(f'Running {s} ...')
r = os.system(s)
else: # python script
r = exec(s, {'yaml': data}) # return None
print(f"Dataset autodownload {f'success, saved to {root}' if r in (0, None) else 'failure'}\n")
else:
raise Exception('Dataset not found.')
return data # dictionary
def url2file(url):
# Convert URL to filename, i.e. https://url.com/file.txt?auth -> file.txt
url = str(Path(url)).replace(':/', '://') # Pathlib turns :// -> :/
file = Path(urllib.parse.unquote(url)).name.split('?')[0] # '%2F' to '/', split https://url.com/file.txt?auth
return file
def download(url, dir='.', unzip=True, delete=True, curl=False, threads=1):
# Multi-threaded file download and unzip function, used in data.yaml for autodownload
def download_one(url, dir):
# Download 1 file
f = dir / Path(url).name # filename
if Path(url).is_file(): # exists in current path
Path(url).rename(f) # move to dir
elif not f.exists():
print(f'Downloading {url} to {f}...')
if curl:
os.system(f"curl -L '{url}' -o '{f}' --retry 9 -C -") # curl download, retry and resume on fail
else:
torch.hub.download_url_to_file(url, f, progress=True) # torch download
if unzip and f.suffix in ('.zip', '.gz'):
print(f'Unzipping {f}...')
if f.suffix == '.zip':
ZipFile(f).extractall(path=dir) # unzip
elif f.suffix == '.gz':
os.system(f'tar xfz {f} --directory {f.parent}') # unzip
if delete:
f.unlink() # remove zip
dir = Path(dir)
dir.mkdir(parents=True, exist_ok=True) # make directory
if threads > 1:
pool = ThreadPool(threads)
pool.imap(lambda x: download_one(*x), zip(url, repeat(dir))) # multi-threaded
pool.close()
pool.join()
else:
for u in [url] if isinstance(url, (str, Path)) else url:
download_one(u, dir)
def make_divisible(x, divisor):
# Returns x evenly divisible by divisor
return math.ceil(x / divisor) * divisor
def clean_str(s):
# Cleans a string by replacing special characters with underscore _
return re.sub(pattern="[|@#!¡·$€%&()=?¿^*;:,¨´><+]", repl="_", string=s)
def one_cycle(y1=0.0, y2=1.0, steps=100):
# lambda function for sinusoidal ramp from y1 to y2 https://arxiv.org/pdf/1812.01187.pdf
return lambda x: ((1 - math.cos(x * math.pi / steps)) / 2) * (y2 - y1) + y1
def colorstr(*input):
# Colors a string https://en.wikipedia.org/wiki/ANSI_escape_code, i.e. colorstr('blue', 'hello world')
*args, string = input if len(input) > 1 else ('blue', 'bold', input[0]) # color arguments, string
colors = {'black': '\033[30m', # basic colors
'red': '\033[31m',
'green': '\033[32m',
'yellow': '\033[33m',
'blue': '\033[34m',
'magenta': '\033[35m',
'cyan': '\033[36m',
'white': '\033[37m',
'bright_black': '\033[90m', # bright colors
'bright_red': '\033[91m',
'bright_green': '\033[92m',
'bright_yellow': '\033[93m',
'bright_blue': '\033[94m',
'bright_magenta': '\033[95m',
'bright_cyan': '\033[96m',
'bright_white': '\033[97m',
'end': '\033[0m', # misc
'bold': '\033[1m',
'underline': '\033[4m'}
return ''.join(colors[x] for x in args) + f'{string}' + colors['end']
def labels_to_class_weights(labels, nc=80):
# Get class weights (inverse frequency) from training labels
if labels[0] is None: # no labels loaded
return torch.Tensor()
labels = np.concatenate(labels, 0) # labels.shape = (866643, 5) for COCO
classes = labels[:, 0].astype(np.int_) # labels = [class xywh]
weights = np.bincount(classes, minlength=nc) # occurrences per class
# Prepend gridpoint count (for uCE training)
# gpi = ((320 / 32 * np.array([1, 2, 4])) ** 2 * 3).sum() # gridpoints per image
# weights = np.hstack([gpi * len(labels) - weights.sum() * 9, weights * 9]) ** 0.5 # prepend gridpoints to start
weights[weights == 0] = 1 # replace empty bins with 1
