Skip to content

GitLab

Commit 5a567950 authored by lidc's avatar lidc
Browse files

yolov5增加了mpi单机多卡和多机多卡启动方式，其readme文件进行了更新，对maskrcnn的debug输出日志进行了删除，并更新了该模型的readme文件

parent a30b77fe
Hide whitespace changes
Inline Side-by-side
Showing with 188 additions and 218 deletions
PyTorch/Compute-Vision/Objection/yolov5/utils/metrics.py
View file @ 5a567950
......@@ -18,7 +18,7 @@ def fitness(x):
return (x[:, :4] * w).sum(1)
def ap_per_class(tp, conf, pred_cls, target_cls, plot=False, save_dir='.', names=(), eps=1e-16):
def ap_per_class(tp, conf, pred_cls, target_cls, plot=False, save_dir='.', names=()):
""" Compute the average precision, given the recall and precision curves.
Source: https://github.com/rafaelpadilla/Object-Detection-Metrics.
# Arguments
......@@ -37,7 +37,7 @@ def ap_per_class(tp, conf, pred_cls, target_cls, plot=False, save_dir='.', names
tp, conf, pred_cls = tp[i], conf[i], pred_cls[i]
# Find unique classes
unique_classes, nt = np.unique(target_cls, return_counts=True)
unique_classes = np.unique(target_cls)
nc = unique_classes.shape[0] # number of classes, number of detections
# Create Precision-Recall curve and compute AP for each class
......@@ -45,7 +45,7 @@ def ap_per_class(tp, conf, pred_cls, target_cls, plot=False, save_dir='.', names
ap, p, r = np.zeros((nc, tp.shape[1])), np.zeros((nc, 1000)), np.zeros((nc, 1000))
for ci, c in enumerate(unique_classes):
i = pred_cls == c
n_l = nt[ci] # number of labels
n_l = (target_cls == c).sum() # number of labels
n_p = i.sum() # number of predictions
if n_p == 0 or n_l == 0:
......@@ -56,7 +56,7 @@ def ap_per_class(tp, conf, pred_cls, target_cls, plot=False, save_dir='.', names
tpc = tp[i].cumsum(0)
# Recall
recall = tpc / (n_l + eps) # recall curve
recall = tpc / (n_l + 1e-16) # recall curve
r[ci] = np.interp(-px, -conf[i], recall[:, 0], left=0) # negative x, xp because xp decreases
# Precision
......@@ -70,9 +70,7 @@ def ap_per_class(tp, conf, pred_cls, target_cls, plot=False, save_dir='.', names
py.append(np.interp(px, mrec, mpre)) # precision at mAP@0.5
# Compute F1 (harmonic mean of precision and recall)
f1 = 2 * p * r / (p + r + eps)
names = [v for k, v in names.items() if k in unique_classes] # list: only classes that have data
names = {i: v for i, v in enumerate(names)} # to dict
f1 = 2 * p * r / (p + r + 1e-16)
if plot:
plot_pr_curve(px, py, ap, Path(save_dir) / 'PR_curve.png', names)
plot_mc_curve(px, f1, Path(save_dir) / 'F1_curve.png', names, ylabel='F1')
......@@ -80,10 +78,7 @@ def ap_per_class(tp, conf, pred_cls, target_cls, plot=False, save_dir='.', names
plot_mc_curve(px, r, Path(save_dir) / 'R_curve.png', names, ylabel='Recall')
i = f1.mean(0).argmax() # max F1 index
p, r, f1 = p[:, i], r[:, i], f1[:, i]
tp = (r * nt).round() # true positives
fp = (tp / (p + eps) - tp).round() # false positives
return tp, fp, p, r, f1, ap, unique_classes.astype('int32')
return p[:, i], r[:, i], ap, f1[:, i], unique_classes.astype('int32')
def compute_ap(recall, precision):
......@@ -165,12 +160,6 @@ class ConfusionMatrix:
def matrix(self):
return self.matrix
def tp_fp(self):
tp = self.matrix.diagonal() # true positives
fp = self.matrix.sum(1) - tp # false positives
# fn = self.matrix.sum(0) - tp # false negatives (missed detections)
return tp[:-1], fp[:-1] # remove background class
def plot(self, normalize=True, save_dir='', names=()):
try:
import seaborn as sn
......@@ -222,22 +211,26 @@ def bbox_iou(box1, box2, x1y1x2y2=True, GIoU=False, DIoU=False, CIoU=False, eps=
union = w1 * h1 + w2 * h2 - inter + eps
iou = inter / union
if CIoU or DIoU or GIoU:
if GIoU or DIoU or CIoU:
cw = torch.max(b1_x2, b2_x2) - torch.min(b1_x1, b2_x1) # convex (smallest enclosing box) width
ch = torch.max(b1_y2, b2_y2) - torch.min(b1_y1, b2_y1) # convex height
if CIoU or DIoU: # Distance or Complete IoU https://arxiv.org/abs/1911.08287v1
c2 = cw ** 2 + ch ** 2 + eps # convex diagonal squared
rho2 = ((b2_x1 + b2_x2 - b1_x1 - b1_x2) ** 2 +
(b2_y1 + b2_y2 - b1_y1 - b1_y2) ** 2) / 4 # center distance squared
if CIoU: # https://github.com/Zzh-tju/DIoU-SSD-pytorch/blob/master/utils/box/box_utils.py#L47
if DIoU:
return iou - rho2 / c2 # DIoU
elif CIoU: # https://github.com/Zzh-tju/DIoU-SSD-pytorch/blob/master/utils/box/box_utils.py#L47
v = (4 / math.pi ** 2) * torch.pow(torch.atan(w2 / h2) - torch.atan(w1 / h1), 2)
with torch.no_grad():
alpha = v / (v - iou + (1 + eps))
return iou - (rho2 / c2 + v * alpha) # CIoU
return iou - rho2 / c2 # DIoU
c_area = cw * ch + eps # convex area
return iou - (c_area - union) / c_area # GIoU https://arxiv.org/pdf/1902.09630.pdf
return iou # IoU
else: # GIoU https://arxiv.org/pdf/1902.09630.pdf
c_area = cw * ch + eps # convex area
return iou - (c_area - union) / c_area # GIoU
else:
return iou # IoU
def box_iou(box1, box2):
# https://github.com/pytorch/vision/blob/master/torchvision/ops/boxes.py
......
