def main():
args = parse_args()
cfg = Config.fromfile(args.config)
# set cudnn_benchmark
torch.backends.cudnn.benchmark = False
cfg.model.pretrained = None
cfg.data.test.test_mode = True
# build the dataloader
# TODO: support multiple images per gpu (only minor changes are needed)
dataset = build_dataset(cfg.data.test)
data_loader = build_dataloader(
dataset,
samples_per_gpu=1,
workers_per_gpu=cfg.data.workers_per_gpu,
dist=False,
shuffle=False)
# build the model and load checkpoint
cfg.model.train_cfg = None
model = build_segmentor(cfg.model, test_cfg=cfg.get('test_cfg'))
fp16_cfg = cfg.get('fp16', None)
if fp16_cfg is not None:
wrap_fp16_model(model)
load_checkpoint(model, args.checkpoint, map_location='cpu')
model = MMDataParallel(model, device_ids=[0])
model.eval()
# the first several iterations may be very slow so skip them
num_warmup = 5
pure_inf_time = 0
total_iters = 200
# benchmark with 200 image and take the average
for i, data in enumerate(data_loader):
torch.cuda.synchronize()
start_time = time.perf_counter()
with torch.no_grad():
model(return_loss=False, rescale=True, **data)
torch.cuda.synchronize()
elapsed = time.perf_counter() - start_time
if i >= num_warmup:
pure_inf_time += elapsed
if (i + 1) % args.log_interval == 0:
fps = (i + 1 - num_warmup) / pure_inf_time
print(f'Done image [{i + 1:<3}/ {total_iters}], '
f'fps: {fps:.2f} img / s')
if (i + 1) == total_iters:
fps = (i + 1 - num_warmup) / pure_inf_time
print(f'Overall fps: {fps:.2f} img / s')
break
def main():
args = parse_args()
assert args.out or args.eval or args.format_only or args.show \
or args.show_dir, \
('Please specify at least one operation (save/eval/format/show the '
'results / save the results) with the argument "--out", "--eval"'
', "--format-only", "--show" or "--show-dir"')
if args.eval and args.format_only:
raise ValueError('--eval and --format_only cannot be both specified')
if args.out is not None and not args.out.endswith(('.pkl', '.pickle')):
raise ValueError('The output file must be a pkl file.')
cfg = mmcv.Config.fromfile(args.config)
if args.options is not None:
cfg.merge_from_dict(args.options)
cfg.model.pretrained = None
cfg.data.test.test_mode = True
# init distributed env first, since logger depends on the dist info.
distributed = False
# build the dataloader
# TODO: support multiple images per gpu (only minor changes are needed)
dataset = build_dataset(cfg.data.test)
data_loader = build_dataloader(
dataset,
samples_per_gpu=1,
workers_per_gpu=cfg.data.workers_per_gpu,
dist=distributed,
shuffle=False)
# load onnx config and meta
cfg.model.train_cfg = None
model = ONNXRuntimeSegmentor(args.model, cfg=cfg, device_id=0)
model.CLASSES = dataset.CLASSES
model.PALETTE = dataset.PALETTE
efficient_test = False
if args.eval_options is not None:
efficient_test = args.eval_options.get('efficient_test', False)
model = MMDataParallel(model, device_ids=[0])
outputs = single_gpu_test(model, data_loader, args.show, args.show_dir,
efficient_test, args.opacity)
rank, _ = get_dist_info()
if rank == 0:
if args.out:
print(f'\nwriting results to {args.out}')
mmcv.dump(outputs, args.out)
kwargs = {} if args.eval_options is None else args.eval_options
if args.format_only:
dataset.format_results(outputs, **kwargs)
if args.eval:
dataset.evaluate(outputs, args.eval, **kwargs)
def predict_rsImage_mmseg(config_file,
trained_model,
image_path,
img_save_dir,
batch_size=1,
gpuid=0,
tile_width=480,
tile_height=480,
overlay_x=160,
overlay_y=160):
cfg = mmcv.Config.fromfile(config_file)
if cfg.get('cudnn_benchmark', False):
torch.backends.cudnn.benchmark = True
cfg.data.test.test_mode = True
distributed = False
# test_mode=False,rsimage='',rsImg_id=0,tile_width=480,tile_height=480,
# overlay_x=160,overlay_y=160
data_args = {
'rsImg_predict': True,
'rsimage': image_path,
'tile_width': tile_width,
'tile_height': tile_height,
'overlay_x': overlay_x,
'overlay_y': overlay_y
}
dataset = build_dataset(cfg.data.test, default_args=data_args)
data_loader = build_dataloader(dataset,
samples_per_gpu=batch_size,
workers_per_gpu=cfg.data.workers_per_gpu,
dist=distributed,
shuffle=False)
cfg.model.train_cfg = None
model = build_segmentor(cfg.model, test_cfg=cfg.get('test_cfg'))
fp16_cfg = cfg.get('fp16', None)
if fp16_cfg is not None:
wrap_fp16_model(model)
checkpoint = load_checkpoint(model, trained_model, map_location='cpu')
if 'CLASSES' in checkpoint.get('meta', {}):
model.CLASSES = checkpoint['meta']['CLASSES']
else:
print('"CLASSES" not found in meta, use dataset.CLASSES instead')
model.CLASSES = dataset.CLASSES
if 'PALETTE' in checkpoint.get('meta', {}):
model.PALETTE = checkpoint['meta']['PALETTE']
else:
print('"PALETTE" not found in meta, use dataset.PALETTE instead')
