Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[Enhance] Add extra dataloader settings in configs #141

Merged
merged 1 commit into from
Apr 13, 2022
Merged

[Enhance] Add extra dataloader settings in configs #141

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
56 changes: 28 additions & 28 deletions mmrazor/apis/mmcls/train.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -65,36 +65,36 @@ def train_mmcls_model(model,
train_dataset = dataset[0]
dataset[0] = split_dataset(train_dataset)

sampler_cfg = cfg.data.get('sampler', None)
loader_cfg = dict(
# cfg.gpus will be ignored if distributed
num_gpus=len(cfg.gpu_ids),
dist=distributed,
round_up=True,
seed=cfg.get('seed'),
sampler_cfg=cfg.get('sampler', None),
)
# 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', {})}

# Difference from mmclassification.
# Build multi dataloaders according the splited datasets.
data_loaders = list()
for dset in dataset:
if isinstance(dset, list):
data_loader = [
build_dataloader(
item_ds,
cfg.data.samples_per_gpu,
cfg.data.workers_per_gpu,
# cfg.gpus will be ignored if distributed
num_gpus=len(cfg.gpu_ids),
dist=distributed,
round_up=True,
seed=cfg.seed,
sampler_cfg=sampler_cfg) for item_ds in dset
build_dataloader(item_ds, **train_loader_cfg)
for item_ds in dset
]
else:
data_loader = build_dataloader(
dset,
cfg.data.samples_per_gpu,
cfg.data.workers_per_gpu,
# cfg.gpus will be ignored if distributed
num_gpus=len(cfg.gpu_ids),
dist=distributed,
round_up=True,
seed=cfg.seed,
sampler_cfg=sampler_cfg)
data_loader = build_dataloader(dset, **train_loader_cfg)

data_loaders.append(data_loader)

Expand Down Expand Up @@ -188,13 +188,13 @@ def train_mmcls_model(model,
# 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=cfg.data.samples_per_gpu,
workers_per_gpu=cfg.data.workers_per_gpu,
dist=distributed,
shuffle=False,
round_up=True)
val_loader_cfg = {
**loader_cfg,
'shuffle': False, # Not shuffle by default
'sampler_cfg': None, # Not use sampler 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'
Expand Down
44 changes: 27 additions & 17 deletions mmrazor/apis/mmseg/train.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -57,17 +57,25 @@ def train_mmseg_model(model,

# 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
]
# 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:
Expand Down Expand Up @@ -130,12 +138,14 @@ def train_mmseg_model(model,
# 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)
# 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
Expand Down
33 changes: 25 additions & 8 deletions tools/mmcls/test_mmcls.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -120,15 +120,32 @@ def main():
init_dist(args.launcher, **cfg.dist_params)

# build the dataloader
dataset = build_dataset(cfg.data.test)
# the extra round_up data will be removed during gpu/cpu collect
data_loader = build_dataloader(
dataset,
samples_per_gpu=cfg.data.samples_per_gpu,
workers_per_gpu=cfg.data.workers_per_gpu,
dataset = build_dataset(cfg.data.test, default_args=dict(test_mode=True))

# build the dataloader
# The default loader config
loader_cfg = dict(
# cfg.gpus will be ignored if distributed
num_gpus=len(cfg.gpu_ids),
dist=distributed,
shuffle=False,
round_up=True)
round_up=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'
]
})
test_loader_cfg = {
**loader_cfg,
'shuffle': False, # Not shuffle by default
'sampler_cfg': None, # Not use sampler by default
**cfg.data.get('test_dataloader', {}),
}
# the extra round_up data will be removed during gpu/cpu collect
data_loader = build_dataloader(dataset, **test_loader_cfg)

# build the algorithm and load checkpoint
algorithm = build_algorithm(cfg.algorithm)
Expand Down
24 changes: 20 additions & 4 deletions tools/mmseg/test_mmseg.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -154,12 +154,28 @@ def main():
# 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,
# 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 algorithm and load checkpoint
# Difference from mmsegmentation
Expand Down