PyTorch/Compute-Vision/Objection/yolov5/utils/plots.py
View file @ 5a567950
......@@ -17,8 +17,7 @@ import seaborn as sn
import torch
from PIL import Image, ImageDraw, ImageFont
from utils.general import (LOGGER, Timeout, check_requirements, clip_coords, increment_path, is_ascii, is_chinese,
try_except, user_config_dir, xywh2xyxy, xyxy2xywh)
from utils.general import user_config_dir, is_ascii, is_chinese, xywh2xyxy, xyxy2xywh
from utils.metrics import fitness
# Settings
......@@ -59,10 +58,7 @@ def check_font(font='Arial.ttf', size=10):
url = "https://ultralytics.com/assets/" + font.name
print(f'Downloading {url} to {font}...')
torch.hub.download_url_to_file(url, str(font), progress=False)
try:
return ImageFont.truetype(str(font), size)
except TypeError:
check_requirements('Pillow>=8.4.0') # known issue https://github.com/ultralytics/yolov5/issues/5374
return ImageFont.truetype(str(font), size)
class Annotator:
......@@ -121,34 +117,6 @@ class Annotator:
return np.asarray(self.im)
def feature_visualization(x, module_type, stage, n=32, save_dir=Path('runs/detect/exp')):
"""
x: Features to be visualized
module_type: Module type
stage: Module stage within model
n: Maximum number of feature maps to plot
save_dir: Directory to save results
"""
if 'Detect' not in module_type:
batch, channels, height, width = x.shape # batch, channels, height, width
if height > 1 and width > 1:
f = save_dir / f"stage{stage}_{module_type.split('.')[-1]}_features.png" # filename
blocks = torch.chunk(x[0].cpu(), channels, dim=0) # select batch index 0, block by channels
n = min(n, channels) # number of plots
fig, ax = plt.subplots(math.ceil(n / 8), 8, tight_layout=True) # 8 rows x n/8 cols
ax = ax.ravel()
plt.subplots_adjust(wspace=0.05, hspace=0.05)
for i in range(n):
ax[i].imshow(blocks[i].squeeze()) # cmap='gray'
ax[i].axis('off')
print(f'Saving {f}... ({n}/{channels})')
plt.savefig(f, dpi=300, bbox_inches='tight')
plt.close()
np.save(str(f.with_suffix('.npy')), x[0].cpu().numpy()) # npy save
def hist2d(x, y, n=100):
# 2d histogram used in labels.png and evolve.png
xedges, yedges = np.linspace(x.min(), x.max(), n), np.linspace(y.min(), y.max(), n)
......@@ -187,7 +155,7 @@ def plot_images(images, targets, paths=None, fname='images.jpg', names=None, max
if isinstance(targets, torch.Tensor):
targets = targets.cpu().numpy()
if np.max(images[0]) <= 1:
images *= 255 # de-normalise (optional)
images *= 255.0 # de-normalise (optional)
bs, _, h, w = images.shape # batch size, _, height, width
bs = min(bs, max_subplots) # limit plot images
ns = np.ceil(bs ** 0.5) # number of subplots (square)
......@@ -282,7 +250,7 @@ def plot_targets_txt(): # from utils.plots import *; plot_targets_txt()
fig, ax = plt.subplots(2, 2, figsize=(8, 8), tight_layout=True)
ax = ax.ravel()
for i in range(4):
ax[i].hist(x[i], bins=100, label=f'{x[i].mean():.3g} +/- {x[i].std():.3g}')
ax[i].hist(x[i], bins=100, label='%.3g +/- %.3g' % (x[i].mean(), x[i].std()))
ax[i].legend()
ax[i].set_title(s[i])
plt.savefig('targets.jpg', dpi=200)
......@@ -325,11 +293,9 @@ def plot_val_study(file='', dir='', x=None): # from utils.plots import *; plot_
plt.savefig(f, dpi=300)
@try_except # known issue https://github.com/ultralytics/yolov5/issues/5395
@Timeout(30) # known issue https://github.com/ultralytics/yolov5/issues/5611
def plot_labels(labels, names=(), save_dir=Path('')):
# plot dataset labels
LOGGER.info(f"Plotting labels to {save_dir / 'labels.jpg'}... ")
print('Plotting labels... ')
c, b = labels[:, 0], labels[:, 1:].transpose() # classes, boxes
nc = int(c.max() + 1) # number of classes
x = pd.DataFrame(b.transpose(), columns=['x', 'y', 'width', 'height'])
......@@ -371,6 +337,37 @@ def plot_labels(labels, names=(), save_dir=Path('')):
plt.close()
def profile_idetection(start=0, stop=0, labels=(), save_dir=''):
# Plot iDetection '*.txt' per-image logs. from utils.plots import *; profile_idetection()
ax = plt.subplots(2, 4, figsize=(12, 6), tight_layout=True)[1].ravel()
s = ['Images', 'Free Storage (GB)', 'RAM Usage (GB)', 'Battery', 'dt_raw (ms)', 'dt_smooth (ms)', 'real-world FPS']
