Skip to content

GitLab

"vscode:/vscode.git/clone" did not exist on "4ba713bf43b7d57e943870d39454ab29faaf820b"
Commit e3b5253b authored by ZCMax's avatar ZCMax Committed by ChaimZhu
Browse files

Update all registries and fix some ut problems

parent 8dd8da12
Hide whitespace changes
Inline Side-by-side
Showing with 186 additions and 573 deletions
docs/zh_cn/benchmarks.md
View file @ e3b5253b
......@@ -4,16 +4,16 @@
## 配置
- 硬件：8 NVIDIA Tesla V100 (32G) GPUs, Intel(R) Xeon(R) Gold 6148 CPU @ 2.40GHz
- 软件：Python 3.7, CUDA 10.1, cuDNN 7.6.5, PyTorch 1.3, numba 0.48.0.
- 模型：由于不同代码库所实现的模型种类有所不同，在基准测试中我们选择了 SECOND、PointPillars、Part-A2 和 VoteNet 几种模型，分别与其他代码库中的相应模型实现进行了对比。
- 度量方法：我们使用整个训练过程中的平均吞吐量作为度量方法，并跳过每个 epoch 的前 50 次迭代以消除训练预热的影响。
* 硬件：8 NVIDIA Tesla V100 (32G) GPUs, Intel(R) Xeon(R) Gold 6148 CPU @ 2.40GHz
* 软件：Python 3.7, CUDA 10.1, cuDNN 7.6.5, PyTorch 1.3, numba 0.48.0.
* 模型：由于不同代码库所实现的模型种类有所不同，在基准测试中我们选择了 SECOND、PointPillars、Part-A2 和 VoteNet 几种模型，分别与其他代码库中的相应模型实现进行了对比。
* 度量方法：我们使用整个训练过程中的平均吞吐量作为度量方法，并跳过每个 epoch 的前 50 次迭代以消除训练预热的影响。
## 主要结果
对于模型的训练速度（样本/秒），我们将 MMDetection3D 与其他实现了相同模型的代码库进行了对比。结果如下所示，表格内的数字越大，代表模型的训练速度越快。代码库中不支持的模型使用 `×` 进行标识。
| 模型 | MMDetection3D | OpenPCDet | votenet | Det3D |
| 模型 | MMDetection3D | OpenPCDet | votenet | Det3D |
| :-----------------: | :-----------: | :-------: | :-----: | :---: |
| VoteNet | 358 | × | 77 | × |
| PointPillars-car | 141 | × | × | 140 |
......@@ -25,104 +25,103 @@
### 为了计算速度所做的修改
- __MMDetection3D__：我们尝试使用与其他代码库中尽可能相同的配置，具体配置细节见 [基准测试配置](https://github.com/open-mmlab/MMDetection3D/blob/master/configs/benchmark)。
* __MMDetection3D__：我们尝试使用与其他代码库中尽可能相同的配置，具体配置细节见 [基准测试配置](https://github.com/open-mmlab/MMDetection3D/blob/master/configs/benchmark)。
- __Det3D__：为了与 Det3D 进行比较，我们使用了 commit [519251e](https://github.com/poodarchu/Det3D/tree/519251e72a5c1fdd58972eabeac67808676b9bb7) 所对应的代码版本。
* __Det3D__：为了与 Det3D 进行比较，我们使用了 commit [519251e](https://github.com/poodarchu/Det3D/tree/519251e72a5c1fdd58972eabeac67808676b9bb7) 所对应的代码版本。
- __OpenPCDet__：为了与 OpenPCDet 进行比较，我们使用了 commit [b32fbddb](https://github.com/open-mmlab/OpenPCDet/tree/b32fbddbe06183507bad433ed99b407cbc2175c2) 所对应的代码版本。
* __OpenPCDet__：为了与 OpenPCDet 进行比较，我们使用了 commit [b32fbddb](https://github.com/open-mmlab/OpenPCDet/tree/b32fbddbe06183507bad433ed99b407cbc2175c2) 所对应的代码版本。
为了计算训练速度，我们在 `./tools/train_utils/train_utils.py` 文件中添加了用于记录运行时间的代码。我们对每个 epoch 的训练速度进行计算，并报告所有 epoch 的平均速度。
<details>
为了计算训练速度，我们在 `./tools/train_utils/train_utils.py` 文件中添加了用于记录运行时间的代码。我们对每个 epoch 的训练速度进行计算，并报告所有 epoch 的平均速度。
<details>
<summary>
（为了使用相同方法进行测试所做的具体修改 - 点击展开）
</summary>
```diff
diff --git a/tools/train_utils/train_utils.py b/tools/train_utils/train_utils.py
index 91f21dd..021359d 100644
--- a/tools/train_utils/train_utils.py
+++ b/tools/train_utils/train_utils.py
@@ -2,6 +2,7 @@ import torch
import os
import glob
import tqdm
+import datetime
from torch.nn.utils import clip_grad_norm_
@@ -13,7 +14,10 @@ def train_one_epoch(model, optimizer, train_loader, model_func, lr_scheduler, ac
if rank == 0:
pbar = tqdm.tqdm(total=total_it_each_epoch, leave=leave_pbar, desc='train', dynamic_ncols=True)
+ start_time = None
for cur_it in range(total_it_each_epoch):
+ if cur_it > 49 and start_time is None:
+ start_time = datetime.datetime.now()
try:
batch = next(dataloader_iter)
except StopIteration:
@@ -55,9 +59,11 @@ def train_one_epoch(model, optimizer, train_loader, model_func, lr_scheduler, ac
tb_log.add_scalar('learning_rate', cur_lr, accumulated_iter)
for key, val in tb_dict.items():
tb_log.add_scalar('train_' + key, val, accumulated_iter)
+ endtime = datetime.datetime.now()
+ speed = (endtime - start_time).seconds / (total_it_each_epoch - 50)