model.PALETTE = dataset.PALETTE
# clean gpu memory when starting a new evaluation.
torch.cuda.empty_cache()
# no distributed
model = MMDataParallel(model, device_ids=[gpuid])
single_gpu_prediction_rsImage(model, data_loader, img_save_dir)
logger.info(f'Config:\n{cfg.pretty_text}')
model = build_segmentor(cfg.model,
train_cfg=cfg.train_cfg,
test_cfg=cfg.test_cfg)
# checkpoint = '/home/zhouzhigong/Documents/mmsegmentation/work_dirs/pspnet_r18-d8_512x512_40k_cityscapes_skd/iter_40000.pth'
# checkpoint = load_checkpoint(model, checkpoint)
model.cuda(0)
model_paral = MMDataParallel(model, device_ids=[0])
train_dataset = build_dataset(cfg.data.train)
train_data_loader = build_dataloader(
train_dataset,
cfg.data.samples_per_gpu, # samples_per_gpu
cfg.data.workers_per_gpu, # workers_per_gpu
len(cfg.gpu_ids),
dist=False,
seed=cfg.seed,
drop_last=True)
val_dataset = build_dataset(cfg.data.test)
val_data_loader = build_dataloader(
val_dataset,
samples_per_gpu=4,
workers_per_gpu=4,
# workers_per_gpu=S_cfg.data.workers_per_gpu,
dist=False,
shuffle=False,
drop_last=True,
)
# # checkpoint = '/home/zhouzhigong/Documents/mmsegmentation/work_dirs/pspnet_r18-d8_512x512_40k_cityscapes_skd/iter_20000.pth'
cfg = seg_model.cfg
train_dataset = CityscapesDataset(data_root=cityspaces_path,
pipeline=cfg.data.train.pipeline,
img_dir=cfg.data.train.img_dir,
ann_dir=cfg.data.train.ann_dir,
test_mode=False)
val_dataset = CityscapesDataset(data_root=cityspaces_path,
pipeline=cfg.data.val.pipeline,
img_dir=cfg.data.val.img_dir,
ann_dir=cfg.data.val.ann_dir,
test_mode=False)
train_loader = build_dataloader(train_dataset,
samples_per_gpu=batch_size,
workers_per_gpu=0,
dataloader_type="DataLoader")
val_loader = build_dataloader(val_dataset,
samples_per_gpu=batch_size,
workers_per_gpu=0,
dataloader_type="DataLoader")
# Freeze Seg Network
for param in seg_model.parameters():
param.requires_grad = False
optimizer = torch.optim.Adam(crf.parameters(), lr=1e-3)
def get_evaluations(log_proba, seg, n_classes, ignore_idx):
def main():
args = parse_args()
assert args.out or args.eval or args.format_only or args.show \
or args.show_dir, \
('Please specify at least one operation (save/eval/format/show the '
'results / save the results) with the argument "--out", "--eval"'
', "--format-only", "--show" or "--show-dir"')
if args.eval and args.format_only:
raise ValueError('--eval and --format_only cannot be both specified')
if args.out is not None and not args.out.endswith(('.pkl', '.pickle')):
raise ValueError('The output file must be a pkl file.')
cfg = mmcv.Config.fromfile(args.config)
if args.cfg_options is not None:
cfg.merge_from_dict(args.cfg_options)
cfg.model.pretrained = None
cfg.data.test.test_mode = True
# init distributed env first, since logger depends on the dist info.
distributed = False
# build the dataloader
# TODO: support multiple images per gpu (only minor changes are needed)
dataset = build_dataset(cfg.data.test)
data_loader = build_dataloader(dataset,
samples_per_gpu=1,
workers_per_gpu=cfg.data.workers_per_gpu,
dist=distributed,
shuffle=False)
# load onnx config and meta
cfg.model.train_cfg = None
if args.backend == 'onnxruntime':
model = ONNXRuntimeSegmentor(args.model, cfg=cfg, device_id=0)
elif args.backend == 'tensorrt':
model = TensorRTSegmentor(args.model, cfg=cfg, device_id=0)
model.CLASSES = dataset.CLASSES
model.PALETTE = dataset.PALETTE
# clean gpu memory when starting a new evaluation.
torch.cuda.empty_cache()
eval_kwargs = {} if args.eval_options is None else args.eval_options
# Deprecated
efficient_test = eval_kwargs.get('efficient_test', False)
if efficient_test:
warnings.warn(
'``efficient_test=True`` does not have effect in tools/test.py, '
'the evaluation and format results are CPU memory efficient by '
'default')
eval_on_format_results = (args.eval is not None
and 'cityscapes' in args.eval)
if eval_on_format_results:
assert len(args.eval) == 1, 'eval on format results is not ' \
'applicable for metrics other than ' \
'cityscapes'
if args.format_only or eval_on_format_results:
if 'imgfile_prefix' in eval_kwargs:
tmpdir = eval_kwargs['imgfile_prefix']
else:
tmpdir = '.format_cityscapes'
eval_kwargs.setdefault('imgfile_prefix', tmpdir)
mmcv.mkdir_or_exist(tmpdir)
else:
tmpdir = None
model = MMDataParallel(model, device_ids=[0])
results = single_gpu_test(model,
data_loader,
args.show,
args.show_dir,
False,
args.opacity,
pre_eval=args.eval is not None
and not eval_on_format_results,
format_only=args.format_only
or eval_on_format_results,
format_args=eval_kwargs)
rank, _ = get_dist_info()
if rank == 0:
if args.out:
warnings.warn(
'The behavior of ``args.out`` has been changed since MMSeg '
'v0.16, the pickled outputs could be seg map as type of '
'np.array, pre-eval results or file paths for '
'``dataset.format_results()``.')