files = list(Path(save_dir).glob('frames*.txt'))
for fi, f in enumerate(files):
try:
results = np.loadtxt(f, ndmin=2).T[:, 90:-30] # clip first and last rows
n = results.shape[1] # number of rows
x = np.arange(start, min(stop, n) if stop else n)
results = results[:, x]
t = (results[0] - results[0].min()) # set t0=0s
results[0] = x
for i, a in enumerate(ax):
if i < len(results):
label = labels[fi] if len(labels) else f.stem.replace('frames_', '')
a.plot(t, results[i], marker='.', label=label, linewidth=1, markersize=5)
a.set_title(s[i])
a.set_xlabel('time (s)')
# if fi == len(files) - 1:
# a.set_ylim(bottom=0)
for side in ['top', 'right']:
a.spines[side].set_visible(False)
else:
a.remove()
except Exception as e:
print('Warning: Plotting error for %s; %s' % (f, e))
ax[1].legend()
plt.savefig(Path(save_dir) / 'idetection_profile.png', dpi=200)
def plot_evolve(evolve_csv='path/to/evolve.csv'): # from utils.plots import *; plot_evolve()
# Plot evolve.csv hyp evolution results
evolve_csv = Path(evolve_csv)
......@@ -387,10 +384,10 @@ def plot_evolve(evolve_csv='path/to/evolve.csv'): # from utils.plots import *;
plt.subplot(6, 5, i + 1)
plt.scatter(v, f, c=hist2d(v, f, 20), cmap='viridis', alpha=.8, edgecolors='none')
plt.plot(mu, f.max(), 'k+', markersize=15)
plt.title(f'{k} = {mu:.3g}', fontdict={'size': 9}) # limit to 40 characters
plt.title('%s = %.3g' % (k, mu), fontdict={'size': 9}) # limit to 40 characters
if i % 5 != 0:
plt.yticks([])
print(f'{k:>15}: {mu:.3g}')
print('%15s: %.3g' % (k, mu))
f = evolve_csv.with_suffix('.png') # filename
plt.savefig(f, dpi=200)
plt.close()
......@@ -423,48 +420,28 @@ def plot_results(file='path/to/results.csv', dir=''):
plt.close()
def profile_idetection(start=0, stop=0, labels=(), save_dir=''):
# Plot iDetection '*.txt' per-image logs. from utils.plots import *; profile_idetection()
ax = plt.subplots(2, 4, figsize=(12, 6), tight_layout=True)[1].ravel()
s = ['Images', 'Free Storage (GB)', 'RAM Usage (GB)', 'Battery', 'dt_raw (ms)', 'dt_smooth (ms)', 'real-world FPS']
files = list(Path(save_dir).glob('frames*.txt'))
for fi, f in enumerate(files):
try:
results = np.loadtxt(f, ndmin=2).T[:, 90:-30] # clip first and last rows
n = results.shape[1] # number of rows
x = np.arange(start, min(stop, n) if stop else n)
results = results[:, x]
t = (results[0] - results[0].min()) # set t0=0s
results[0] = x
for i, a in enumerate(ax):
if i < len(results):
label = labels[fi] if len(labels) else f.stem.replace('frames_', '')
a.plot(t, results[i], marker='.', label=label, linewidth=1, markersize=5)
a.set_title(s[i])
a.set_xlabel('time (s)')
# if fi == len(files) - 1:
# a.set_ylim(bottom=0)
for side in ['top', 'right']:
a.spines[side].set_visible(False)
else:
a.remove()
except Exception as e:
print(f'Warning: Plotting error for {f}; {e}')
ax[1].legend()
plt.savefig(Path(save_dir) / 'idetection_profile.png', dpi=200)
def feature_visualization(x, module_type, stage, n=32, save_dir=Path('runs/detect/exp')):
"""
x: Features to be visualized
module_type: Module type
stage: Module stage within model
n: Maximum number of feature maps to plot
save_dir: Directory to save results
"""
if 'Detect' not in module_type:
batch, channels, height, width = x.shape # batch, channels, height, width
if height > 1 and width > 1:
f = f"stage{stage}_{module_type.split('.')[-1]}_features.png" # filename
blocks = torch.chunk(x[0].cpu(), channels, dim=0) # select batch index 0, block by channels
n = min(n, channels) # number of plots
fig, ax = plt.subplots(math.ceil(n / 8), 8, tight_layout=True) # 8 rows x n/8 cols
ax = ax.ravel()
plt.subplots_adjust(wspace=0.05, hspace=0.05)
for i in range(n):
ax[i].imshow(blocks[i].squeeze()) # cmap='gray'
ax[i].axis('off')
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:
file.parent.mkdir(parents=True, exist_ok=True) # make directory
cv2.imwrite(str(increment_path(file).with_suffix('.jpg')), crop)
return crop
print(f'Saving {save_dir / f}... ({n}/{channels})')
plt.savefig(save_dir / f, dpi=300, bbox_inches='tight')
plt.close()
PyTorch/Compute-Vision/Objection/yolov5/utils/torch_utils.py