if rank == 0:
pbar.close()
- return accumulated_iter
+ return accumulated_iter, speed
def train_model(model, optimizer, train_loader, model_func, lr_scheduler, optim_cfg,
@@ -65,6 +71,7 @@ def train_model(model, optimizer, train_loader, model_func, lr_scheduler, optim_
lr_warmup_scheduler=None, ckpt_save_interval=1, max_ckpt_save_num=50,
merge_all_iters_to_one_epoch=False):
accumulated_iter = start_iter
+ speeds = []
with tqdm.trange(start_epoch, total_epochs, desc='epochs', dynamic_ncols=True, leave=(rank == 0)) as tbar:
total_it_each_epoch = len(train_loader)
if merge_all_iters_to_one_epoch:
@@ -82,7 +89,7 @@ def train_model(model, optimizer, train_loader, model_func, lr_scheduler, optim_
cur_scheduler = lr_warmup_scheduler
else:
cur_scheduler = lr_scheduler
- accumulated_iter = train_one_epoch(
+ accumulated_iter, speed = train_one_epoch(
model, optimizer, train_loader, model_func,
lr_scheduler=cur_scheduler,
accumulated_iter=accumulated_iter, optim_cfg=optim_cfg,
@@ -91,7 +98,7 @@ def train_model(model, optimizer, train_loader, model_func, lr_scheduler, optim_
total_it_each_epoch=total_it_each_epoch,
dataloader_iter=dataloader_iter
)
-
+ speeds.append(speed)
# save trained model
trained_epoch = cur_epoch + 1
if trained_epoch % ckpt_save_interval == 0 and rank == 0:
@@ -107,6 +114,8 @@ def train_model(model, optimizer, train_loader, model_func, lr_scheduler, optim_
save_checkpoint(
checkpoint_state(model, optimizer, trained_epoch, accumulated_iter), filename=ckpt_name,
)
+ print(speed)
+ print(f'*******{sum(speeds) / len(speeds)}******')
def model_state_to_cpu(model_state):
```
</details>
```diff
diff --git a/tools/train_utils/train_utils.py b/tools/train_utils/train_utils.py
index 91f21dd..021359d 100644
--- a/tools/train_utils/train_utils.py
+++ b/tools/train_utils/train_utils.py
@@ -2,6 +2,7 @@ import torch
import os
import glob
import tqdm
+import datetime
from torch.nn.utils import clip_grad_norm_
@@ -13,7 +14,10 @@ def train_one_epoch(model, optimizer, train_loader, model_func, lr_scheduler, ac
if rank == 0:
pbar = tqdm.tqdm(total=total_it_each_epoch, leave=leave_pbar, desc='train', dynamic_ncols=True)
+ start_time = None
for cur_it in range(total_it_each_epoch):
+ if cur_it > 49 and start_time is None:
+ start_time = datetime.datetime.now()
try:
batch = next(dataloader_iter)
except StopIteration:
@@ -55,9 +59,11 @@ def train_one_epoch(model, optimizer, train_loader, model_func, lr_scheduler, ac
tb_log.add_scalar('learning_rate', cur_lr, accumulated_iter)
for key, val in tb_dict.items():
tb_log.add_scalar('train_' + key, val, accumulated_iter)
+ endtime = datetime.datetime.now()
+ speed = (endtime - start_time).seconds / (total_it_each_epoch - 50)
if rank == 0:
pbar.close()
- return accumulated_iter
+ return accumulated_iter, speed
def train_model(model, optimizer, train_loader, model_func, lr_scheduler, optim_cfg,
@@ -65,6 +71,7 @@ def train_model(model, optimizer, train_loader, model_func, lr_scheduler, optim_
lr_warmup_scheduler=None, ckpt_save_interval=1, max_ckpt_save_num=50,
merge_all_iters_to_one_epoch=False):
accumulated_iter = start_iter
+ speeds = []
with tqdm.trange(start_epoch, total_epochs, desc='epochs', dynamic_ncols=True, leave=(rank == 0)) as tbar:
total_it_each_epoch = len(train_loader)
if merge_all_iters_to_one_epoch:
@@ -82,7 +89,7 @@ def train_model(model, optimizer, train_loader, model_func, lr_scheduler, optim_
cur_scheduler = lr_warmup_scheduler
else:
cur_scheduler = lr_scheduler
- accumulated_iter = train_one_epoch(
+ accumulated_iter, speed = train_one_epoch(
model, optimizer, train_loader, model_func,
lr_scheduler=cur_scheduler,
accumulated_iter=accumulated_iter, optim_cfg=optim_cfg,