print(f'\nwriting results to {args.out}')
mmcv.dump(results, args.out)
if args.eval:
dataset.evaluate(results, args.eval, **eval_kwargs)
if tmpdir is not None and eval_on_format_results:
# remove tmp dir when cityscapes evaluation
shutil.rmtree(tmpdir)
def main():
args = parse_args()
cfg = Config.fromfile(args.config)
timestamp = time.strftime('%Y%m%d_%H%M%S', time.localtime())
if args.work_dir is not None:
mmcv.mkdir_or_exist(osp.abspath(args.work_dir))
json_file = osp.join(args.work_dir, f'fps_{timestamp}.json')
else:
# use config filename as default work_dir if cfg.work_dir is None
work_dir = osp.join('./work_dirs',
osp.splitext(osp.basename(args.config))[0])
mmcv.mkdir_or_exist(osp.abspath(work_dir))
json_file = osp.join(work_dir, f'fps_{timestamp}.json')
repeat_times = args.repeat_times
# set cudnn_benchmark
torch.backends.cudnn.benchmark = False
cfg.model.pretrained = None
cfg.data.test.test_mode = True
benchmark_dict = dict(config=args.config, unit='img / s')
overall_fps_list = []
for time_index in range(repeat_times):
print(f'Run {time_index + 1}:')
# build the dataloader
# TODO: support multiple images per gpu (only minor changes are needed)
dataset = build_dataset(cfg.data.test)
data_loader = build_dataloader(
dataset,
samples_per_gpu=1,
workers_per_gpu=cfg.data.workers_per_gpu,
dist=False,
shuffle=False)
# build the model and load checkpoint
cfg.model.train_cfg = None
model = build_segmentor(cfg.model, test_cfg=cfg.get('test_cfg'))
fp16_cfg = cfg.get('fp16', None)
if fp16_cfg is not None:
wrap_fp16_model(model)
if 'checkpoint' in args and osp.exists(args.checkpoint):
load_checkpoint(model, args.checkpoint, map_location='cpu')
model = MMDataParallel(model, device_ids=[0])
model.eval()
# the first several iterations may be very slow so skip them
num_warmup = 5
pure_inf_time = 0
total_iters = 200
# benchmark with 200 image and take the average
for i, data in enumerate(data_loader):
torch.cuda.synchronize()
start_time = time.perf_counter()
with torch.no_grad():
model(return_loss=False, rescale=True, **data)
torch.cuda.synchronize()
elapsed = time.perf_counter() - start_time
if i >= num_warmup:
pure_inf_time += elapsed
if (i + 1) % args.log_interval == 0:
fps = (i + 1 - num_warmup) / pure_inf_time
print(f'Done image [{i + 1:<3}/ {total_iters}], '
f'fps: {fps:.2f} img / s')
if (i + 1) == total_iters:
fps = (i + 1 - num_warmup) / pure_inf_time
print(f'Overall fps: {fps:.2f} img / s\n')
benchmark_dict[f'overall_fps_{time_index + 1}'] = round(fps, 2)
overall_fps_list.append(fps)
break
benchmark_dict['average_fps'] = round(np.mean(overall_fps_list), 2)
benchmark_dict['fps_variance'] = round(np.var(overall_fps_list), 4)
print(f'Average fps of {repeat_times} evaluations: '
f'{benchmark_dict["average_fps"]}')
print(f'The variance of {repeat_times} evaluations: '
f'{benchmark_dict["fps_variance"]}')
mmcv.dump(benchmark_dict, json_file, indent=4)
def train_segmentor(model,
dataset,
cfg,
distributed=False,
validate=False,
timestamp=None,
meta=None):
"""Launch segmentor training."""
logger = get_root_logger(cfg.log_level)
# prepare data loaders
# print('----------------------------')
# print(type(dataset),len(dataset)) # <class 'list'> 1
# print(type(dataset[0])) # <class 'mmseg.datasets.cityscapes.CityscapesDataset'>
# print(len(dataset[0])) # 2975
# print(dataset[0][0]['img'].size())
dataset = dataset if isinstance(dataset, (list, tuple)) else [dataset]
data_loaders = [
build_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
]
print('---------------------------')
# print(data_loaders[0].next)
print('before')
print(cfg.gpu_ids)
print(next(model.parameters()).device)
# print(next(model.teacher.parameters()).device)
# put model on gpus
if distributed:
find_unused_parameters = cfg.get('find_unused_parameters', False)
find_unused_parameters = True
# 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)
print('after')
print(next(model.parameters()).device)
# print(next(model.teacher.parameters()).device)
# build runner
optimizer = build_optimizer(model, cfg.optimizer)
runner = IterBasedRunner(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_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_hook = DistEvalHook if distributed else EvalHook
runner.register_hook(eval_hook(val_dataloader, **eval_cfg))
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, cfg.total_iters)
model = build_segmentor(cfg.model,
train_cfg=cfg.train_cfg,
test_cfg=cfg.test_cfg)
checkpoint = '/home/zhouzhigong/Documents/mmsegmentation/work_dirs/pspnet_r18-d8_512x512_40k_cityscapes_skd/iter_40000.pth'
checkpoint = load_checkpoint(model, checkpoint)
model.eval()
# model.cuda(0)
model = MMDataParallel(model, device_ids=[1])
# dataset = build_dataset(cfg.data.train)
dataset = build_dataset(cfg.data.test)
data_loader = build_dataloader(
dataset,
samples_per_gpu=4,
workers_per_gpu=4,
# workers_per_gpu=S_cfg.data.workers_per_gpu,
dist=False,
shuffle=False,
drop_last=True,
)
outputs = single_gpu_test(model, data_loader, show=False, out_dir=None)
eval_results = dataset.evaluate(outputs, metric='mIoU', logger=None)
print(
eval_results
) # {'mIoU': 0.5864396163552457, 'mAcc': 0.6625518273733926, 'aAcc': 0.9302386656807492}