weights = 1 / weights # number of targets per class
weights /= weights.sum() # normalize
return torch.from_numpy(weights)
def labels_to_image_weights(labels, nc=80, class_weights=np.ones(80)):
# Produces image weights based on class_weights and image contents
class_counts = np.array([np.bincount(x[:, 0].astype(np.int_), minlength=nc) for x in labels])
image_weights = (class_weights.reshape(1, nc) * class_counts).sum(1)
# index = random.choices(range(n), weights=image_weights, k=1) # weight image sample
return image_weights
def coco80_to_coco91_class(): # converts 80-index (val2014) to 91-index (paper)
# https://tech.amikelive.com/node-718/what-object-categories-labels-are-in-coco-dataset/
# a = np.loadtxt('data/coco.names', dtype='str', delimiter='\n')
# b = np.loadtxt('data/coco_paper.names', dtype='str', delimiter='\n')
# x1 = [list(a[i] == b).index(True) + 1 for i in range(80)] # darknet to coco
# x2 = [list(b[i] == a).index(True) if any(b[i] == a) else None for i in range(91)] # coco to darknet
x = [1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 27, 28, 31, 32, 33, 34,
35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63,
64, 65, 67, 70, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 84, 85, 86, 87, 88, 89, 90]
return x
def xyxy2xywh(x):
# Convert nx4 boxes from [x1, y1, x2, y2] to [x, y, w, h] where xy1=top-left, xy2=bottom-right
y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x)
y[:, 0] = (x[:, 0] + x[:, 2]) / 2 # x center
y[:, 1] = (x[:, 1] + x[:, 3]) / 2 # y center
y[:, 2] = x[:, 2] - x[:, 0] # width
y[:, 3] = x[:, 3] - x[:, 1] # height
return y
def xywh2xyxy(x):
# Convert nx4 boxes from [x, y, w, h] to [x1, y1, x2, y2] where xy1=top-left, xy2=bottom-right
y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x)
y[:, 0] = x[:, 0] - x[:, 2] / 2 # top left x
y[:, 1] = x[:, 1] - x[:, 3] / 2 # top left y
y[:, 2] = x[:, 0] + x[:, 2] / 2 # bottom right x
y[:, 3] = x[:, 1] + x[:, 3] / 2 # bottom right y
return y
def xywhn2xyxy(x, w=640, h=640, padw=0, padh=0):
# Convert nx4 boxes from [x, y, w, h] normalized to [x1, y1, x2, y2] where xy1=top-left, xy2=bottom-right
y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x)
y[:, 0] = w * (x[:, 0] - x[:, 2] / 2) + padw # top left x
y[:, 1] = h * (x[:, 1] - x[:, 3] / 2) + padh # top left y
y[:, 2] = w * (x[:, 0] + x[:, 2] / 2) + padw # bottom right x
y[:, 3] = h * (x[:, 1] + x[:, 3] / 2) + padh # bottom right y
return y
def xyxy2xywhn(x, w=640, h=640, clip=False, eps=0.0):
# Convert nx4 boxes from [x1, y1, x2, y2] to [x, y, w, h] normalized where xy1=top-left, xy2=bottom-right
if clip:
clip_coords(x, (h - eps, w - eps)) # warning: inplace clip
y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x)
y[:, 0] = ((x[:, 0] + x[:, 2]) / 2) / w # x center
y[:, 1] = ((x[:, 1] + x[:, 3]) / 2) / h # y center
y[:, 2] = (x[:, 2] - x[:, 0]) / w # width
y[:, 3] = (x[:, 3] - x[:, 1]) / h # height
return y
def xyn2xy(x, w=640, h=640, padw=0, padh=0):
# Convert normalized segments into pixel segments, shape (n,2)
y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x)
y[:, 0] = w * x[:, 0] + padw # top left x
y[:, 1] = h * x[:, 1] + padh # top left y
return y
def segment2box(segment, width=640, height=640):
# Convert 1 segment label to 1 box label, applying inside-image constraint, i.e. (xy1, xy2, ...) to (xyxy)
x, y = segment.T # segment xy
inside = (x >= 0) & (y >= 0) & (x <= width) & (y <= height)
x, y, = x[inside], y[inside]