@@ -91,7 +98,7 @@ def train_model(model, optimizer, train_loader, model_func, lr_scheduler, optim_
total_it_each_epoch=total_it_each_epoch,
dataloader_iter=dataloader_iter
)
-
+ speeds.append(speed)
# save trained model
trained_epoch = cur_epoch + 1
if trained_epoch % ckpt_save_interval == 0 and rank == 0:
@@ -107,6 +114,8 @@ def train_model(model, optimizer, train_loader, model_func, lr_scheduler, optim_
save_checkpoint(
checkpoint_state(model, optimizer, trained_epoch, accumulated_iter), filename=ckpt_name,
)
+ print(speed)
+ print(f'*******{sum(speeds) / len(speeds)}******')
def model_state_to_cpu(model_state):
```
</details>
### VoteNet
- __MMDetection3D__：在 v0.1.0 版本下, 执行如下命令：
* __MMDetection3D__：在 v0.1.0 版本下, 执行如下命令：
```bash
./tools/dist_train.sh configs/votenet/votenet_16x8_sunrgbd-3d-10class.py 8 --no-validate
```
- __votenet__：在 commit [2f6d6d3](https://github.com/facebookresearch/votenet/tree/2f6d6d36ff98d96901182e935afe48ccee82d566) 版本下，执行如下命令：
* __votenet__：在 commit [2f6d6d3](https://github.com/facebookresearch/votenet/tree/2f6d6d36ff98d96901182e935afe48ccee82d566) 版本下，执行如下命令：
```bash
python train.py --dataset sunrgbd --batch_size 16
......@@ -197,13 +196,13 @@
### PointPillars-car
- __MMDetection3D__：在 v0.1.0 版本下, 执行如下命令：
* __MMDetection3D__：在 v0.1.0 版本下, 执行如下命令：
```bash
./tools/dist_train.sh configs/benchmark/hv_pointpillars_secfpn_3x8_100e_det3d_kitti-3d-car.py 8 --no-validate
```
- __Det3D__：在 commit [519251e](https://github.com/poodarchu/Det3D/tree/519251e72a5c1fdd58972eabeac67808676b9bb7) 版本下，使用 `kitti_point_pillars_mghead_syncbn.py` 并执行如下命令：
* __Det3D__：在 commit [519251e](https://github.com/poodarchu/Det3D/tree/519251e72a5c1fdd58972eabeac67808676b9bb7) 版本下，使用 `kitti_point_pillars_mghead_syncbn.py` 并执行如下命令：
```bash
./tools/scripts/train.sh --launcher=slurm --gpus=8
......@@ -239,13 +238,13 @@
### PointPillars-3class
- __MMDetection3D__：在 v0.1.0 版本下, 执行如下命令：
* __MMDetection3D__：在 v0.1.0 版本下, 执行如下命令：
```bash
./tools/dist_train.sh configs/benchmark/hv_pointpillars_secfpn_4x8_80e_pcdet_kitti-3d-3class.py 8 --no-validate
```
- __OpenPCDet__：在 commit [b32fbddb](https://github.com/open-mmlab/OpenPCDet/tree/b32fbddbe06183507bad433ed99b407cbc2175c2) 版本下，执行如下命令：
* __OpenPCDet__：在 commit [b32fbddb](https://github.com/open-mmlab/OpenPCDet/tree/b32fbddbe06183507bad433ed99b407cbc2175c2) 版本下，执行如下命令：
```bash
cd tools
......@@ -256,13 +255,13 @@
基准测试中的 SECOND 指在 [second.Pytorch](https://github.com/traveller59/second.pytorch) 首次被实现的 [SECONDv1.5](https://github.com/traveller59/second.pytorch/blob/master/second/configs/all.fhd.config)。Det3D 实现的 SECOND 中，使用了自己实现的 Multi-Group Head，因此无法将它的速度与其他代码库进行对比。
- __MMDetection3D__：在 v0.1.0 版本下, 执行如下命令：
* __MMDetection3D__：在 v0.1.0 版本下, 执行如下命令：
```bash
./tools/dist_train.sh configs/benchmark/hv_second_secfpn_4x8_80e_pcdet_kitti-3d-3class.py 8 --no-validate
```
- __OpenPCDet__：在 commit [b32fbddb](https://github.com/open-mmlab/OpenPCDet/tree/b32fbddbe06183507bad433ed99b407cbc2175c2) 版本下，执行如下命令：
* __OpenPCDet__：在 commit [b32fbddb](https://github.com/open-mmlab/OpenPCDet/tree/b32fbddbe06183507bad433ed99b407cbc2175c2) 版本下，执行如下命令：
```bash
cd tools
......@@ -271,13 +270,13 @@
### Part-A2
- __MMDetection3D__：在 v0.1.0 版本下, 执行如下命令：
* __MMDetection3D__：在 v0.1.0 版本下, 执行如下命令：
```bash
./tools/dist_train.sh configs/benchmark/hv_PartA2_secfpn_4x8_cyclic_80e_pcdet_kitti-3d-3class.py 8 --no-validate
```
- __OpenPCDet__：在 commit [b32fbddb](https://github.com/open-mmlab/OpenPCDet/tree/b32fbddbe06183507bad433ed99b407cbc2175c2) 版本下，执行如下命令以进行模型训练：
* __OpenPCDet__：在 commit [b32fbddb](https://github.com/open-mmlab/OpenPCDet/tree/b32fbddbe06183507bad433ed99b407cbc2175c2) 版本下，执行如下命令以进行模型训练：
```bash
cd tools
......