# for i in range(5):
# data_batch = next(iter_loaders[0])
# print(data_batch.keys())
# img = data_batch['img'].data
# img_metas = data_batch['img_metas'].data
def test_build_dataloader():
dataset = ToyDataset()
samples_per_gpu = 3
# dist=True, shuffle=True, 1GPU
dataloader = build_dataloader(dataset,
samples_per_gpu=samples_per_gpu,
workers_per_gpu=2)
assert dataloader.batch_size == samples_per_gpu
assert len(dataloader) == int(math.ceil(len(dataset) / samples_per_gpu))
assert isinstance(dataloader.sampler, DistributedSampler)
assert dataloader.sampler.shuffle
# dist=True, shuffle=False, 1GPU
dataloader = build_dataloader(dataset,
samples_per_gpu=samples_per_gpu,
workers_per_gpu=2,
shuffle=False)
assert dataloader.batch_size == samples_per_gpu
assert len(dataloader) == int(math.ceil(len(dataset) / samples_per_gpu))
assert isinstance(dataloader.sampler, DistributedSampler)
assert not dataloader.sampler.shuffle
# dist=True, shuffle=True, 8GPU
dataloader = build_dataloader(dataset,
samples_per_gpu=samples_per_gpu,
workers_per_gpu=2,
num_gpus=8)
assert dataloader.batch_size == samples_per_gpu
assert len(dataloader) == int(math.ceil(len(dataset) / samples_per_gpu))
assert dataloader.num_workers == 2
# dist=False, shuffle=True, 1GPU
dataloader = build_dataloader(dataset,
samples_per_gpu=samples_per_gpu,
workers_per_gpu=2,
dist=False)
assert dataloader.batch_size == samples_per_gpu
assert len(dataloader) == int(math.ceil(len(dataset) / samples_per_gpu))
assert isinstance(dataloader.sampler, RandomSampler)
assert dataloader.num_workers == 2
# dist=False, shuffle=False, 1GPU
dataloader = build_dataloader(dataset,
samples_per_gpu=3,
workers_per_gpu=2,
shuffle=False,
dist=False)
assert dataloader.batch_size == samples_per_gpu
assert len(dataloader) == int(math.ceil(len(dataset) / samples_per_gpu))
assert isinstance(dataloader.sampler, SequentialSampler)
assert dataloader.num_workers == 2
# dist=False, shuffle=True, 8GPU
dataloader = build_dataloader(dataset,
samples_per_gpu=3,
workers_per_gpu=2,
num_gpus=8,
dist=False)
assert dataloader.batch_size == samples_per_gpu * 8
assert len(dataloader) == int(math.ceil(
len(dataset) / samples_per_gpu / 8))
assert isinstance(dataloader.sampler, RandomSampler)
assert dataloader.num_workers == 16
data_root=data_root,
img_dir='train/image',
ann_dir='train/label_cvt',
split='train/split/val_mini.txt',
mosaic_ratio=1,
pipeline=train_pipeline),
)
dataset = [build_dataset(data['train'])]
bs = 8
data_loaders = [
build_dataloader(
ds,
bs,
0,
# cfg.gpus will be ignored if distributed
len(range(0, 1)),
dist=False,
seed=41) for ds in dataset
]
data_loader = data_loaders[0]
data_per_batch = iter(data_loader).__next__()
img_metas = data_per_batch['img_metas']
img_metas_data = img_metas.data[0]
images = data_per_batch['img'].data[0].numpy()
labels = data_per_batch['gt_semantic_seg'].data[0]
for image, label, data_info in zip(images, labels, img_metas_data):
def train_segmentor(model,
dataset,
cfg,
distributed=False,
validate=False,
timestamp=None,
meta=None):
"""Launch segmentor training."""
logger = get_root_logger(cfg.log_level)
# prepare data loaders
dataset = dataset if isinstance(dataset, (list, tuple)) else [dataset]
if not torch.cuda.is_available():
len_gpu_ids = 2 # need to be changed
else:
len_gpu_ids = len(cfg.gpu_ids)
data_loaders = [
build_dataloader(
ds, # A PyTorch dataset.
cfg.data.
samples_per_gpu, # Number of training samples on each GPU, i.e., batch size of each GPU.
cfg.data.
workers_per_gpu, # How many subprocesses to use for data loading for each GPU.
# cfg.gpus will be ignored if distributed
len_gpu_ids,
# len(cfg.gpu_ids), # Number of GPUs. Only used in non-distributed training.
dist=distributed, # Distributed training/test or not. Default: True.
seed=cfg.seed,
drop_last=True) for ds in dataset
]
''' About build_dataloader
shuffle (bool): Whether to shuffle the data at every epoch.
Default: True.
seed (int | None): Seed to be used. Default: None.
drop_last (bool): Whether to drop the last incomplete batch in epoch.
Default: False
pin_memory (bool): Whether to use pin_memory in DataLoader.
Default: True
dataloader_type (str): Type of dataloader. Default: 'PoolDataLoader'
kwargs: any keyword argument to be used to initialize DataLoader'''
# 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:
if torch.cuda.is_available():
model = MMDataParallel(model.cuda(cfg.gpu_ids[0]),
device_ids=cfg.gpu_ids)
else:
model = MMDataParallel(model.to('cpu'))
# 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_dataloader(
val_dataset,
samples_per_gpu=len_gpu_ids,
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 = DistEvalHook if distributed else EvalHook
runner.register_hook(eval_hook(val_dataloader, **eval_cfg))
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 main():
args = parse_args()
assert args.out or args.eval or args.format_only or args.show \
or args.show_dir, \
('Please specify at least one operation (save/eval/format/show the '
'results / save the results) with the argument "--out", "--eval"'
', "--format-only", "--show" or "--show-dir"')
if args.eval and args.format_only:
raise ValueError('--eval and --format_only cannot be both specified')
if args.out is not None and not args.out.endswith(('.pkl', '.pickle')):
raise ValueError('The output file must be a pkl file.')