return np.array([x.min(), y.min(), x.max(), y.max()]) if any(x) else np.zeros((1, 4)) # xyxy
def segments2boxes(segments):
# Convert segment labels to box labels, i.e. (cls, xy1, xy2, ...) to (cls, xywh)
boxes = []
for s in segments:
x, y = s.T # segment xy
boxes.append([x.min(), y.min(), x.max(), y.max()]) # cls, xyxy
return xyxy2xywh(np.array(boxes)) # cls, xywh
def resample_segments(segments, n=1000):
# Up-sample an (n,2) segment
for i, s in enumerate(segments):
x = np.linspace(0, len(s) - 1, n)
xp = np.arange(len(s))
segments[i] = np.concatenate([np.interp(x, xp, s[:, i]) for i in range(2)]).reshape(2, -1).T # segment xy
return segments
def scale_coords(img1_shape, coords, img0_shape, ratio_pad=None):
# Rescale coords (xyxy) from img1_shape to img0_shape
if ratio_pad is None: # calculate from img0_shape
gain = min(img1_shape[0] / img0_shape[0], img1_shape[1] / img0_shape[1]) # gain = old / new
pad = (img1_shape[1] - img0_shape[1] * gain) / 2, (img1_shape[0] - img0_shape[0] * gain) / 2 # wh padding
else:
gain = ratio_pad[0][0]
pad = ratio_pad[1]
coords[:, [0, 2]] -= pad[0] # x padding
coords[:, [1, 3]] -= pad[1] # y padding
coords[:, :4] /= gain
clip_coords(coords, img0_shape)
return coords
def clip_coords(boxes, shape):
# Clip bounding xyxy bounding boxes to image shape (height, width)
if isinstance(boxes, torch.Tensor): # faster individually
boxes[:, 0].clamp_(0, shape[1]) # x1
boxes[:, 1].clamp_(0, shape[0]) # y1
boxes[:, 2].clamp_(0, shape[1]) # x2
boxes[:, 3].clamp_(0, shape[0]) # y2
else: # np.array (faster grouped)
boxes[:, [0, 2]] = boxes[:, [0, 2]].clip(0, shape[1]) # x1, x2
boxes[:, [1, 3]] = boxes[:, [1, 3]].clip(0, shape[0]) # y1, y2
def non_max_suppression(prediction, conf_thres=0.25, iou_thres=0.45, classes=None, agnostic=False, multi_label=False,
labels=(), max_det=300):
"""Runs Non-Maximum Suppression (NMS) on inference results
Returns:
list of detections, on (n,6) tensor per image [xyxy, conf, cls]
"""
nc = prediction.shape[2] - 5 # number of classes
xc = prediction[..., 4] > conf_thres # candidates
# Checks
assert 0 <= conf_thres <= 1, f'Invalid Confidence threshold {conf_thres}, valid values are between 0.0 and 1.0'
assert 0 <= iou_thres <= 1, f'Invalid IoU {iou_thres}, valid values are between 0.0 and 1.0'
# Settings
min_wh, max_wh = 2, 4096 # (pixels) minimum and maximum box width and height
max_nms = 30000 # maximum number of boxes into torchvision.ops.nms()
time_limit = 10.0 # seconds to quit after
redundant = True # require redundant detections
multi_label &= nc > 1 # multiple labels per box (adds 0.5ms/img)
merge = False # use merge-NMS
t = time.time()
output = [torch.zeros((0, 6), device=prediction.device)] * prediction.shape[0]
for xi, x in enumerate(prediction): # image index, image inference
# Apply constraints
# x[((x[..., 2:4] < min_wh) | (x[..., 2:4] > max_wh)).any(1), 4] = 0 # width-height
x = x[xc[xi]] # confidence
# Cat apriori labels if autolabelling
if labels and len(labels[xi]):
l = labels[xi]
v = torch.zeros((len(l), nc + 5), device=x.device)
v[:, :4] = l[:, 1:5] # box
v[:, 4] = 1.0 # conf
v[range(len(l)), l[:, 0].long() + 5] = 1.0 # cls
x = torch.cat((x, v), 0)
# If none remain process next image
if not x.shape[0]:
continue
# Compute conf
x[:, 5:] *= x[:, 4:5] # conf = obj_conf * cls_conf
# Box (center x, center y, width, height) to (x1, y1, x2, y2)
box = xywh2xyxy(x[:, :4])
# Detections matrix nx6 (xyxy, conf, cls)
if multi_label:
i, j = (x[:, 5:] > conf_thres).nonzero(as_tuple=False).T
x = torch.cat((box[i], x[i, j + 5, None], j[:, None].float()), 1)
else: # best class only