mmdet3d/apis/__init__.py
View file @ e3b5253b
......@@ -3,12 +3,13 @@ from .inference import (convert_SyncBN, inference_detector,
inference_mono_3d_detector,
inference_multi_modality_detector, inference_segmentor,
init_model, show_result_meshlab)
from .test import single_gpu_test
from .train import init_random_seed, train_model
__all__ = [
'inference_detector', 'init_model', 'single_gpu_test',
'inference_mono_3d_detector', 'show_result_meshlab', 'convert_SyncBN',
'train_model', 'inference_multi_modality_detector', 'inference_segmentor',
'init_random_seed'
'inference_detector',
'init_model',
'inference_mono_3d_detector',
'show_result_meshlab',
'convert_SyncBN',
'inference_multi_modality_detector',
'inference_segmentor',
]
mmdet3d/apis/test.py deleted 100644 → 0
View file @ 8dd8da12
# Copyright (c) OpenMMLab. All rights reserved.
from os import path as osp
import mmcv
import torch
from mmcv.image import tensor2imgs
from mmdet3d.models import (Base3DDetector, Base3DSegmentor,
SingleStageMono3DDetector)
def single_gpu_test(model,
data_loader,
show=False,
out_dir=None,
show_score_thr=0.3):
"""Test model with single gpu.
This method tests model with single gpu and gives the 'show' option.
By setting ``show=True``, it saves the visualization results under
``out_dir``.
Args:
model (nn.Module): Model to be tested.
data_loader (nn.Dataloader): Pytorch data loader.
show (bool, optional): Whether to save viualization results.
Default: True.
out_dir (str, optional): The path to save visualization results.
Default: None.
Returns:
list[dict]: The prediction results.
"""
model.eval()
results = []
dataset = data_loader.dataset
prog_bar = mmcv.ProgressBar(len(dataset))
for i, data in enumerate(data_loader):
with torch.no_grad():
result = model(return_loss=False, rescale=True, **data)
if show:
# Visualize the results of MMDetection3D model
# 'show_results' is MMdetection3D visualization API
models_3d = (Base3DDetector, Base3DSegmentor,
SingleStageMono3DDetector)
if isinstance(model.module, models_3d):
model.module.show_results(
data,
result,
out_dir=out_dir,
show=show,
score_thr=show_score_thr)
# Visualize the results of MMDetection model
# 'show_result' is MMdetection visualization API
else:
batch_size = len(result)
if batch_size == 1 and isinstance(data['img'][0],
torch.Tensor):
img_tensor = data['img'][0]
else:
img_tensor = data['img'][0].data[0]
img_metas = data['img_metas'][0].data[0]
imgs = tensor2imgs(img_tensor, **img_metas[0]['img_norm_cfg'])
assert len(imgs) == len(img_metas)
for i, (img, img_meta) in enumerate(zip(imgs, img_metas)):
h, w, _ = img_meta['img_shape']
img_show = img[:h, :w, :]
ori_h, ori_w = img_meta['ori_shape'][:-1]
img_show = mmcv.imresize(img_show, (ori_w, ori_h))
if out_dir:
out_file = osp.join(out_dir, img_meta['ori_filename'])
else:
out_file = None
model.module.show_result(
img_show,
result[i],
show=show,
out_file=out_file,
score_thr=show_score_thr)
results.extend(result)
batch_size = len(result)
for _ in range(batch_size):
prog_bar.update()
return results
mmdet3d/apis/train.py deleted 100644 → 0
View file @ 8dd8da12
# Copyright (c) OpenMMLab. All rights reserved.
import random
import warnings
import numpy as np
import torch
from mmcv.parallel import MMDataParallel, MMDistributedDataParallel
from mmcv.runner import (HOOKS, DistSamplerSeedHook, EpochBasedRunner,
Fp16OptimizerHook, OptimizerHook, build_optimizer,
build_runner, get_dist_info)
from mmcv.utils import build_from_cfg
from torch import distributed as dist
from mmdet3d.datasets import build_dataset
from mmdet3d.utils import find_latest_checkpoint
from mmdet.core import DistEvalHook as MMDET_DistEvalHook
from mmdet.core import EvalHook as MMDET_EvalHook
from mmdet.datasets import build_dataloader as build_mmdet_dataloader
from mmdet.datasets import replace_ImageToTensor
from mmdet.utils import get_root_logger as get_mmdet_root_logger
from mmseg.core import DistEvalHook as MMSEG_DistEvalHook
from mmseg.core import EvalHook as MMSEG_EvalHook
from mmseg.datasets import build_dataloader as build_mmseg_dataloader
from mmseg.utils import get_root_logger as get_mmseg_root_logger
def init_random_seed(seed=None, device='cuda'):
"""Initialize random seed.
If the seed is not set, the seed will be automatically randomized,
and then broadcast to all processes to prevent some potential bugs.
Args:
seed (int, optional): The seed. Default to None.
device (str, optional): The device where the seed will be put on.
Default to 'cuda'.
Returns:
int: Seed to be used.
"""
if seed is not None:
return seed
# Make sure all ranks share the same random seed to prevent
# some potential bugs. Please refer to
# https://github.com/open-mmlab/mmdetection/issues/6339
rank, world_size = get_dist_info()
seed = np.random.randint(2**31)
if world_size == 1:
return seed
if rank == 0:
random_num = torch.tensor(seed, dtype=torch.int32, device=device)
else:
random_num = torch.tensor(0, dtype=torch.int32, device=device)
dist.broadcast(random_num, src=0)
return random_num.item()
def set_random_seed(seed, deterministic=False):
"""Set random seed.
Args:
seed (int): Seed to be used.
deterministic (bool): Whether to set the deterministic option for
CUDNN backend, i.e., set `torch.backends.cudnn.deterministic`
to True and `torch.backends.cudnn.benchmark` to False.