cfg = mmcv.Config.fromfile(args.config)
if args.options is not None:
cfg.merge_from_dict(args.options)
# set cudnn_benchmark
if cfg.get('cudnn_benchmark', False):
torch.backends.cudnn.benchmark = True
if args.aug_test:
# hard code index
cfg.data.test.pipeline[1].img_ratios = [
0.5, 0.75, 1.0, 1.25, 1.5, 1.75
]
cfg.data.test.pipeline[1].flip = True
cfg.model.pretrained = None
cfg.data.test.test_mode = True
# init distributed env first, since logger depends on the dist info.
if args.launcher == 'none':
distributed = False
else:
distributed = True
init_dist(args.launcher, **cfg.dist_params)
rank, _ = get_dist_info()
# allows not to create
if args.work_dir is not None and rank == 0:
mmcv.mkdir_or_exist(osp.abspath(args.work_dir))
timestamp = time.strftime('%Y%m%d_%H%M%S', time.localtime())
json_file = osp.join(args.work_dir, f'eval_{timestamp}.json')
# build the dataloader
# TODO: support multiple images per gpu (only minor changes are needed)
dataset = build_dataset(cfg.data.test)
data_loader = build_dataloader(dataset,
samples_per_gpu=1,
workers_per_gpu=cfg.data.workers_per_gpu,
dist=distributed,
shuffle=False)
# build the model and load checkpoint
cfg.model.train_cfg = None
model = build_segmentor(cfg.model, test_cfg=cfg.get('test_cfg'))
fp16_cfg = cfg.get('fp16', None)
if fp16_cfg is not None:
wrap_fp16_model(model)
checkpoint = load_checkpoint(model, args.checkpoint, map_location='cpu')
if 'CLASSES' in checkpoint.get('meta', {}):
model.CLASSES = checkpoint['meta']['CLASSES']
else:
print('"CLASSES" not found in meta, use dataset.CLASSES instead')
model.CLASSES = dataset.CLASSES
if 'PALETTE' in checkpoint.get('meta', {}):
model.PALETTE = checkpoint['meta']['PALETTE']
else:
print('"PALETTE" not found in meta, use dataset.PALETTE instead')
model.PALETTE = dataset.PALETTE
# clean gpu memory when starting a new evaluation.
torch.cuda.empty_cache()
eval_kwargs = {} if args.eval_options is None else args.eval_options
# Deprecated
efficient_test = eval_kwargs.get('efficient_test', False)
if efficient_test:
warnings.warn(
'``efficient_test=True`` does not have effect in tools/test.py, '
'the evaluation and format results are CPU memory efficient by '
'default')
eval_on_format_results = (args.eval is not None
and 'cityscapes' in args.eval)
if eval_on_format_results:
assert len(args.eval) == 1, 'eval on format results is not ' \
'applicable for metrics other than ' \
'cityscapes'
if args.format_only or eval_on_format_results:
if 'imgfile_prefix' in eval_kwargs:
tmpdir = eval_kwargs['imgfile_prefix']
else:
tmpdir = '.format_cityscapes'
eval_kwargs.setdefault('imgfile_prefix', tmpdir)
mmcv.mkdir_or_exist(tmpdir)
else:
tmpdir = None
if not distributed:
model = MMDataParallel(model, device_ids=[0])
results = single_gpu_test(model,
data_loader,
args.show,
args.show_dir,
False,
args.opacity,
pre_eval=args.eval is not None
and not eval_on_format_results,
format_only=args.format_only
or eval_on_format_results,
format_args=eval_kwargs)
else:
model = MMDistributedDataParallel(
model.cuda(),
device_ids=[torch.cuda.current_device()],
broadcast_buffers=False)
results = multi_gpu_test(model,
data_loader,
args.tmpdir,
args.gpu_collect,
False,
pre_eval=args.eval is not None
and not eval_on_format_results,
format_only=args.format_only
or eval_on_format_results,
format_args=eval_kwargs)
rank, _ = get_dist_info()
if rank == 0:
if args.out:
warnings.warn(
'The behavior of ``args.out`` has been changed since MMSeg '
'v0.16, the pickled outputs could be seg map as type of '
'np.array, pre-eval results or file paths for '
'``dataset.format_results()``.')
print(f'\nwriting results to {args.out}')
mmcv.dump(results, args.out)
if args.eval:
eval_kwargs.update(metric=args.eval)
metric = dataset.evaluate(results, **eval_kwargs)
metric_dict = dict(config=args.config, metric=metric)
if args.work_dir is not None and rank == 0:
mmcv.dump(metric_dict, json_file, indent=4)
if tmpdir is not None and eval_on_format_results:
# remove tmp dir when cityscapes evaluation
shutil.rmtree(tmpdir)
# mean_IU, IU_array = model1.evalute_model(model1.student, valloader, gpu_id='0', input_size='512,512', num_classes=19, whole=True)
# print('mean_IU:', mean_IU)
# print('IU_array:', IU_array)
## mmseg
checkpoint = load_checkpoint(model1.student, pretrain_model_1)
# model = model1.student
S_config = 'configs/pspnet/pspnet_r18-d8_512x512_40k_cityscapes_1gpu.py'
S_cfg = Config.fromfile(S_config)
dataset = build_dataset(S_cfg.data.train)
# dataset = build_dataset(S_cfg.data.test)
data_loader = build_dataloader(
dataset,
samples_per_gpu=1,
workers_per_gpu=1,
# workers_per_gpu=S_cfg.data.workers_per_gpu,
dist=False,
shuffle=False)
# model.CLASSES = checkpoint['meta']['CLASSES']
# model.PALETTE = checkpoint['meta']['PALETTE']
# distributed = False
# if not distributed:
# model = MMDataParallel(model, device_ids=[0])
# # outputs = single_gpu_test(model, data_loader, args.show, args.show_dir)
# outputs = single_gpu_test(model, data_loader, show=False, out_dir=None)
# else:
# model = MMDistributedDataParallel(
# model.cuda(),
# device_ids=[torch.cuda.current_device()],
def main():
args = parse_args()
assert args.out or args.eval or args.format_only or args.show \
or args.show_dir, \
('Please specify at least one operation (save/eval/format/show the '
'results / save the results) with the argument "--out", "--eval"'
', "--format-only", "--show" or "--show-dir"')
if args.eval and args.format_only:
raise ValueError('--eval and --format_only cannot be both specified')
if args.out is not None and not args.out.endswith(('.pkl', '.pickle')):
raise ValueError('The output file must be a pkl file.')