View file @ 5a567950
......@@ -4,6 +4,7 @@ PyTorch utils
"""
import datetime
import logging
import math
import os
import platform
......@@ -17,14 +18,15 @@ import torch
import torch.distributed as dist
import torch.nn as nn
import torch.nn.functional as F
from utils.general import LOGGER
import torchvision
try:
import thop # for FLOPs computation
except ImportError:
thop = None
LOGGER = logging.getLogger(__name__)
@contextmanager
def torch_distributed_zero_first(local_rank: int):
......@@ -53,7 +55,7 @@ def git_describe(path=Path(__file__).parent): # path must be a directory
return '' # not a git repository
def select_device(device='', batch_size=0, newline=True):
def select_device(device='', batch_size=None):
# device = 'cpu' or '0' or '0,1,2,3'
s = f'YOLOv5 🚀 {git_describe() or date_modified()} torch {torch.__version__} ' # string
device = str(device).strip().lower().replace('cuda:', '') # to string, 'cuda:0' to '0'
......@@ -68,17 +70,15 @@ def select_device(device='', batch_size=0, newline=True):
if cuda:
devices = device.split(',') if device else '0' # range(torch.cuda.device_count()) # i.e. 0,1,6,7
n = len(devices) # device count
if n > 1 and batch_size > 0: # check batch_size is divisible by device_count
if n > 1 and batch_size: # check batch_size is divisible by device_count
assert batch_size % n == 0, f'batch-size {batch_size} not multiple of GPU count {n}'
space = ' ' * (len(s) + 1)
for i, d in enumerate(devices):
p = torch.cuda.get_device_properties(i)
s += f"{'' if i == 0 else space}CUDA:{d} ({p.name}, {p.total_memory / 1024 ** 2:.0f}MiB)\n" # bytes to MB
s += f"{'' if i == 0 else space}CUDA:{d} ({p.name}, {p.total_memory / 1024 ** 2}MB)\n" # bytes to MB
else:
s += 'CPU\n'
if not newline:
s = s.rstrip()
LOGGER.info(s.encode().decode('ascii', 'ignore') if platform.system() == 'Windows' else s) # emoji-safe
return torch.device('cuda:0' if cuda else 'cpu')
......@@ -100,6 +100,7 @@ def profile(input, ops, n=10, device=None):
# profile(input, [m1, m2], n=100) # profile over 100 iterations
results = []
logging.basicConfig(format="%(message)s", level=logging.INFO)
device = device or select_device()
print(f"{'Params':>12s}{'GFLOPs':>12s}{'GPU_mem (GB)':>14s}{'forward (ms)':>14s}{'backward (ms)':>14s}"
f"{'input':>24s}{'output':>24s}")
......@@ -110,7 +111,7 @@ def profile(input, ops, n=10, device=None):
for m in ops if isinstance(ops, list) else [ops]:
m = m.to(device) if hasattr(m, 'to') else m # device
m = m.half() if hasattr(m, 'half') and isinstance(x, torch.Tensor) and x.dtype is torch.float16 else m
tf, tb, t = 0, 0, [0, 0, 0] # dt forward, backward
tf, tb, t = 0., 0., [0., 0., 0.] # dt forward, backward
try:
flops = thop.profile(m, inputs=(x,), verbose=False)[0] / 1E9 * 2 # GFLOPs
except:
......@@ -122,10 +123,10 @@ def profile(input, ops, n=10, device=None):
y = m(x)
t[1] = time_sync()
try:
_ = (sum(yi.sum() for yi in y) if isinstance(y, list) else y).sum().backward()
_ = (sum([yi.sum() for yi in y]) if isinstance(y, list) else y).sum().backward()
t[2] = time_sync()
except Exception as e: # no backward method
# print(e) # for debug
print(e)
t[2] = float('nan')
tf += (t[1] - t[0]) * 1000 / n # ms per op forward
tb += (t[2] - t[1]) * 1000 / n # ms per op backward
......@@ -152,6 +153,11 @@ def de_parallel(model):
return model.module if is_parallel(model) else model
def intersect_dicts(da, db, exclude=()):
# Dictionary intersection of matching keys and shapes, omitting 'exclude' keys, using da values
return {k: v for k, v in da.items() if k in db and not any(x in k for x in exclude) and v.shape == db[k].shape}
def initialize_weights(model):
for m in model.modules():
t = type(m)
......@@ -160,7 +166,7 @@ def initialize_weights(model):
elif t is nn.BatchNorm2d:
m.eps = 1e-3
m.momentum = 0.03
elif t in [nn.Hardswish, nn.LeakyReLU, nn.ReLU, nn.ReLU6, nn.SiLU]:
elif t in [nn.Hardswish, nn.LeakyReLU, nn.ReLU, nn.ReLU6]:
m.inplace = True
......@@ -171,7 +177,7 @@ def find_modules(model, mclass=nn.Conv2d):
def sparsity(model):
# Return global model sparsity
a, b = 0, 0
a, b = 0., 0.