Default: False.
"""
random.seed(seed)
np.random.seed(seed)
torch.manual_seed(seed)
torch.cuda.manual_seed_all(seed)
if deterministic:
torch.backends.cudnn.deterministic = True
torch.backends.cudnn.benchmark = False
def train_segmentor(model,
dataset,
cfg,
distributed=False,
validate=False,
timestamp=None,
meta=None):
"""Launch segmentor training."""
logger = get_mmseg_root_logger(cfg.log_level)
# prepare data loaders
dataset = dataset if isinstance(dataset, (list, tuple)) else [dataset]
data_loaders = [
build_mmseg_dataloader(
ds,
cfg.data.samples_per_gpu,
cfg.data.workers_per_gpu,
# cfg.gpus will be ignored if distributed
len(cfg.gpu_ids),
dist=distributed,
seed=cfg.seed,
drop_last=True) for ds in dataset
]
# put model on gpus
if distributed:
find_unused_parameters = cfg.get('find_unused_parameters', False)
# Sets the `find_unused_parameters` parameter in
# torch.nn.parallel.DistributedDataParallel
model = MMDistributedDataParallel(
model.cuda(),
device_ids=[torch.cuda.current_device()],
broadcast_buffers=False,
find_unused_parameters=find_unused_parameters)
else:
model = MMDataParallel(
model.cuda(cfg.gpu_ids[0]), device_ids=cfg.gpu_ids)
# build runner
optimizer = build_optimizer(model, cfg.optimizer)
if cfg.get('runner') is None:
cfg.runner = {'type': 'IterBasedRunner', 'max_iters': cfg.total_iters}
warnings.warn(
'config is now expected to have a `runner` section, '
'please set `runner` in your config.', UserWarning)
runner = build_runner(
cfg.runner,
default_args=dict(
model=model,
batch_processor=None,
optimizer=optimizer,
work_dir=cfg.work_dir,
logger=logger,
meta=meta))
# register hooks
runner.register_training_hooks(cfg.lr_config, cfg.optimizer_config,
cfg.checkpoint_config, cfg.log_config,
cfg.get('momentum_config', None))
# an ugly walkaround to make the .log and .log.json filenames the same
runner.timestamp = timestamp
# register eval hooks
if validate:
val_dataset = build_dataset(cfg.data.val, dict(test_mode=True))
val_dataloader = build_mmseg_dataloader(
val_dataset,
samples_per_gpu=1,
workers_per_gpu=cfg.data.workers_per_gpu,
dist=distributed,
shuffle=False)
eval_cfg = cfg.get('evaluation', {})
eval_cfg['by_epoch'] = cfg.runner['type'] != 'IterBasedRunner'
eval_hook = MMSEG_DistEvalHook if distributed else MMSEG_EvalHook
# In this PR (https://github.com/open-mmlab/mmcv/pull/1193), the
# priority of IterTimerHook has been modified from 'NORMAL' to 'LOW'.
runner.register_hook(
eval_hook(val_dataloader, **eval_cfg), priority='LOW')
# user-defined hooks
if cfg.get('custom_hooks', None):
custom_hooks = cfg.custom_hooks
assert isinstance(custom_hooks, list), \
f'custom_hooks expect list type, but got {type(custom_hooks)}'
for hook_cfg in cfg.custom_hooks:
assert isinstance(hook_cfg, dict), \
'Each item in custom_hooks expects dict type, but got ' \
f'{type(hook_cfg)}'
hook_cfg = hook_cfg.copy()
priority = hook_cfg.pop('priority', 'NORMAL')
hook = build_from_cfg(hook_cfg, HOOKS)
runner.register_hook(hook, priority=priority)
if cfg.resume_from:
runner.resume(cfg.resume_from)
elif cfg.load_from:
runner.load_checkpoint(cfg.load_from)
runner.run(data_loaders, cfg.workflow)
def train_detector(model,
dataset,
cfg,
distributed=False,
validate=False,
timestamp=None,
meta=None):
logger = get_mmdet_root_logger(log_level=cfg.log_level)
# prepare data loaders
dataset = dataset if isinstance(dataset, (list, tuple)) else [dataset]
if 'imgs_per_gpu' in cfg.data:
logger.warning('"imgs_per_gpu" is deprecated in MMDet V2.0. '
'Please use "samples_per_gpu" instead')
if 'samples_per_gpu' in cfg.data:
logger.warning(
f'Got "imgs_per_gpu"={cfg.data.imgs_per_gpu} and '
f'"samples_per_gpu"={cfg.data.samples_per_gpu}, "imgs_per_gpu"'
f'={cfg.data.imgs_per_gpu} is used in this experiments')
else:
logger.warning(
'Automatically set "samples_per_gpu"="imgs_per_gpu"='
f'{cfg.data.imgs_per_gpu} in this experiments')
cfg.data.samples_per_gpu = cfg.data.imgs_per_gpu
runner_type = 'EpochBasedRunner' if 'runner' not in cfg else cfg.runner[
'type']
data_loaders = [
build_mmdet_dataloader(
ds,
cfg.data.samples_per_gpu,
cfg.data.workers_per_gpu,
# `num_gpus` will be ignored if distributed
num_gpus=len(cfg.gpu_ids),
dist=distributed,
seed=cfg.seed,
runner_type=runner_type,
persistent_workers=cfg.data.get('persistent_workers', False))
for ds in dataset
]
# put model on gpus
if distributed:
find_unused_parameters = cfg.get('find_unused_parameters', False)
# Sets the `find_unused_parameters` parameter in
# torch.nn.parallel.DistributedDataParallel
model = MMDistributedDataParallel(
model.cuda(),
device_ids=[torch.cuda.current_device()],
broadcast_buffers=False,
find_unused_parameters=find_unused_parameters)
else:
model = MMDataParallel(
model.cuda(cfg.gpu_ids[0]), device_ids=cfg.gpu_ids)
# build runner
optimizer = build_optimizer(model, cfg.optimizer)
if 'runner' not in cfg:
cfg.runner = {
'type': 'EpochBasedRunner',
'max_epochs': cfg.total_epochs
}
warnings.warn(
'config is now expected to have a `runner` section, '
'please set `runner` in your config.', UserWarning)
else:
if 'total_epochs' in cfg:
assert cfg.total_epochs == cfg.runner.max_epochs
runner = build_runner(
cfg.runner,
default_args=dict(
model=model,
optimizer=optimizer,
work_dir=cfg.work_dir,
logger=logger,
meta=meta))
# an ugly workaround to make .log and .log.json filenames the same
runner.timestamp = timestamp
# fp16 setting
fp16_cfg = cfg.get('fp16', None)
if fp16_cfg is not None:
optimizer_config = Fp16OptimizerHook(
**cfg.optimizer_config, **fp16_cfg, distributed=distributed)
elif distributed and 'type' not in cfg.optimizer_config:
optimizer_config = OptimizerHook(**cfg.optimizer_config)
else:
optimizer_config = cfg.optimizer_config
# register hooks
runner.register_training_hooks(
cfg.lr_config,
optimizer_config,
cfg.checkpoint_config,
cfg.log_config,
cfg.get('momentum_config', None),
custom_hooks_config=cfg.get('custom_hooks', None))
if distributed:
if isinstance(runner, EpochBasedRunner):
runner.register_hook(DistSamplerSeedHook())
# register eval hooks
if validate:
# Support batch_size > 1 in validation
val_samples_per_gpu = cfg.data.val.pop('samples_per_gpu', 1)
if val_samples_per_gpu > 1:
# Replace 'ImageToTensor' to 'DefaultFormatBundle'
cfg.data.val.pipeline = replace_ImageToTensor(
cfg.data.val.pipeline)
val_dataset = build_dataset(cfg.data.val, dict(test_mode=True))
val_dataloader = build_mmdet_dataloader(
val_dataset,
samples_per_gpu=val_samples_per_gpu,
workers_per_gpu=cfg.data.workers_per_gpu,
dist=distributed,
shuffle=False)
eval_cfg = cfg.get('evaluation', {})
eval_cfg['by_epoch'] = cfg.runner['type'] != 'IterBasedRunner'
eval_hook = MMDET_DistEvalHook if distributed else MMDET_EvalHook
# In this PR (https://github.com/open-mmlab/mmcv/pull/1193), the
# priority of IterTimerHook has been modified from 'NORMAL' to 'LOW'.
runner.register_hook(
eval_hook(val_dataloader, **eval_cfg), priority='LOW')
resume_from = None
if cfg.resume_from is None and cfg.get('auto_resume'):
resume_from = find_latest_checkpoint(cfg.work_dir)
if resume_from is not None:
cfg.resume_from = resume_from
if cfg.resume_from:
runner.resume(cfg.resume_from)
elif cfg.load_from:
runner.load_checkpoint(cfg.load_from)
runner.run(data_loaders, cfg.workflow)
def train_model(model,
dataset,
cfg,
distributed=False,
validate=False,
timestamp=None,
meta=None):
"""A function wrapper for launching model training according to cfg.
Because we need different eval_hook in runner. Should be deprecated in the
future.
"""
if cfg.model.type in ['EncoderDecoder3D']:
train_segmentor(
model,
dataset,
cfg,
distributed=distributed,
validate=validate,
timestamp=timestamp,
meta=meta)
else:
train_detector(
model,
dataset,
cfg,
distributed=distributed,
validate=validate,
timestamp=timestamp,
meta=meta)
mmdet3d/core/anchor/__init__.py
View file @ e3b5253b
# Copyright (c) OpenMMLab. All rights reserved.
from mmdet.core.anchor import build_prior_generator
from .anchor_3d_generator import (AlignedAnchor3DRangeGenerator,
AlignedAnchor3DRangeGeneratorPerCls,
Anchor3DRangeGenerator)
from .builder import (ANCHOR_GENERATORS, PRIOR_GENERATORS,
build_anchor_generator, build_prior_generator)
__all__ = [
'AlignedAnchor3DRangeGenerator', 'Anchor3DRangeGenerator',
'build_prior_generator', 'AlignedAnchor3DRangeGeneratorPerCls'
'build_prior_generator', 'AlignedAnchor3DRangeGeneratorPerCls',
'build_anchor_generator', 'ANCHOR_GENERATORS', 'PRIOR_GENERATORS'
]
mmdet3d/core/anchor/anchor_3d_generator.py
View file @ e3b5253b
......@@ -2,10 +2,10 @@
import mmcv
import torch
from mmdet.core.anchor import ANCHOR_GENERATORS
from mmdet3d.registry import TASK_UTILS
@ANCHOR_GENERATORS.register_module()
@TASK_UTILS.register_module()
class Anchor3DRangeGenerator(object):
"""3D Anchor Generator by range.