cfg = mmcv.Config.fromfile(args.config)
if args.cfg_options is not None:
cfg.merge_from_dict(args.cfg_options)
# set multi-process settings
setup_multi_processes(cfg)
# set cudnn_benchmark
if cfg.get('cudnn_benchmark', False):
torch.backends.cudnn.benchmark = True
if args.aug_test:
# hard code index
cfg.data.test.pipeline[1].img_ratios = [
0.5, 0.75, 1.0, 1.25, 1.5, 1.75
]
cfg.data.test.pipeline[1].flip = True
cfg.model.pretrained = None
cfg.data.test.test_mode = True
if args.gpu_id is not None:
cfg.gpu_ids = [args.gpu_id]
# init distributed env first, since logger depends on the dist info.
if args.launcher == 'none':
cfg.gpu_ids = [args.gpu_id]
distributed = False
if len(cfg.gpu_ids) > 1:
warnings.warn(f'The gpu-ids is reset from {cfg.gpu_ids} to '
f'{cfg.gpu_ids[0:1]} to avoid potential error in '
'non-distribute testing time.')
cfg.gpu_ids = cfg.gpu_ids[0:1]
else:
distributed = True
init_dist(args.launcher, **cfg.dist_params)
rank, _ = get_dist_info()
# allows not to create
if args.work_dir is not None and rank == 0:
mmcv.mkdir_or_exist(osp.abspath(args.work_dir))
timestamp = time.strftime('%Y%m%d_%H%M%S', time.localtime())
if args.aug_test:
json_file = osp.join(args.work_dir,
f'eval_multi_scale_{timestamp}.json')
else:
json_file = osp.join(args.work_dir,
f'eval_single_scale_{timestamp}.json')
elif rank == 0:
work_dir = osp.join('./work_dirs',
osp.splitext(osp.basename(args.config))[0])
mmcv.mkdir_or_exist(osp.abspath(work_dir))
timestamp = time.strftime('%Y%m%d_%H%M%S', time.localtime())
if args.aug_test:
json_file = osp.join(work_dir,
f'eval_multi_scale_{timestamp}.json')
else:
json_file = osp.join(work_dir,
f'eval_single_scale_{timestamp}.json')
# build the dataloader
# TODO: support multiple images per gpu (only minor changes are needed)
dataset = build_dataset(cfg.data.test)
# The default loader config
loader_cfg = dict(
# cfg.gpus will be ignored if distributed
num_gpus=len(cfg.gpu_ids),
dist=distributed,
shuffle=False)
# The overall dataloader settings
loader_cfg.update({
k: v
for k, v in cfg.data.items() if k not in [
'train', 'val', 'test', 'train_dataloader', 'val_dataloader',
'test_dataloader'
]
})
test_loader_cfg = {
**loader_cfg,
'samples_per_gpu': 1,
'shuffle': False, # Not shuffle by default
**cfg.data.get('test_dataloader', {})
}
# build the dataloader
data_loader = build_dataloader(dataset, **test_loader_cfg)
# build the model and load checkpoint
cfg.model.train_cfg = None
model = build_segmentor(cfg.model, test_cfg=cfg.get('test_cfg'))
fp16_cfg = cfg.get('fp16', None)
if fp16_cfg is not None:
wrap_fp16_model(model)
checkpoint = load_checkpoint(model, args.checkpoint, map_location='cpu')
if 'CLASSES' in checkpoint.get('meta', {}):
model.CLASSES = checkpoint['meta']['CLASSES']
else:
print('"CLASSES" not found in meta, use dataset.CLASSES instead')
model.CLASSES = dataset.CLASSES
if 'PALETTE' in checkpoint.get('meta', {}):
model.PALETTE = checkpoint['meta']['PALETTE']
else:
print('"PALETTE" not found in meta, use dataset.PALETTE instead')
model.PALETTE = dataset.PALETTE
# clean gpu memory when starting a new evaluation.
torch.cuda.empty_cache()
eval_kwargs = {} if args.eval_options is None else args.eval_options
# Deprecated
efficient_test = eval_kwargs.get('efficient_test', False)
if efficient_test:
warnings.warn(
'``efficient_test=True`` does not have effect in tools/test.py, '
'the evaluation and format results are CPU memory efficient by '
'default')
eval_on_format_results = (args.eval is not None
and 'cityscapes' in args.eval)
if eval_on_format_results:
assert len(args.eval) == 1, 'eval on format results is not ' \
'applicable for metrics other than ' \
'cityscapes'
if args.format_only or eval_on_format_results:
if 'imgfile_prefix' in eval_kwargs:
tmpdir = eval_kwargs['imgfile_prefix']
else:
tmpdir = '.format_cityscapes'
eval_kwargs.setdefault('imgfile_prefix', tmpdir)
mmcv.mkdir_or_exist(tmpdir)
else:
tmpdir = None
if not distributed:
warnings.warn(
'SyncBN is only supported with DDP. To be compatible with DP, '
'we convert SyncBN to BN. Please use dist_train.sh which can '
'avoid this error.')