for p in model.parameters():
a += p.numel()
b += (p == 0).sum()
......@@ -217,7 +223,7 @@ def model_info(model, verbose=False, img_size=640):
n_p = sum(x.numel() for x in model.parameters()) # number parameters
n_g = sum(x.numel() for x in model.parameters() if x.requires_grad) # number gradients
if verbose:
print(f"{'layer':>5} {'name':>40} {'gradient':>9} {'parameters':>12} {'shape':>20} {'mu':>10} {'sigma':>10}")
print('%5s %40s %9s %12s %20s %10s %10s' % ('layer', 'name', 'gradient', 'parameters', 'shape', 'mu', 'sigma'))
for i, (name, p) in enumerate(model.named_parameters()):
name = name.replace('module_list.', '')
print('%5g %40s %9s %12g %20s %10.3g %10.3g' %
......@@ -236,6 +242,25 @@ def model_info(model, verbose=False, img_size=640):
LOGGER.info(f"Model Summary: {len(list(model.modules()))} layers, {n_p} parameters, {n_g} gradients{fs}")
def load_classifier(name='resnet101', n=2):
# Loads a pretrained model reshaped to n-class output
model = torchvision.models.__dict__[name](pretrained=True)
# ResNet model properties
# input_size = [3, 224, 224]
# input_space = 'RGB'
# input_range = [0, 1]
# mean = [0.485, 0.456, 0.406]
# std = [0.229, 0.224, 0.225]
# Reshape output to n classes
filters = model.fc.weight.shape[1]
model.fc.bias = nn.Parameter(torch.zeros(n), requires_grad=True)
model.fc.weight = nn.Parameter(torch.zeros(n, filters), requires_grad=True)
model.fc.out_features = n
return model
def scale_img(img, ratio=1.0, same_shape=False, gs=32): # img(16,3,256,416)
# scales img(bs,3,y,x) by ratio constrained to gs-multiple
if ratio == 1.0:
......@@ -245,7 +270,7 @@ def scale_img(img, ratio=1.0, same_shape=False, gs=32): # img(16,3,256,416)
s = (int(h * ratio), int(w * ratio)) # new size
img = F.interpolate(img, size=s, mode='bilinear', align_corners=False) # resize
if not same_shape: # pad/crop img
h, w = (math.ceil(x * ratio / gs) * gs for x in (h, w))
h, w = [math.ceil(x * ratio / gs) * gs for x in (h, w)]
return F.pad(img, [0, w - s[1], 0, h - s[0]], value=0.447) # value = imagenet mean
......@@ -274,10 +299,7 @@ class EarlyStopping:
self.possible_stop = delta >= (self.patience - 1) # possible stop may occur next epoch
stop = delta >= self.patience # stop training if patience exceeded
if stop:
LOGGER.info(f'Stopping training early as no improvement observed in last {self.patience} epochs. '
f'Best results observed at epoch {self.best_epoch}, best model saved as best.pt.\n'
f'To update EarlyStopping(patience={self.patience}) pass a new patience value, '
f'i.e. `python train.py --patience 300` or use `--patience 0` to disable EarlyStopping.')
LOGGER.info(f'EarlyStopping patience {self.patience} exceeded, stopping training.')
return stop
......@@ -311,7 +333,7 @@ class ModelEMA:
for k, v in self.ema.state_dict().items():
if v.dtype.is_floating_point:
v *= d
v += (1 - d) * msd[k].detach()
v += (1. - d) * msd[k].detach()
def update_attr(self, model, include=(), exclude=('process_group', 'reducer')):
# Update EMA attributes
......
PyTorch/Compute-Vision/Objection/yolov5/val.py
View file @ 5a567950
......@@ -3,19 +3,7 @@
Validate a trained YOLOv5 model accuracy on a custom dataset
Usage:
$ python path/to/val.py --weights yolov5s.pt --data coco128.yaml --img 640
Usage - formats:
$ python path/to/val.py --weights yolov5s.pt # PyTorch
yolov5s.torchscript # TorchScript
yolov5s.onnx # ONNX Runtime or OpenCV DNN with --dnn
yolov5s.xml # OpenVINO
yolov5s.engine # TensorRT
yolov5s.mlmodel # CoreML (MacOS-only)
yolov5s_saved_model # TensorFlow SavedModel
yolov5s.pb # TensorFlow GraphDef
yolov5s.tflite # TensorFlow Lite
yolov5s_edgetpu.tflite # TensorFlow Edge TPU
$ python path/to/val.py --data coco128.yaml --weights yolov5s.pt --img 640
"""
import argparse
......@@ -35,15 +23,15 @@ 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
from models.common import DetectMultiBackend
from utils.callbacks import Callbacks
from models.experimental import attempt_load
from utils.datasets import create_dataloader
from utils.general import (LOGGER, box_iou, check_dataset, check_img_size, check_requirements, check_yaml,
coco80_to_coco91_class, colorstr, increment_path, non_max_suppression, print_args,
scale_coords, xywh2xyxy, xyxy2xywh)
from utils.metrics import ConfusionMatrix, ap_per_class
from utils.general import coco80_to_coco91_class, check_dataset, check_img_size, check_requirements, \
check_suffix, check_yaml, box_iou, non_max_suppression, scale_coords, xyxy2xywh, xywh2xyxy, set_logging, \
increment_path, colorstr, print_args
from utils.metrics import ap_per_class, ConfusionMatrix
from utils.plots import output_to_target, plot_images, plot_val_study
from utils.torch_utils import select_device, time_sync
from utils.callbacks import Callbacks
def save_one_txt(predn, save_conf, shape, file):
......@@ -101,7 +89,6 @@ def run(data,
iou_thres=0.6, # NMS IoU threshold
task='val', # train, val, test, speed or study
device='', # cuda device, i.e. 0 or 0,1,2,3 or cpu
workers=8, # max dataloader workers (per RANK in DDP mode)
single_cls=False, # treat as single-class dataset
augment=False, # augmented inference
verbose=False, # verbose output
......@@ -113,7 +100,6 @@ def run(data,
name='exp', # save to project/name
exist_ok=False, # existing project/name ok, do not increment
half=True, # use FP16 half-precision inference
dnn=False, # use OpenCV DNN for ONNX inference
model=None,
dataloader=None,
save_dir=Path(''),
......@@ -124,10 +110,8 @@ def run(data,
# Initialize/load model and set device
training = model is not None
if training: # called by train.py
device, pt, jit, engine = next(model.parameters()).device, True, False, False # get model device, PyTorch model
device = next(model.parameters()).device # get model device
half &= device.type != 'cpu' # half precision only supported on CUDA
model.half() if half else model.float()
else: # called directly
device = select_device(device, batch_size=batch_size)
......@@ -136,23 +120,22 @@ def run(data,
(save_dir / 'labels' if save_txt else save_dir).mkdir(parents=True, exist_ok=True) # make dir
# Load model
model = DetectMultiBackend(weights, device=device, dnn=dnn, data=data)
stride, pt, jit, onnx, engine = model.stride, model.pt, model.jit, model.onnx, model.engine
imgsz = check_img_size(imgsz, s=stride) # check image size
half &= (pt or jit or onnx or engine) and device.type != 'cpu' # FP16 supported on limited backends with CUDA
if pt or jit:
model.model.half() if half else model.model.float()
elif engine:
batch_size = model.batch_size
else:
half = False
batch_size = 1 # export.py models default to batch-size 1
device = torch.device('cpu')
LOGGER.info(f'Forcing --batch-size 1 square inference shape(1,3,{imgsz},{imgsz}) for non-PyTorch backends')
check_suffix(weights, '.pt')
model = attempt_load(weights, map_location=device) # load FP32 model
gs = max(int(model.stride.max()), 32) # grid size (max stride)
imgsz = check_img_size(imgsz, s=gs) # check image size
# Multi-GPU disabled, incompatible with .half() https://github.com/ultralytics/yolov5/issues/99
# if device.type != 'cpu' and torch.cuda.device_count() > 1:
# model = nn.DataParallel(model)
# Data
data = check_dataset(data) # check
# Half
half &= device.type != 'cpu' # half precision only supported on CUDA
model.half() if half else model.float()
# Configure
model.eval()
is_coco = isinstance(data.get('val'), str) and data['val'].endswith('coco/val2017.txt') # COCO dataset
......@@ -162,11 +145,12 @@ def run(data,
# Dataloader
if not training:
model.warmup(imgsz=(1, 3, imgsz, imgsz), half=half) # warmup
if device.type != 'cpu':
model(torch.zeros(1, 3, imgsz, imgsz).to(device).type_as(next(model.parameters()))) # run once
pad = 0.0 if task == 'speed' else 0.5
task = task if task in ('train', 'val', 'test') else 'val' # path to train/val/test images
dataloader = create_dataloader(data[task], imgsz, batch_size, stride, single_cls, pad=pad, rect=pt,
workers=workers, prefix=colorstr(f'{task}: '))[0]
dataloader = create_dataloader(data[task], imgsz, batch_size, gs, single_cls, pad=pad, rect=True,
prefix=colorstr(f'{task}: '))[0]
seen = 0
confusion_matrix = ConfusionMatrix(nc=nc)
......@@ -176,34 +160,32 @@ def run(data,
dt, p, r, f1, mp, mr, map50, map = [0.0, 0.0, 0.0], 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0
loss = torch.zeros(3, device=device)
jdict, stats, ap, ap_class = [], [], [], []
pbar = tqdm(dataloader, desc=s, bar_format='{l_bar}{bar:10}{r_bar}{bar:-10b}') # progress bar
for batch_i, (im, targets, paths, shapes) in enumerate(pbar):
for batch_i, (img, targets, paths, shapes) in enumerate(tqdm(dataloader, desc=s)):
t1 = time_sync()
if pt or jit or engine:
im = im.to(device, non_blocking=True)
targets = targets.to(device)
im = im.half() if half else im.float() # uint8 to fp16/32
im /= 255 # 0 - 255 to 0.0 - 1.0
nb, _, height, width = im.shape # batch size, channels, height, width
img = img.to(device, non_blocking=True)
img = img.half() if half else img.float() # uint8 to fp16/32
img /= 255.0 # 0 - 255 to 0.0 - 1.0
targets = targets.to(device)
nb, _, height, width = img.shape # batch size, channels, height, width
t2 = time_sync()
dt[0] += t2 - t1
# Inference
out, train_out = model(im) if training else model(im, augment=augment, val=True) # inference, loss outputs
# Run model
out, train_out = model(img, augment=augment) # inference and training outputs
dt[1] += time_sync() - t2
# Loss
# Compute loss
if compute_loss:
loss += compute_loss([x.float() for x in train_out], targets)[1] # box, obj, cls
# NMS
# Run NMS
targets[:, 2:] *= torch.Tensor([width, height, width, height]).to(device) # to pixels
lb = [targets[targets[:, 0] == i, 1:] for i in range(nb)] if save_hybrid else [] # for autolabelling
t3 = time_sync()
out = non_max_suppression(out, conf_thres, iou_thres, labels=lb, multi_label=True, agnostic=single_cls)
dt[2] += time_sync() - t3
# Metrics
# Statistics per image
for si, pred in enumerate(out):
labels = targets[targets[:, 0] == si, 1:]
nl = len(labels)
......@@ -220,12 +202,12 @@ def run(data,
if single_cls:
pred[:, 5] = 0
predn = pred.clone()
scale_coords(im[si].shape[1:], predn[:, :4], shape, shapes[si][1]) # native-space pred
scale_coords(img[si].shape[1:], predn[:, :4], shape, shapes[si][1]) # native-space pred
# Evaluate
if nl:
tbox = xywh2xyxy(labels[:, 1:5]) # target boxes
scale_coords(im[si].shape[1:], tbox, shape, shapes[si][1]) # native-space labels
scale_coords(img[si].shape[1:], tbox, shape, shapes[si][1]) # native-space labels
labelsn = torch.cat((labels[:, 0:1], tbox), 1) # native-space labels
correct = process_batch(predn, labelsn, iouv)
if plots:
......@@ -239,19 +221,19 @@ def run(data,
save_one_txt(predn, save_conf, shape, file=save_dir / 'labels' / (path.stem + '.txt'))
if save_json:
save_one_json(predn, jdict, path, class_map) # append to COCO-JSON dictionary
callbacks.run('on_val_image_end', pred, predn, path, names, im[si])
callbacks.run('on_val_image_end', pred, predn, path, names, img[si])
# Plot images
if plots and batch_i < 3:
f = save_dir / f'val_batch{batch_i}_labels.jpg' # labels
Thread(target=plot_images, args=(im, targets, paths, f, names), daemon=True).start()
Thread(target=plot_images, args=(img, targets, paths, f, names), daemon=True).start()
f = save_dir / f'val_batch{batch_i}_pred.jpg' # predictions
Thread(target=plot_images, args=(im, output_to_target(out), paths, f, names), daemon=True).start()
Thread(target=plot_images, args=(img, output_to_target(out), paths, f, names), daemon=True).start()
# Compute metrics
# Compute statistics
stats = [np.concatenate(x, 0) for x in zip(*stats)] # to numpy
if len(stats) and stats[0].any():
tp, fp, p, r, f1, ap, ap_class = ap_per_class(*stats, plot=plots, save_dir=save_dir, names=names)
p, r, ap, f1, ap_class = ap_per_class(*stats, plot=plots, save_dir=save_dir, names=names)
ap50, ap = ap[:, 0], ap.mean(1) # AP@0.5, AP@0.5:0.95
mp, mr, map50, map = p.mean(), r.mean(), ap50.mean(), ap.mean()
nt = np.bincount(stats[3].astype(np.int64), minlength=nc) # number of targets per class
......@@ -260,18 +242,18 @@ def run(data,
# Print results
pf = '%20s' + '%11i' * 2 + '%11.3g' * 4 # print format
LOGGER.info(pf % ('all', seen, nt.sum(), mp, mr, map50, map))
print(pf % ('all', seen, nt.sum(), mp, mr, map50, map))
# Print results per class
if (verbose or (nc < 50 and not training)) and nc > 1 and len(stats):
for i, c in enumerate(ap_class):
LOGGER.info(pf % (names[c], seen, nt[c], p[i], r[i], ap50[i], ap[i]))
print(pf % (names[c], seen, nt[c], p[i], r[i], ap50[i], ap[i]))
# Print speeds
t = tuple(x / seen * 1E3 for x in dt) # speeds per image
if not training:
shape = (batch_size, 3, imgsz, imgsz)
LOGGER.info(f'Speed: %.1fms pre-process, %.1fms inference, %.1fms NMS per image at shape {shape}' % t)
print(f'Speed: %.1fms pre-process, %.1fms inference, %.1fms NMS per image at shape {shape}' % t)
# Plots
if plots:
......@@ -283,7 +265,7 @@ def run(data,
w = Path(weights[0] if isinstance(weights, list) else weights).stem if weights is not None else '' # weights
anno_json = str(Path(data.get('path', '../coco')) / 'annotations/instances_val2017.json') # annotations json
pred_json = str(save_dir / f"{w}_predictions.json") # predictions json
LOGGER.info(f'\nEvaluating pycocotools mAP... saving {pred_json}...')
print(f'\nEvaluating pycocotools mAP... saving {pred_json}...')
with open(pred_json, 'w') as f:
json.dump(jdict, f)
......@@ -302,13 +284,13 @@ def run(data,
eval.summarize()
map, map50 = eval.stats[:2] # update results (mAP@0.5:0.95, mAP@0.5)
except Exception as e:
LOGGER.info(f'pycocotools unable to run: {e}')
print(f'pycocotools unable to run: {e}')
# Return results
model.float() # for training
if not training:
s = f"\n{len(list(save_dir.glob('labels/*.txt')))} labels saved to {save_dir / 'labels'}" if save_txt else ''
LOGGER.info(f"Results saved to {colorstr('bold', save_dir)}{s}")
print(f"Results saved to {colorstr('bold', save_dir)}{s}")
maps = np.zeros(nc) + map
for i, c in enumerate(ap_class):
maps[c] = ap[i]
......@@ -325,7 +307,6 @@ def parse_opt():
parser.add_argument('--iou-thres', type=float, default=0.6, help='NMS IoU threshold')
parser.add_argument('--task', default='val', help='train, val, test, speed or study')
parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
parser.add_argument('--workers', type=int, default=8, help='max dataloader workers (per RANK in DDP mode)')
parser.add_argument('--single-cls', action='store_true', help='treat as single-class dataset')
parser.add_argument('--augment', action='store_true', help='augmented inference')
parser.add_argument('--verbose', action='store_true', help='report mAP by class')
......@@ -337,7 +318,6 @@ def parse_opt():
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('--half', action='store_true', help='use FP16 half-precision inference')
parser.add_argument('--dnn', action='store_true', help='use OpenCV DNN for ONNX inference')
opt = parser.parse_args()
opt.data = check_yaml(opt.data) # check YAML
opt.save_json |= opt.data.endswith('coco.yaml')
......@@ -347,34 +327,32 @@ def parse_opt():
def main(opt):
check_requirements(requirements=ROOT / 'requirements.txt', exclude=('tensorboard', 'thop'))
set_logging()
check_requirements(exclude=('tensorboard', 'thop'))
if opt.task in ('train', 'val', 'test'): # run normally
if opt.conf_thres > 0.001: # https://github.com/ultralytics/yolov5/issues/1466
LOGGER.info(f'WARNING: confidence threshold {opt.conf_thres} >> 0.001 will produce invalid mAP values.')
run(**vars(opt))
else:
weights = opt.weights if isinstance(opt.weights, list) else [opt.weights]
opt.half = True # FP16 for fastest results
if opt.task == 'speed': # speed benchmarks
# python val.py --task speed --data coco.yaml --batch 1 --weights yolov5n.pt yolov5s.pt...
opt.conf_thres, opt.iou_thres, opt.save_json = 0.25, 0.45, False
for opt.weights in weights:
run(**vars(opt), plots=False)
elif opt.task == 'study': # speed vs mAP benchmarks
# python val.py --task study --data coco.yaml --iou 0.7 --weights yolov5n.pt yolov5s.pt...
for opt.weights in weights:
f = f'study_{Path(opt.data).stem}_{Path(opt.weights).stem}.txt' # filename to save to
x, y = list(range(256, 1536 + 128, 128)), [] # x axis (image sizes), y axis
for opt.imgsz in x: # img-size
LOGGER.info(f'\nRunning {f} --imgsz {opt.imgsz}...')
r, _, t = run(**vars(opt), plots=False)
y.append(r + t) # results and times
np.savetxt(f, y, fmt='%10.4g') # save
os.system('zip -r study.zip study_*.txt')
plot_val_study(x=x) # plot
elif opt.task == 'speed': # speed benchmarks
# python val.py --task speed --data coco.yaml --batch 1 --weights yolov5n.pt yolov5s.pt...
for w in opt.weights if isinstance(opt.weights, list) else [opt.weights]:
run(opt.data, weights=w, batch_size=opt.batch_size, imgsz=opt.imgsz, conf_thres=.25, iou_thres=.45,
device=opt.device, save_json=False, plots=False)
elif opt.task == 'study': # run over a range of settings and save/plot
# python val.py --task study --data coco.yaml --iou 0.7 --weights yolov5n.pt yolov5s.pt...
x = list(range(256, 1536 + 128, 128)) # x axis (image sizes)
for w in opt.weights if isinstance(opt.weights, list) else [opt.weights]:
f = f'study_{Path(opt.data).stem}_{Path(w).stem}.txt' # filename to save to
y = [] # y axis
for i in x: # img-size
print(f'\nRunning {f} point {i}...')
r, _, t = run(opt.data, weights=w, batch_size=opt.batch_size, imgsz=i, conf_thres=opt.conf_thres,
iou_thres=opt.iou_thres, device=opt.device, save_json=opt.save_json, plots=False)
y.append(r + t) # results and times
np.savetxt(f, y, fmt='%10.4g') # save
os.system('zip -r study.zip study_*.txt')
plot_val_study(x=x) # plot
if __name__ == "__main__":
......
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