conf, j = x[:, 5:].max(1, keepdim=True)
x = torch.cat((box, conf, j.float()), 1)[conf.view(-1) > conf_thres]
# Filter by class
if classes is not None:
x = x[(x[:, 5:6] == torch.tensor(classes, device=x.device)).any(1)]
# Apply finite constraint
# if not torch.isfinite(x).all():
# x = x[torch.isfinite(x).all(1)]
# Check shape
n = x.shape[0] # number of boxes
if not n: # no boxes
continue
elif n > max_nms: # excess boxes
x = x[x[:, 4].argsort(descending=True)[:max_nms]] # sort by confidence
# Batched NMS
c = x[:, 5:6] * (0 if agnostic else max_wh) # classes
boxes, scores = x[:, :4] + c, x[:, 4] # boxes (offset by class), scores
i = torchvision.ops.nms(boxes, scores, iou_thres) # NMS
if i.shape[0] > max_det: # limit detections
i = i[:max_det]
if merge and (1 < n < 3E3): # Merge NMS (boxes merged using weighted mean)
# update boxes as boxes(i,4) = weights(i,n) * boxes(n,4)
iou = box_iou(boxes[i], boxes) > iou_thres # iou matrix
weights = iou * scores[None] # box weights
x[i, :4] = torch.mm(weights, x[:, :4]).float() / weights.sum(1, keepdim=True) # merged boxes
if redundant:
i = i[iou.sum(1) > 1] # require redundancy
output[xi] = x[i]
if (time.time() - t) > time_limit:
print(f'WARNING: NMS time limit {time_limit}s exceeded')
break # time limit exceeded
return output
def strip_optimizer(f='best.pt', s=''): # from utils.general import *; strip_optimizer()
# Strip optimizer from 'f' to finalize training, optionally save as 's'
x = torch.load(f, map_location=torch.device('cpu'))
if x.get('ema'):
x['model'] = x['ema'] # replace model with ema
for k in 'optimizer', 'training_results', 'wandb_id', 'ema', 'updates': # keys
x[k] = None
x['epoch'] = -1
x['model'].half() # to FP16
for p in x['model'].parameters():
p.requires_grad = False
torch.save(x, s or f)
mb = os.path.getsize(s or f) / 1E6 # filesize
print(f"Optimizer stripped from {f},{(' saved as %s,' % s) if s else ''} {mb:.1f}MB")
def print_mutation(results, hyp, save_dir, bucket):
evolve_csv, results_csv, evolve_yaml = save_dir / 'evolve.csv', save_dir / 'results.csv', save_dir / 'hyp_evolve.yaml'
keys = ('metrics/precision', 'metrics/recall', 'metrics/mAP_0.5', 'metrics/mAP_0.5:0.95',
'val/box_loss', 'val/obj_loss', 'val/cls_loss') + tuple(hyp.keys()) # [results + hyps]
keys = tuple(x.strip() for x in keys)
vals = results + tuple(hyp.values())
n = len(keys)
# Download (optional)
if bucket:
url = f'gs://{bucket}/evolve.csv'
if gsutil_getsize(url) > (os.path.getsize(evolve_csv) if os.path.exists(evolve_csv) else 0):
os.system(f'gsutil cp {url} {save_dir}') # download evolve.csv if larger than local
# Log to evolve.csv
s = '' if evolve_csv.exists() else (('%20s,' * n % keys).rstrip(',') + '\n') # add header
with open(evolve_csv, 'a') as f:
f.write(s + ('%20.5g,' * n % vals).rstrip(',') + '\n')
# Print to screen
print(colorstr('evolve: ') + ', '.join(f'{x.strip():>20s}' for x in keys))
print(colorstr('evolve: ') + ', '.join(f'{x:20.5g}' for x in vals), end='\n\n\n')
# Save yaml
with open(evolve_yaml, 'w') as f:
data = pd.read_csv(evolve_csv)
data = data.rename(columns=lambda x: x.strip()) # strip keys
i = np.argmax(fitness(data.values[:, :7])) #
f.write('# YOLOv5 Hyperparameter Evolution Results\n' +
f'# Best generation: {i}\n' +
f'# Last generation: {len(data)}\n' +
'# ' + ', '.join(f'{x.strip():>20s}' for x in keys[:7]) + '\n' +
'# ' + ', '.join(f'{x:>20.5g}' for x in data.values[i, :7]) + '\n\n')
yaml.safe_dump(hyp, f, sort_keys=False)
if bucket:
os.system(f'gsutil cp {evolve_csv} {evolve_yaml} gs://{bucket}') # upload
def apply_classifier(x, model, img, im0):