if not torch.cuda.is_available():
assert digit_version(mmcv.__version__) >= digit_version('1.4.4'), \
'Please use MMCV >= 1.4.4 for CPU training!'
model = revert_sync_batchnorm(model)
model = MMDataParallel(model, device_ids=cfg.gpu_ids)
results = single_gpu_test(model,
data_loader,
args.show,
args.show_dir,
False,
args.opacity,
pre_eval=args.eval is not None
and not eval_on_format_results,
format_only=args.format_only
or eval_on_format_results,
format_args=eval_kwargs)
else:
model = MMDistributedDataParallel(
model.cuda(),
device_ids=[torch.cuda.current_device()],
broadcast_buffers=False)
results = multi_gpu_test(model,
data_loader,
args.tmpdir,
args.gpu_collect,
False,
pre_eval=args.eval is not None
and not eval_on_format_results,
format_only=args.format_only
or eval_on_format_results,
format_args=eval_kwargs)
rank, _ = get_dist_info()
if rank == 0:
if args.out:
warnings.warn(
'The behavior of ``args.out`` has been changed since MMSeg '
'v0.16, the pickled outputs could be seg map as type of '
'np.array, pre-eval results or file paths for '
'``dataset.format_results()``.')
print(f'\nwriting results to {args.out}')
mmcv.dump(results, args.out)
if args.eval:
eval_kwargs.update(metric=args.eval)
metric = dataset.evaluate(results, **eval_kwargs)
metric_dict = dict(config=args.config, metric=metric)
mmcv.dump(metric_dict, json_file, indent=4)
if tmpdir is not None and eval_on_format_results:
# remove tmp dir when cityscapes evaluation
shutil.rmtree(tmpdir)
def main():
args = parse_args()
assert args.out or args.eval or args.format_only or args.show \
or args.show_dir, \
('Please specify at least one operation (save/eval/format/show the '
'results / save the results) with the argument "--out", "--eval"'
', "--format-only", "--show" or "--show-dir"')
if args.eval and args.format_only:
raise ValueError('--eval and --format_only cannot be both specified')
if args.out is not None and not args.out.endswith(('.pkl', '.pickle')):
raise ValueError('The output file must be a pkl file.')
cfg = mmcv.Config.fromfile(args.config)
if args.options is not None:
cfg.merge_from_dict(args.options)
# set cudnn_benchmark
if cfg.get('cudnn_benchmark', False):
torch.backends.cudnn.benchmark = True
if args.aug_test:
# hard code index
cfg.data.test.pipeline[1].img_ratios = [
0.5, 0.75, 1.0, 1.25, 1.5, 1.75
]
cfg.data.test.pipeline[1].flip = True
cfg.model.pretrained = None
cfg.data.test.test_mode = True
# init distributed env first, since logger depends on the dist info.
if args.launcher == 'none':
distributed = False
else:
distributed = True
init_dist(args.launcher, **cfg.dist_params)
# build the dataloader
# TODO: support multiple images per gpu (only minor changes are needed)
dataset = build_dataset(cfg.data.test)
data_loader = build_dataloader(dataset,
samples_per_gpu=1,
workers_per_gpu=cfg.data.workers_per_gpu,
dist=distributed,
shuffle=False)
# build the model and load checkpoint
cfg.model.train_cfg = None
model = build_segmentor(cfg.model, test_cfg=cfg.get('test_cfg'))
checkpoint = load_checkpoint(model, args.checkpoint, map_location='cpu')
model.CLASSES = checkpoint['meta']['CLASSES']
model.PALETTE = checkpoint['meta']['PALETTE']
efficient_test = False
if args.eval_options is not None:
efficient_test = args.eval_options.get('efficient_test', False)
if not distributed:
#for concatenated (multi) image input.
model = MMDataParallel(model, device_ids=[0])
outputs = single_gpu_test_multi(model, data_loader, args.show,
args.show_dir, args.show_original_dir,
efficient_test)
else:
#currently did not support for multi image
model = MMDistributedDataParallel(
model.cuda(),
device_ids=[torch.cuda.current_device()],
broadcast_buffers=False)
outputs = multi_gpu_test(model, data_loader, args.tmpdir,
args.gpu_collect, efficient_test)
rank, _ = get_dist_info()
if rank == 0:
if args.out:
print(f'\nwriting results to {args.out}')
mmcv.dump(outputs, args.out)
kwargs = {} if args.eval_options is None else args.eval_options
if args.format_only:
dataset.format_results(outputs, **kwargs)
if args.eval:
dataset.evaluate(outputs, args.eval, **kwargs)
def main():
args = parse_args()
assert args.out or args.eval or args.format_only or args.show \
or args.show_dir, \
('Please specify at least one operation (save/eval/format/show the '
'results / save the results) with the argument "--out", "--eval"'
', "--format-only", "--show" or "--show-dir"')
if args.eval and args.format_only:
raise ValueError('--eval and --format_only cannot be both specified')
if args.out is not None and not args.out.endswith(('.pkl', '.pickle')):
raise ValueError('The output file must be a pkl file.')
cfg = mmcv.Config.fromfile(args.config)
# work_dir is determined in this priority: CLI > segment in file > filename
if args.work_dir is not None:
# update configs according to CLI args if args.work_dir is not None
cfg.work_dir = args.work_dir
elif cfg.get('work_dir', None) is None:
# use config filename as default work_dir if cfg.work_dir is None
cfg.work_dir = osp.join('./work_dirs',
osp.splitext(osp.basename(args.config))[0])
if args.options is not None:
cfg.merge_from_dict(args.options)
# set cudnn_benchmark
if cfg.get('cudnn_benchmark', False):
torch.backends.cudnn.benchmark = True
if args.aug_test:
# hard code index
cfg.data.test.pipeline[1].img_ratios = [
0.5, 0.75, 1.0, 1.25, 1.5, 1.75
]
cfg.data.test.pipeline[1].flip = True
cfg.model.pretrained = None
cfg.data.test.test_mode = True
# init distributed env first, since logger depends on the dist info.
if args.launcher == 'none':
distributed = False
else:
distributed = True
init_dist(args.launcher, **cfg.dist_params)
# init the logger before other steps
logger = None
if args.eval:
timestamp = time.strftime('%Y%m%d_%H%M%S', time.localtime())
log_file = osp.join(cfg.work_dir, f'test_{timestamp}.log')
logger = get_root_logger(log_file=log_file, log_level=cfg.log_level)
# set random seeds
if args.seed is not None:
set_random_seed(args.seed, deterministic=args.deterministic)
if logger is not None:
logger.info(f'Set random seed to {args.seed}, deterministic: '
f'{args.deterministic}')
else:
print(f'Set random seed to {args.seed}, deterministic: '
f'{args.deterministic}')
# build the dataloader
# TODO: support multiple images per gpu (only minor changes are needed)
dataset = build_dataset(cfg.data.val, dict(test_mode=True))
data_loader = build_dataloader(
dataset,
samples_per_gpu=1,
workers_per_gpu=cfg.data.workers_per_gpu,
dist=distributed,
shuffle=False)
# build the model and load checkpoint
model = build_segmentor(cfg.model, train_cfg=None, test_cfg=cfg.test_cfg)
checkpoint = load_checkpoint(model, args.checkpoint, map_location='cpu')
model.CLASSES = checkpoint['meta']['CLASSES']
model.PALETTE = checkpoint['meta']['PALETTE']
if not distributed:
model = MMDataParallel(model, device_ids=[0])
outputs = single_gpu_test(model, data_loader, args.show, args.show_dir)
else:
model = MMDistributedDataParallel(
model.cuda(),
device_ids=[torch.cuda.current_device()],
broadcast_buffers=False)
outputs = multi_gpu_test(model, data_loader, args.tmpdir,
args.gpu_collect)
rank, _ = get_dist_info()
if rank == 0:
if args.out:
print(f'\nwriting results to {args.out}')
mmcv.dump(outputs, args.out)
kwargs = {} if args.eval_options is None else args.eval_options
if args.format_only:
dataset.format_results(outputs, **kwargs)
if args.eval:
dataset.evaluate(outputs, args.eval, logger, **kwargs)
def train_segmentor(model,
dataset,
cfg,
distributed=False,
validate=False,
timestamp=None,
meta=None):
"""Launch segmentor training."""
logger = get_root_logger(cfg.log_level)
# prepare data loaders
dataset = dataset if isinstance(dataset, (list, tuple)) else [dataset]
data_loaders = [
build_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_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 = DistEvalHook if distributed else 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_segmentor(model,
dataset,
cfg,
distributed=False,
validate=False,
timestamp=None,
meta=None):
"""Launch segmentor training."""
logger = get_root_logger(cfg.log_level)
# prepare data loaders
dataset = dataset if isinstance(dataset, (list, tuple)) else [dataset]
data_loaders = [
build_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', True)
# 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)
# model.ddp = model
else:
model = MMDataParallel(model.cuda(cfg.gpu_ids[0]),
device_ids=cfg.gpu_ids)
# print(model)
# 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))
# print(cfg.optimizer)
# print(cfg.optimizer_config)
optimizer_config = OptimizerHookLW(**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))
# 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_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 = DistEvalHook if distributed else EvalHook
runner.register_hook(eval_hook(val_dataloader, **eval_cfg))
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_segmentor(model,
dataset,
cfg,
distributed=False,
validate=False,
timestamp=None,
meta=None):
"""Launch segmentor training."""
logger = get_root_logger(cfg.log_level)
# prepare data loaders
dataset = dataset if isinstance(dataset, (list, tuple)) else [dataset]
# The default loader config
loader_cfg = dict(
# cfg.gpus will be ignored if distributed
num_gpus=len(cfg.gpu_ids),
dist=distributed,
seed=cfg.seed,
drop_last=True)
# The overall dataloader settings
loader_cfg.update({
k: v
for k, v in cfg.data.items() if k not in [
'train', 'val', 'test', 'train_dataloader', 'val_dataloader',
'test_dataloader'
]
})
# The specific dataloader settings
train_loader_cfg = {**loader_cfg, **cfg.data.get('train_dataloader', {})}
data_loaders = [build_dataloader(ds, **train_loader_cfg) 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:
if not torch.cuda.is_available():
assert digit_version(mmcv.__version__) >= digit_version('1.4.4'), \
'Please use MMCV >= 1.4.4 for CPU training!'
model = MMDataParallel(model, 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))
if distributed:
# when distributed training by epoch, using`DistSamplerSeedHook` to set
# the different seed to distributed sampler for each epoch, it will
# shuffle dataset at each epoch and avoid overfitting.
if isinstance(runner, EpochBasedRunner):
runner.register_hook(DistSamplerSeedHook())
# 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))
# The specific dataloader settings
val_loader_cfg = {
**loader_cfg,
'samples_per_gpu': 1,
'shuffle': False, # Not shuffle by default
**cfg.data.get('val_dataloader', {}),
}
val_dataloader = build_dataloader(val_dataset, **val_loader_cfg)
eval_cfg = cfg.get('evaluation', {})
eval_cfg['by_epoch'] = cfg.runner['type'] != 'IterBasedRunner'
eval_hook = DistEvalHook if distributed else 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 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)