......@@ -221,7 +221,7 @@ class Anchor3DRangeGenerator(object):
return ret
@ANCHOR_GENERATORS.register_module()
@TASK_UTILS.register_module()
class AlignedAnchor3DRangeGenerator(Anchor3DRangeGenerator):
"""Aligned 3D Anchor Generator by range.
......@@ -340,7 +340,7 @@ class AlignedAnchor3DRangeGenerator(Anchor3DRangeGenerator):
return ret
@ANCHOR_GENERATORS.register_module()
@TASK_UTILS.register_module()
class AlignedAnchor3DRangeGeneratorPerCls(AlignedAnchor3DRangeGenerator):
"""3D Anchor Generator by range for per class.
......
mmdet3d/core/anchor/builder.py 0 → 100644
View file @ e3b5253b
# Copyright (c) OpenMMLab. All rights reserved.
import warnings
from mmdet3d.registry import TASK_UTILS
PRIOR_GENERATORS = TASK_UTILS
ANCHOR_GENERATORS = TASK_UTILS
def build_prior_generator(cfg, default_args=None):
warnings.warn(
'``build_prior_generator`` would be deprecated soon, please use '
'``mmdet3d.registry.TASK_UTILS.build()`` ')
return TASK_UTILS.build(cfg, default_args=default_args)
def build_anchor_generator(cfg, default_args=None):
warnings.warn(
'``build_anchor_generator`` would be deprecated soon, please use '
'``mmdet3d.registry.TASK_UTILS.build()`` ')
return TASK_UTILS.build(cfg, default_args=default_args)
mmdet3d/core/bbox/__init__.py
View file @ e3b5253b
# Copyright (c) OpenMMLab. All rights reserved.
from .assigners import AssignResult, BaseAssigner, MaxIoUAssigner
from .coders import DeltaXYZWLHRBBoxCoder
# from .bbox_target import bbox_target
from .builder import build_assigner, build_bbox_coder, build_sampler
from .coders import DeltaXYZWLHRBBoxCoder
from .iou_calculators import (AxisAlignedBboxOverlaps3D, BboxOverlaps3D,
BboxOverlapsNearest3D,
axis_aligned_bbox_overlaps_3d, bbox_overlaps_3d,
......@@ -26,5 +27,6 @@ __all__ = [
'LiDARInstance3DBoxes', 'CameraInstance3DBoxes', 'bbox3d2roi',
'bbox3d2result', 'DepthInstance3DBoxes', 'BaseInstance3DBoxes',
'bbox3d_mapping_back', 'xywhr2xyxyr', 'limit_period', 'points_cam2img',
'points_img2cam', 'get_box_type', 'Coord3DMode', 'mono_cam_box2vis'
'points_img2cam', 'get_box_type', 'Coord3DMode', 'mono_cam_box2vis',
'build_assigner', 'build_bbox_coder', 'build_sampler'
]
mmdet3d/core/bbox/builder.py 0 → 100644
View file @ e3b5253b
# Copyright (c) OpenMMLab. All rights reserved.
import warnings
from mmdet3d.registry import TASK_UTILS
BBOX_ASSIGNERS = TASK_UTILS
BBOX_SAMPLERS = TASK_UTILS
BBOX_CODERS = TASK_UTILS
def build_assigner(cfg, **default_args):
"""Builder of box assigner."""
warnings.warn('``build_assigner`` would be deprecated soon, please use '
'``mmdet3d.registry.TASK_UTILS.build()`` ')
return TASK_UTILS.build(cfg, default_args=default_args)
def build_sampler(cfg, **default_args):
"""Builder of box sampler."""
warnings.warn('``build_sampler`` would be deprecated soon, please use '
'``mmdet3d.registry.TASK_UTILS.build()`` ')
return TASK_UTILS.build(cfg, default_args=default_args)
def build_bbox_coder(cfg, **default_args):
"""Builder of box coder."""
warnings.warn('``build_bbox_coder`` would be deprecated soon, please use '
'``mmdet3d.registry.TASK_UTILS.build()`` ')
return TASK_UTILS.build(cfg, default_args=default_args)
mmdet3d/core/bbox/coders/__init__.py
View file @ e3b5253b
# Copyright (c) OpenMMLab. All rights reserved.
from mmdet.core.bbox import build_bbox_coder
from .anchor_free_bbox_coder import AnchorFreeBBoxCoder
from .centerpoint_bbox_coders import CenterPointBBoxCoder
from .delta_xyzwhlr_bbox_coder import DeltaXYZWLHRBBoxCoder
......@@ -12,7 +11,7 @@ from .point_xyzwhlr_bbox_coder import PointXYZWHLRBBoxCoder
from .smoke_bbox_coder import SMOKECoder
__all__ = [
'build_bbox_coder', 'DeltaXYZWLHRBBoxCoder', 'PartialBinBasedBBoxCoder',
'DeltaXYZWLHRBBoxCoder', 'PartialBinBasedBBoxCoder',
'CenterPointBBoxCoder', 'AnchorFreeBBoxCoder', 'GroupFree3DBBoxCoder',
'PointXYZWHLRBBoxCoder', 'FCOS3DBBoxCoder', 'PGDBBoxCoder', 'SMOKECoder',
'MonoFlexCoder'
......
mmdet3d/core/bbox/coders/anchor_free_bbox_coder.py
View file @ e3b5253b
......@@ -2,11 +2,11 @@
import numpy as np
import torch
from mmdet.core.bbox.builder import BBOX_CODERS
from mmdet3d.registry import TASK_UTILS
from .partial_bin_based_bbox_coder import PartialBinBasedBBoxCoder
@BBOX_CODERS.register_module()
@TASK_UTILS.register_module()
class AnchorFreeBBoxCoder(PartialBinBasedBBoxCoder):
"""Anchor free bbox coder for 3D boxes.
......
mmdet3d/core/bbox/coders/centerpoint_bbox_coders.py
View file @ e3b5253b
# Copyright (c) OpenMMLab. All rights reserved.
import torch
from mmdet3d.registry import TASK_UTILS
from mmdet.core.bbox import BaseBBoxCoder
from mmdet.core.bbox.builder import BBOX_CODERS
@BBOX_CODERS.register_module()
@TASK_UTILS.register_module()
class CenterPointBBoxCoder(BaseBBoxCoder):
"""Bbox coder for CenterPoint.
......
mmdet3d/core/bbox/coders/delta_xyzwhlr_bbox_coder.py
View file @ e3b5253b
# Copyright (c) OpenMMLab. All rights reserved.
import torch
from mmdet3d.registry import TASK_UTILS
from mmdet.core.bbox import BaseBBoxCoder
from mmdet.core.bbox.builder import BBOX_CODERS
@BBOX_CODERS.register_module()
@TASK_UTILS.register_module()
class DeltaXYZWLHRBBoxCoder(BaseBBoxCoder):
"""Bbox Coder for 3D boxes.
......
mmdet3d/core/bbox/coders/fcos3d_bbox_coder.py
View file @ e3b5253b
......@@ -2,12 +2,12 @@
import numpy as np
import torch
from mmdet3d.registry import TASK_UTILS
from mmdet.core.bbox import BaseBBoxCoder
from mmdet.core.bbox.builder import BBOX_CODERS
from ..structures import limit_period
@BBOX_CODERS.register_module()
@TASK_UTILS.register_module()
class FCOS3DBBoxCoder(BaseBBoxCoder):
"""Bounding box coder for FCOS3D.
......
mmdet3d/core/bbox/coders/groupfree3d_bbox_coder.py
View file @ e3b5253b
......@@ -2,11 +2,11 @@
import numpy as np
import torch
from mmdet.core.bbox.builder import BBOX_CODERS
from mmdet3d.registry import TASK_UTILS
from .partial_bin_based_bbox_coder import PartialBinBasedBBoxCoder
@BBOX_CODERS.register_module()
@TASK_UTILS.register_module()
class GroupFree3DBBoxCoder(PartialBinBasedBBoxCoder):
"""Modified partial bin based bbox coder for GroupFree3D.
......
mmdet3d/core/bbox/coders/monoflex_bbox_coder.py
View file @ e3b5253b
......@@ -3,11 +3,11 @@ import numpy as np
import torch
from torch.nn import functional as F
from mmdet3d.registry import TASK_UTILS
from mmdet.core.bbox import BaseBBoxCoder
from mmdet.core.bbox.builder import BBOX_CODERS
@BBOX_CODERS.register_module()
@TASK_UTILS.register_module()
class MonoFlexCoder(BaseBBoxCoder):
"""Bbox Coder for MonoFlex.
......
mmdet3d/core/bbox/coders/partial_bin_based_bbox_coder.py
View file @ e3b5253b
......@@ -2,11 +2,11 @@
import numpy as np
import torch
from mmdet3d.registry import TASK_UTILS
from mmdet.core.bbox import BaseBBoxCoder
from mmdet.core.bbox.builder import BBOX_CODERS
@BBOX_CODERS.register_module()
@TASK_UTILS.register_module()
class PartialBinBasedBBoxCoder(BaseBBoxCoder):
"""Partial bin based bbox coder.
......
mmdet3d/core/bbox/coders/pgd_bbox_coder.py
View file @ e3b5253b
......@@ -3,11 +3,11 @@ import numpy as np
import torch
from torch.nn import functional as F
from mmdet.core.bbox.builder import BBOX_CODERS
from mmdet3d.registry import TASK_UTILS
from .fcos3d_bbox_coder import FCOS3DBBoxCoder
@BBOX_CODERS.register_module()
@TASK_UTILS.register_module()
class PGDBBoxCoder(FCOS3DBBoxCoder):
"""Bounding box coder for PGD."""
......
mmdet3d/core/bbox/coders/point_xyzwhlr_bbox_coder.py
View file @ e3b5253b
......@@ -2,11 +2,11 @@
import numpy as np
import torch
from mmdet3d.registry import TASK_UTILS
from mmdet.core.bbox import BaseBBoxCoder
from mmdet.core.bbox.builder import BBOX_CODERS
@BBOX_CODERS.register_module()
@TASK_UTILS.register_module()
class PointXYZWHLRBBoxCoder(BaseBBoxCoder):
"""Point based bbox coder for 3D boxes.
......
mmdet3d/core/bbox/coders/smoke_bbox_coder.py
View file @ e3b5253b
......@@ -2,11 +2,11 @@
import numpy as np
import torch
from mmdet3d.registry import TASK_UTILS
from mmdet.core.bbox import BaseBBoxCoder
from mmdet.core.bbox.builder import BBOX_CODERS
@BBOX_CODERS.register_module()
@TASK_UTILS.register_module()
class SMOKECoder(BaseBBoxCoder):
"""Bbox Coder for SMOKE.
......
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