# Apply a second stage classifier to yolo outputs
im0 = [im0] if isinstance(im0, np.ndarray) else im0
for i, d in enumerate(x): # per image
if d is not None and len(d):
d = d.clone()
# Reshape and pad cutouts
b = xyxy2xywh(d[:, :4]) # boxes
b[:, 2:] = b[:, 2:].max(1)[0].unsqueeze(1) # rectangle to square
b[:, 2:] = b[:, 2:] * 1.3 + 30 # pad
d[:, :4] = xywh2xyxy(b).long()
# Rescale boxes from img_size to im0 size
scale_coords(img.shape[2:], d[:, :4], im0[i].shape)
# Classes
pred_cls1 = d[:, 5].long()
ims = []
for j, a in enumerate(d): # per item
cutout = im0[i][int(a[1]):int(a[3]), int(a[0]):int(a[2])]
im = cv2.resize(cutout, (224, 224)) # BGR
# cv2.imwrite('example%i.jpg' % j, cutout)
im = im[:, :, ::-1].transpose(2, 0, 1) # BGR to RGB, to 3x416x416
im = np.ascontiguousarray(im, dtype=np.float32) # uint8 to float32
im /= 255.0 # 0 - 255 to 0.0 - 1.0
ims.append(im)
pred_cls2 = model(torch.Tensor(ims).to(d.device)).argmax(1) # classifier prediction
x[i] = x[i][pred_cls1 == pred_cls2] # retain matching class detections
return x
def save_one_box(xyxy, im, file='image.jpg', gain=1.02, pad=10, square=False, BGR=False, save=True):
# Save image crop as {file} with crop size multiple {gain} and {pad} pixels. Save and/or return crop
xyxy = torch.tensor(xyxy).view(-1, 4)
b = xyxy2xywh(xyxy) # boxes
if square:
b[:, 2:] = b[:, 2:].max(1)[0].unsqueeze(1) # attempt rectangle to square
b[:, 2:] = b[:, 2:] * gain + pad # box wh * gain + pad
xyxy = xywh2xyxy(b).long()
clip_coords(xyxy, im.shape)
crop = im[int(xyxy[0, 1]):int(xyxy[0, 3]), int(xyxy[0, 0]):int(xyxy[0, 2]), ::(1 if BGR else -1)]
if save:
cv2.imwrite(str(increment_path(file, mkdir=True).with_suffix('.jpg')), crop)
return crop
def increment_path(path, exist_ok=False, sep='', mkdir=False):
# Increment file or directory path, i.e. runs/exp --> runs/exp{sep}2, runs/exp{sep}3, ... etc.
path = Path(path) # os-agnostic
if path.exists() and not exist_ok:
suffix = path.suffix
path = path.with_suffix('')
dirs = glob.glob(f"{path}{sep}*") # similar paths
matches = [re.search(rf"%s{sep}(\d+)" % path.stem, d) for d in dirs]
i = [int(m.groups()[0]) for m in matches if m] # indices
n = max(i) + 1 if i else 2 # increment number
path = Path(f"{path}{sep}{n}{suffix}") # update path
dir = path if path.suffix == '' else path.parent # directory
if not dir.exists() and mkdir:
dir.mkdir(parents=True, exist_ok=True) # make directory
return path
utils/google_app_engine/Dockerfile 0 → 100644
View file @ a7b29f47
FROM gcr.io/google-appengine/python
# Create a virtualenv for dependencies. This isolates these packages from
# system-level packages.
# Use -p python3 or -p python3.7 to select python version. Default is version 2.
RUN virtualenv /env -p python3
# Setting these environment variables are the same as running
# source /env/bin/activate.
ENV VIRTUAL_ENV /env
ENV PATH /env/bin:$PATH
RUN apt-get update && apt-get install -y python-opencv
# Copy the application's requirements.txt and run pip to install all
# dependencies into the virtualenv.
ADD requirements.txt /app/requirements.txt
RUN pip install -r /app/requirements.txt
# Add the application source code.
ADD . /app
# Run a WSGI server to serve the application. gunicorn must be declared as
# a dependency in requirements.txt.
CMD gunicorn -b :$PORT main:app
utils/google_app_engine/additional_requirements.txt 0 → 100644
View file @ a7b29f47
# add these requirements in your app on top of the existing ones
pip==19.2
Flask==1.0.2
gunicorn==19.9.0
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment