Python mmcv.parallel.scatter() Examples
The following are 30
code examples of mmcv.parallel.scatter().
You can vote up the ones you like or vote down the ones you don't like,
and go to the original project or source file by following the links above each example.
You may also want to check out all available functions/classes of the module
mmcv.parallel
, or try the search function
.
.
Example #1
| Source File: inference.py From mmfashion with Apache License 2.0 | 7 votes |
|
def inference_detector(model, img):
"""Inference image(s) with the detector.
Args:
model (nn.Module): The loaded detector.
imgs (str/ndarray or list[str/ndarray]): Either image files or loaded
images.
Returns:
If imgs is a str, a generator will be returned, otherwise return the
detection results directly.
"""
cfg = model.cfg
device = next(model.parameters()).device # model device
# build the data pipeline
test_pipeline = [LoadImage()] + cfg.data.test.pipeline[1:]
test_pipeline = Compose(test_pipeline)
# prepare data
data = dict(img=img)
data = test_pipeline(data)
data = scatter(collate([data], samples_per_gpu=1), [device])[0]
# forward the model
with torch.no_grad():
result = model(return_loss=False, rescale=True, **data)
return result
Example #2
| Source File: eval_hooks.py From hrnet with MIT License | 5 votes |
|
def after_train_epoch(self, runner):
if not self.every_n_epochs(runner, self.interval):
return
runner.model.eval()
results = [None for _ in range(len(self.dataset))]
if runner.rank == 0:
prog_bar = mmcv.ProgressBar(len(self.dataset))
for idx in range(runner.rank, len(self.dataset), runner.world_size):
data = self.dataset[idx]
data_gpu = scatter(
collate([data], samples_per_gpu=1),
[torch.cuda.current_device()])[0]
# compute output
with torch.no_grad():
result = runner.model(
return_loss=False, rescale=True, **data_gpu)
results[idx] = result
batch_size = runner.world_size
if runner.rank == 0:
for _ in range(batch_size):
prog_bar.update()
if runner.rank == 0:
print('\n')
dist.barrier()
for i in range(1, runner.world_size):
tmp_file = osp.join(runner.work_dir, 'temp_{}.pkl'.format(i))
tmp_results = mmcv.load(tmp_file)
for idx in range(i, len(results), runner.world_size):
results[idx] = tmp_results[idx]
os.remove(tmp_file)
self.evaluate(runner, results)
else:
tmp_file = osp.join(runner.work_dir,
'temp_{}.pkl'.format(runner.rank))
mmcv.dump(results, tmp_file)
dist.barrier()
dist.barrier()
Example #3
| Source File: inference.py From mmdetection with Apache License 2.0 | 5 votes |
|
def inference_detector(model, img):
"""Inference image(s) with the detector.
Args:
model (nn.Module): The loaded detector.
imgs (str/ndarray or list[str/ndarray]): Either image files or loaded
images.
Returns:
If imgs is a str, a generator will be returned, otherwise return the
detection results directly.
"""
cfg = model.cfg
device = next(model.parameters()).device # model device
# build the data pipeline
test_pipeline = [LoadImage()] + cfg.data.test.pipeline[1:]
test_pipeline = Compose(test_pipeline)
# prepare data
data = dict(img=img)
data = test_pipeline(data)
data = collate([data], samples_per_gpu=1)
if next(model.parameters()).is_cuda:
# scatter to specified GPU
data = scatter(data, [device])[0]
else:
# Use torchvision ops for CPU mode instead
for m in model.modules():
if isinstance(m, (RoIPool, RoIAlign)):
if not m.aligned:
# aligned=False is not implemented on CPU
# set use_torchvision on-the-fly
m.use_torchvision = True
warnings.warn('We set use_torchvision=True in CPU mode.')
# just get the actual data from DataContainer
data['img_metas'] = data['img_metas'][0].data
# forward the model
with torch.no_grad():
result = model(return_loss=False, rescale=True, **data)
return result
Example #4
| Source File: test.py From FNA with Apache License 2.0 | 5 votes |
|
def _data_func(data, device_id):
data = scatter(collate([data], samples_per_gpu=1), [device_id])[0]
return dict(return_loss=False, rescale=True, **data)
Example #5
| Source File: inference.py From Cascade-RPN with Apache License 2.0 | 5 votes |
|
def inference_detector(model, img):
"""Inference image(s) with the detector.
Args:
model (nn.Module): The loaded detector.
imgs (str/ndarray or list[str/ndarray]): Either image files or loaded
images.
Returns:
If imgs is a str, a generator will be returned, otherwise return the
detection results directly.
"""
cfg = model.cfg
device = next(model.parameters()).device # model device
# build the data pipeline
test_pipeline = [LoadImage()] + cfg.data.test.pipeline[1:]
test_pipeline = Compose(test_pipeline)
# prepare data
data = dict(img=img)
data = test_pipeline(data)
data = scatter(collate([data], samples_per_gpu=1), [device])[0]
# forward the model
with torch.no_grad():
result = model(return_loss=False, rescale=True, **data)
return result
# TODO: merge this method with the one in BaseDetector
Example #6
| Source File: eval_hooks.py From Cascade-RPN with Apache License 2.0 | 5 votes |
|
def after_train_epoch(self, runner):
if not self.every_n_epochs(runner, self.interval):
return
runner.model.eval()
results = [None for _ in range(len(self.dataset))]
if runner.rank == 0:
prog_bar = mmcv.ProgressBar(len(self.dataset))
for idx in range(runner.rank, len(self.dataset), runner.world_size):
data = self.dataset[idx]
data_gpu = scatter(
collate([data], samples_per_gpu=1),
[torch.cuda.current_device()])[0]
# compute output
with torch.no_grad():
result = runner.model(
return_loss=False, rescale=True, **data_gpu)
results[idx] = result
batch_size = runner.world_size
if runner.rank == 0:
for _ in range(batch_size):
prog_bar.update()
if runner.rank == 0:
print('\n')
dist.barrier()
for i in range(1, runner.world_size):
tmp_file = osp.join(runner.work_dir, 'temp_{}.pkl'.format(i))
tmp_results = mmcv.load(tmp_file)
for idx in range(i, len(results), runner.world_size):
results[idx] = tmp_results[idx]
os.remove(tmp_file)
self.evaluate(runner, results)
else:
tmp_file = osp.join(runner.work_dir,
'temp_{}.pkl'.format(runner.rank))
mmcv.dump(results, tmp_file)
dist.barrier()
dist.barrier()
Example #7
| Source File: inference.py From Feature-Selective-Anchor-Free-Module-for-Single-Shot-Object-Detection with Apache License 2.0 | 5 votes |
|
def inference_detector(model, img):
"""Inference image(s) with the detector.
Args:
model (nn.Module): The loaded detector.
imgs (str/ndarray or list[str/ndarray]): Either image files or loaded
images.
Returns:
If imgs is a str, a generator will be returned, otherwise return the
detection results directly.
"""
cfg = model.cfg
device = next(model.parameters()).device # model device
# build the data pipeline
test_pipeline = [LoadImage()] + cfg.data.test.pipeline[1:]
test_pipeline = Compose(test_pipeline)
# prepare data
data = dict(img=img)
data = test_pipeline(data)
data = scatter(collate([data], samples_per_gpu=1), [device])[0]
# forward the model
with torch.no_grad():
result = model(return_loss=False, rescale=True, **data)
return result
# TODO: merge this method with the one in BaseDetector
Example #8
| Source File: eval_hooks.py From Feature-Selective-Anchor-Free-Module-for-Single-Shot-Object-Detection with Apache License 2.0 | 5 votes |
|
def after_train_epoch(self, runner):
if not self.every_n_epochs(runner, self.interval):
return
runner.model.eval()
results = [None for _ in range(len(self.dataset))]
if runner.rank == 0:
prog_bar = mmcv.ProgressBar(len(self.dataset))
for idx in range(runner.rank, len(self.dataset), runner.world_size):
data = self.dataset[idx]
data_gpu = scatter(
collate([data], samples_per_gpu=1),
[torch.cuda.current_device()])[0]
# compute output
with torch.no_grad():
result = runner.model(
return_loss=False, rescale=True, **data_gpu)
results[idx] = result
batch_size = runner.world_size
if runner.rank == 0:
for _ in range(batch_size):
prog_bar.update()
if runner.rank == 0:
print('\n')
dist.barrier()
for i in range(1, runner.world_size):
tmp_file = osp.join(runner.work_dir, 'temp_{}.pkl'.format(i))
tmp_results = mmcv.load(tmp_file)
for idx in range(i, len(results), runner.world_size):
results[idx] = tmp_results[idx]
os.remove(tmp_file)
self.evaluate(runner, results)
else:
tmp_file = osp.join(runner.work_dir,
'temp_{}.pkl'.format(runner.rank))
mmcv.dump(results, tmp_file)
dist.barrier()
dist.barrier()
Example #9
| Source File: eval_hooks.py From kaggle-imaterialist with MIT License | 5 votes |
|
def after_train_epoch(self, runner):
if not self.every_n_epochs(runner, self.interval):
return
runner.model.eval()
results = [None for _ in range(len(self.dataset))]
if runner.rank == 0:
prog_bar = mmcv.ProgressBar(len(self.dataset))
for idx in range(runner.rank, len(self.dataset), runner.world_size):
data = self.dataset[idx]
data_gpu = scatter(
collate([data], samples_per_gpu=1),
[torch.cuda.current_device()])[0]
# compute output
with torch.no_grad():
result = runner.model(
return_loss=False, rescale=True, **data_gpu)
results[idx] = result
batch_size = runner.world_size
if runner.rank == 0:
for _ in range(batch_size):
prog_bar.update()
if runner.rank == 0:
print('\n')
dist.barrier()
for i in range(1, runner.world_size):
tmp_file = osp.join(runner.work_dir, 'temp_{}.pkl'.format(i))
tmp_results = mmcv.load(tmp_file)
for idx in range(i, len(results), runner.world_size):
results[idx] = tmp_results[idx]
os.remove(tmp_file)
self.evaluate(runner, results)
else:
tmp_file = osp.join(runner.work_dir,
'temp_{}.pkl'.format(runner.rank))
mmcv.dump(results, tmp_file)
dist.barrier()
dist.barrier()
Example #10
| Source File: eval_hooks.py From mmaction with Apache License 2.0 | 5 votes |
|
def after_train_epoch(self, runner):
if not self.every_n_epochs(runner, self.interval):
return
runner.model.eval()
results = [None for _ in range(len(self.dataset))]
if runner.rank == 0:
prog_bar = mmcv.ProgressBar(len(self.dataset))
for idx in range(runner.rank, len(self.dataset), runner.world_size):
data = self.dataset[idx]
data_gpu = scatter(
collate([data], samples_per_gpu=1),
[torch.cuda.current_device()])[0]
# compute output
with torch.no_grad():
result = runner.model(
return_loss=False, rescale=True, **data_gpu)
results[idx] = result
batch_size = runner.world_size
if runner.rank == 0:
for _ in range(batch_size):
prog_bar.update()
if runner.rank == 0:
print('\n')
dist.barrier()
for i in range(1, runner.world_size):
tmp_file = osp.join(runner.work_dir, 'temp_{}.pkl'.format(i))
tmp_results = mmcv.load(tmp_file)
for idx in range(i, len(results), runner.world_size):
results[idx] = tmp_results[idx]
os.remove(tmp_file)
self.evaluate(runner, results)
else:
tmp_file = osp.join(runner.work_dir,
'temp_{}.pkl'.format(runner.rank))
mmcv.dump(results, tmp_file)
dist.barrier()
dist.barrier()
Example #11
| Source File: test_detector.py From mmaction with Apache License 2.0 | 5 votes |
|
def _data_func(data, device_id):
data = scatter(collate([data], samples_per_gpu=1), [device_id])[0]
return dict(return_loss=False, rescale=True, **data)
Example #12
| Source File: eval_hooks.py From FoveaBox with Apache License 2.0 | 5 votes |
|
def after_train_epoch(self, runner):
if not self.every_n_epochs(runner, self.interval):
return
runner.model.eval()
results = [None for _ in range(len(self.dataset))]
if runner.rank == 0:
prog_bar = mmcv.ProgressBar(len(self.dataset))
for idx in range(runner.rank, len(self.dataset), runner.world_size):
data = self.dataset[idx]
data_gpu = scatter(
collate([data], samples_per_gpu=1),
[torch.cuda.current_device()])[0]
# compute output
with torch.no_grad():
result = runner.model(
return_loss=False, rescale=True, **data_gpu)
results[idx] = result
batch_size = runner.world_size
if runner.rank == 0:
for _ in range(batch_size):
prog_bar.update()
if runner.rank == 0:
print('\n')
dist.barrier()
for i in range(1, runner.world_size):
tmp_file = osp.join(runner.work_dir, 'temp_{}.pkl'.format(i))
tmp_results = mmcv.load(tmp_file)
for idx in range(i, len(results), runner.world_size):
results[idx] = tmp_results[idx]
os.remove(tmp_file)
self.evaluate(runner, results)
else:
tmp_file = osp.join(runner.work_dir,
'temp_{}.pkl'.format(runner.rank))
mmcv.dump(results, tmp_file)
dist.barrier()
dist.barrier()
Example #13
| Source File: test.py From hrnet with MIT License | 5 votes |
|
def _data_func(data, device_id):
data = scatter(collate([data], samples_per_gpu=1), [device_id])[0]
return dict(return_loss=False, rescale=True, **data)
Example #14
| Source File: eval_hooks.py From CenterNet with Apache License 2.0 | 5 votes |
|
def after_train_epoch(self, runner):
if not self.every_n_epochs(runner, self.interval):
return
runner.model.eval()
results = [None for _ in range(len(self.dataset))]
if runner.rank == 0:
prog_bar = mmcv.ProgressBar(len(self.dataset))
for idx in range(runner.rank, len(self.dataset), runner.world_size):
data = self.dataset[idx]
data_gpu = scatter(
collate([data], samples_per_gpu=1),
[torch.cuda.current_device()])[0]
# compute output
with torch.no_grad():
result = runner.model(
return_loss=False, rescale=True, **data_gpu)
results[idx] = result
batch_size = runner.world_size
if runner.rank == 0:
for _ in range(batch_size):
prog_bar.update()
if runner.rank == 0:
print('\n')
dist.barrier()
for i in range(1, runner.world_size):
tmp_file = osp.join(runner.work_dir, 'temp_{}.pkl'.format(i))
tmp_results = mmcv.load(tmp_file)
for idx in range(i, len(results), runner.world_size):
results[idx] = tmp_results[idx]
os.remove(tmp_file)
self.evaluate(runner, results)
else:
tmp_file = osp.join(runner.work_dir,
'temp_{}.pkl'.format(runner.rank))
mmcv.dump(results, tmp_file)
dist.barrier()
dist.barrier()
Example #15
| Source File: inference.py From ttfnet with Apache License 2.0 | 5 votes |
|
def inference_detector(model, img):
"""Inference image(s) with the detector.
Args:
model (nn.Module): The loaded detector.
imgs (str/ndarray or list[str/ndarray]): Either image files or loaded
images.
Returns:
If imgs is a str, a generator will be returned, otherwise return the
detection results directly.
"""
cfg = model.cfg
device = next(model.parameters()).device # model device
# build the data pipeline
test_pipeline = [LoadImage()] + cfg.data.test.pipeline[1:]
test_pipeline = Compose(test_pipeline)
# prepare data
data = dict(img=img)
data = test_pipeline(data)
data = scatter(collate([data], samples_per_gpu=1), [device])[0]
# forward the model
with torch.no_grad():
result = model(return_loss=False, rescale=True, **data)
return result
# TODO: merge this method with the one in BaseDetector
Example #16
| Source File: eval_hooks.py From ttfnet with Apache License 2.0 | 5 votes |
|
def after_train_epoch(self, runner):
if not self.every_n_epochs(runner, self.interval):
return
runner.model.eval()
results = [None for _ in range(len(self.dataset))]
if runner.rank == 0:
prog_bar = mmcv.ProgressBar(len(self.dataset))
for idx in range(runner.rank, len(self.dataset), runner.world_size):
data = self.dataset[idx]
data_gpu = scatter(
collate([data], samples_per_gpu=1),
[torch.cuda.current_device()])[0]
# compute output
with torch.no_grad():
result = runner.model(
return_loss=False, rescale=True, **data_gpu)
results[idx] = result
batch_size = runner.world_size
if runner.rank == 0:
for _ in range(batch_size):
prog_bar.update()
if runner.rank == 0:
print('\n')
dist.barrier()
for i in range(1, runner.world_size):
tmp_file = osp.join(runner.work_dir, 'temp_{}.pkl'.format(i))
tmp_results = mmcv.load(tmp_file)
for idx in range(i, len(results), runner.world_size):
results[idx] = tmp_results[idx]
os.remove(tmp_file)
self.evaluate(runner, results)
else:
tmp_file = osp.join(runner.work_dir,
'temp_{}.pkl'.format(runner.rank))
mmcv.dump(results, tmp_file)
dist.barrier()
dist.barrier()
Example #17
| Source File: eval_hooks.py From AugFPN with Apache License 2.0 | 5 votes |
|
def after_train_epoch(self, runner):
if not self.every_n_epochs(runner, self.interval):
return
runner.model.eval()
results = [None for _ in range(len(self.dataset))]
prog_bar = mmcv.ProgressBar(len(self.dataset))
for idx in range(runner.rank, len(self.dataset), runner.world_size):
data = self.dataset[idx]
data_gpu = scatter(
collate([data], samples_per_gpu=1),
[torch.cuda.current_device()])[0]
# compute output
with torch.no_grad():
result = runner.model(
return_loss=False, rescale=True, **data_gpu)
results[idx] = result
batch_size = runner.world_size
for _ in range(batch_size):
prog_bar.update()
if runner.rank == 0:
print('\n')
self._barrier(runner.rank, runner.world_size)
for i in range(1, runner.world_size):
tmp_file = osp.join(runner.work_dir, 'temp_{}.pkl'.format(i))
tmp_results = mmcv.load(tmp_file)
for idx in range(i, len(results), runner.world_size):
results[idx] = tmp_results[idx]
os.remove(tmp_file)
self.evaluate(runner, results)
else:
tmp_file = osp.join(runner.work_dir,
'temp_{}.pkl'.format(runner.rank))
mmcv.dump(results, tmp_file)
self._barrier(runner.rank, runner.world_size)
self._barrier(runner.rank, runner.world_size)
Example #18
| Source File: test.py From AugFPN with Apache License 2.0 | 5 votes |
|
def _data_func(data, device_id):
data = scatter(collate([data], samples_per_gpu=1), [device_id])[0]
return dict(return_loss=False, rescale=True, **data)
Example #19
| Source File: slurm_test.py From AugFPN with Apache License 2.0 | 5 votes |
|
def _data_func(data, device_id):
data = scatter(collate([data], samples_per_gpu=1), [device_id])[0]
return dict(return_loss=False, rescale=True, **data)
Example #20
| Source File: eval_hooks.py From kaggle-kuzushiji-recognition with MIT License | 5 votes |
|
def after_train_epoch(self, runner):
if not self.every_n_epochs(runner, self.interval):
return
runner.model.eval()
results = [None for _ in range(len(self.dataset))]
if runner.rank == 0:
prog_bar = mmcv.ProgressBar(len(self.dataset))
for idx in range(runner.rank, len(self.dataset), runner.world_size):
data = self.dataset[idx]
data_gpu = scatter(
collate([data], samples_per_gpu=1),
[torch.cuda.current_device()])[0]
# compute output
with torch.no_grad():
result = runner.model(
return_loss=False, rescale=True, **data_gpu)
results[idx] = result
batch_size = runner.world_size
if runner.rank == 0:
for _ in range(batch_size):
prog_bar.update()
if runner.rank == 0:
print('\n')
dist.barrier()
for i in range(1, runner.world_size):
tmp_file = osp.join(runner.work_dir, 'temp_{}.pkl'.format(i))
tmp_results = mmcv.load(tmp_file)
for idx in range(i, len(results), runner.world_size):
results[idx] = tmp_results[idx]
os.remove(tmp_file)
self.evaluate(runner, results)
else:
tmp_file = osp.join(runner.work_dir,
'temp_{}.pkl'.format(runner.rank))
mmcv.dump(results, tmp_file)
dist.barrier()
dist.barrier()
Example #21
| Source File: inference.py From mmdetection with Apache License 2.0 | 5 votes |
|
def async_inference_detector(model, img):
"""Async inference image(s) with the detector.
Args:
model (nn.Module): The loaded detector.
imgs (str/ndarray or list[str/ndarray]): Either image files or loaded
images.
Returns:
Awaitable detection results.
"""
cfg = model.cfg
device = next(model.parameters()).device # model device
# build the data pipeline
test_pipeline = [LoadImage()] + cfg.data.test.pipeline[1:]
test_pipeline = Compose(test_pipeline)
# prepare data
data = dict(img=img)
data = test_pipeline(data)
data = scatter(collate([data], samples_per_gpu=1), [device])[0]
# We don't restore `torch.is_grad_enabled()` value during concurrent
# inference since execution can overlap
torch.set_grad_enabled(False)
result = await model.aforward_test(rescale=True, **data)
return result
Example #22
| Source File: eval_hooks.py From AerialDetection with Apache License 2.0 | 5 votes |
|
def after_train_epoch(self, runner):
if not self.every_n_epochs(runner, self.interval):
return
runner.model.eval()
results = [None for _ in range(len(self.dataset))]
if runner.rank == 0:
prog_bar = mmcv.ProgressBar(len(self.dataset))
for idx in range(runner.rank, len(self.dataset), runner.world_size):
data = self.dataset[idx]
data_gpu = scatter(
collate([data], samples_per_gpu=1),
[torch.cuda.current_device()])[0]
# compute output
with torch.no_grad():
result = runner.model(
return_loss=False, rescale=True, **data_gpu)
results[idx] = result
batch_size = runner.world_size
if runner.rank == 0:
for _ in range(batch_size):
prog_bar.update()
if runner.rank == 0:
print('\n')
dist.barrier()
for i in range(1, runner.world_size):
tmp_file = osp.join(runner.work_dir, 'temp_{}.pkl'.format(i))
tmp_results = mmcv.load(tmp_file)
for idx in range(i, len(results), runner.world_size):
results[idx] = tmp_results[idx]
os.remove(tmp_file)
self.evaluate(runner, results)
else:
tmp_file = osp.join(runner.work_dir,
'temp_{}.pkl'.format(runner.rank))
mmcv.dump(results, tmp_file)
dist.barrier()
dist.barrier()
Example #23
| Source File: eval_hooks.py From GCNet with Apache License 2.0 | 5 votes |
|
def after_train_epoch(self, runner):
if not self.every_n_epochs(runner, self.interval):
return
runner.model.eval()
results = [None for _ in range(len(self.dataset))]
if runner.rank == 0:
prog_bar = mmcv.ProgressBar(len(self.dataset))
for idx in range(runner.rank, len(self.dataset), runner.world_size):
data = self.dataset[idx]
data_gpu = scatter(
collate([data], samples_per_gpu=1),
[torch.cuda.current_device()])[0]
# compute output
with torch.no_grad():
result = runner.model(
return_loss=False, rescale=True, **data_gpu)
results[idx] = result
batch_size = runner.world_size
if runner.rank == 0:
for _ in range(batch_size):
prog_bar.update()
if runner.rank == 0:
print('\n')
dist.barrier()
for i in range(1, runner.world_size):
tmp_file = osp.join(runner.work_dir, 'temp_{}.pkl'.format(i))
tmp_results = mmcv.load(tmp_file)
for idx in range(i, len(results), runner.world_size):
results[idx] = tmp_results[idx]
os.remove(tmp_file)
self.evaluate(runner, results)
else:
tmp_file = osp.join(runner.work_dir,
'temp_{}.pkl'.format(runner.rank))
mmcv.dump(results, tmp_file)
dist.barrier()
dist.barrier()
Example #24
| Source File: eval_hooks.py From mmdetection-annotated with Apache License 2.0 | 5 votes |
|
def after_train_epoch(self, runner):
if not self.every_n_epochs(runner, self.interval):
return
runner.model.eval()
results = [None for _ in range(len(self.dataset))]
if runner.rank == 0:
prog_bar = mmcv.ProgressBar(len(self.dataset))
for idx in range(runner.rank, len(self.dataset), runner.world_size):
data = self.dataset[idx]
data_gpu = scatter(
collate([data], samples_per_gpu=1),
[torch.cuda.current_device()])[0]
# compute output
with torch.no_grad():
result = runner.model(
return_loss=False, rescale=True, **data_gpu)
results[idx] = result
batch_size = runner.world_size
if runner.rank == 0:
for _ in range(batch_size):
prog_bar.update()
if runner.rank == 0:
print('\n')
dist.barrier()
for i in range(1, runner.world_size):
tmp_file = osp.join(runner.work_dir, 'temp_{}.pkl'.format(i))
tmp_results = mmcv.load(tmp_file)
for idx in range(i, len(results), runner.world_size):
results[idx] = tmp_results[idx]
os.remove(tmp_file)
self.evaluate(runner, results)
else:
tmp_file = osp.join(runner.work_dir,
'temp_{}.pkl'.format(runner.rank))
mmcv.dump(results, tmp_file)
dist.barrier()
dist.barrier()
Example #25
| Source File: inference.py From mmfashion with Apache License 2.0 | 5 votes |
|
def async_inference_detector(model, img):
"""Async inference image(s) with the detector.
Args:
model (nn.Module): The loaded detector.
imgs (str/ndarray or list[str/ndarray]): Either image files or loaded
images.
Returns:
Awaitable detection results.
"""
cfg = model.cfg
device = next(model.parameters()).device # model device
# build the data pipeline
test_pipeline = [LoadImage()] + cfg.data.test.pipeline[1:]
test_pipeline = Compose(test_pipeline)
# prepare data
data = dict(img=img)
data = test_pipeline(data)
data = scatter(collate([data], samples_per_gpu=1), [device])[0]
# We don't restore `torch.is_grad_enabled()` value during concurrent
# inference since execution can overlap
torch.set_grad_enabled(False)
result = await model.aforward_test(rescale=True, **data)
return result
# TODO: merge this method with the one in BaseDetector
Example #26
| Source File: eval_hooks.py From mmdetection_with_SENet154 with Apache License 2.0 | 5 votes |
|
def after_train_epoch(self, runner):
if not self.every_n_epochs(runner, self.interval):
return
runner.model.eval()
results = [None for _ in range(len(self.dataset))]
if runner.rank == 0:
prog_bar = mmcv.ProgressBar(len(self.dataset))
for idx in range(runner.rank, len(self.dataset), runner.world_size):
data = self.dataset[idx]
data_gpu = scatter(
collate([data], samples_per_gpu=1),
[torch.cuda.current_device()])[0]
# compute output
with torch.no_grad():
result = runner.model(
return_loss=False, rescale=True, **data_gpu)
results[idx] = result
batch_size = runner.world_size
if runner.rank == 0:
for _ in range(batch_size):
prog_bar.update()
if runner.rank == 0:
print('\n')
dist.barrier()
for i in range(1, runner.world_size):
tmp_file = osp.join(runner.work_dir, 'temp_{}.pkl'.format(i))
tmp_results = mmcv.load(tmp_file)
for idx in range(i, len(results), runner.world_size):
results[idx] = tmp_results[idx]
os.remove(tmp_file)
self.evaluate(runner, results)
else:
tmp_file = osp.join(runner.work_dir,
'temp_{}.pkl'.format(runner.rank))
mmcv.dump(results, tmp_file)
dist.barrier()
dist.barrier()
Example #27
| Source File: eval_hooks.py From PolarMask with Apache License 2.0 | 5 votes |
|
def after_train_epoch(self, runner):
if not self.every_n_epochs(runner, self.interval):
return
runner.model.eval()
results = [None for _ in range(len(self.dataset))]
if runner.rank == 0:
prog_bar = mmcv.ProgressBar(len(self.dataset))
for idx in range(runner.rank, len(self.dataset), runner.world_size):
data = self.dataset[idx]
data_gpu = scatter(
collate([data], samples_per_gpu=1),
[torch.cuda.current_device()])[0]
# compute output
with torch.no_grad():
result = runner.model(
return_loss=False, rescale=True, **data_gpu)
results[idx] = result
batch_size = runner.world_size
if runner.rank == 0:
for _ in range(batch_size):
prog_bar.update()
if runner.rank == 0:
print('\n')
dist.barrier()
for i in range(1, runner.world_size):
tmp_file = osp.join(runner.work_dir, 'temp_{}.pkl'.format(i))
tmp_results = mmcv.load(tmp_file)
for idx in range(i, len(results), runner.world_size):
results[idx] = tmp_results[idx]
os.remove(tmp_file)
self.evaluate(runner, results)
else:
tmp_file = osp.join(runner.work_dir,
'temp_{}.pkl'.format(runner.rank))
mmcv.dump(results, tmp_file)
dist.barrier()
dist.barrier()
Example #28
| Source File: inference.py From kaggle-kuzushiji-recognition with MIT License | 5 votes |
|
def inference_detector(model, img):
"""Inference image(s) with the detector.
Args:
model (nn.Module): The loaded detector.
imgs (str/ndarray or list[str/ndarray]): Either image files or loaded
images.
Returns:
If imgs is a str, a generator will be returned, otherwise return the
detection results directly.
"""
cfg = model.cfg
device = next(model.parameters()).device # model device
# build the data pipeline
test_pipeline = [LoadImage()] + cfg.data.test.pipeline[1:]
test_pipeline = Compose(test_pipeline)
# prepare data
data = dict(img=img)
data = test_pipeline(data)
data = scatter(collate([data], samples_per_gpu=1), [device])[0]
# forward the model
with torch.no_grad():
result = model(return_loss=False, rescale=True, **data)
return result
# TODO: merge this method with the one in BaseDetector
Example #29
| Source File: eval_hooks.py From Libra_R-CNN with Apache License 2.0 | 5 votes |
|
def after_train_epoch(self, runner):
if not self.every_n_epochs(runner, self.interval):
return
runner.model.eval()
results = [None for _ in range(len(self.dataset))]
if runner.rank == 0:
prog_bar = mmcv.ProgressBar(len(self.dataset))
for idx in range(runner.rank, len(self.dataset), runner.world_size):
data = self.dataset[idx]
data_gpu = scatter(
collate([data], samples_per_gpu=1),
[torch.cuda.current_device()])[0]
# compute output
with torch.no_grad():
result = runner.model(
return_loss=False, rescale=True, **data_gpu)
results[idx] = result
batch_size = runner.world_size
if runner.rank == 0:
for _ in range(batch_size):
prog_bar.update()
if runner.rank == 0:
print('\n')
dist.barrier()
for i in range(1, runner.world_size):
tmp_file = osp.join(runner.work_dir, 'temp_{}.pkl'.format(i))
tmp_results = mmcv.load(tmp_file)
for idx in range(i, len(results), runner.world_size):
results[idx] = tmp_results[idx]
os.remove(tmp_file)
self.evaluate(runner, results)
else:
tmp_file = osp.join(runner.work_dir,
'temp_{}.pkl'.format(runner.rank))
mmcv.dump(results, tmp_file)
dist.barrier()
dist.barrier()
Example #30
| Source File: eval_hooks.py From Grid-R-CNN with Apache License 2.0 | 5 votes |
|
def after_train_epoch(self, runner):
if not self.every_n_epochs(runner, self.interval):
return
runner.model.eval()
results = [None for _ in range(len(self.dataset))]
if runner.rank == 0:
prog_bar = mmcv.ProgressBar(len(self.dataset))
for idx in range(runner.rank, len(self.dataset), runner.world_size):
data = self.dataset[idx]
data_gpu = scatter(
collate([data], samples_per_gpu=1),
[torch.cuda.current_device()])[0]
# compute output
with torch.no_grad():
result = runner.model(
return_loss=False, rescale=True, **data_gpu)
results[idx] = result
batch_size = runner.world_size
if runner.rank == 0:
for _ in range(batch_size):
prog_bar.update()
if runner.rank == 0:
print('\n')
dist.barrier()
for i in range(1, runner.world_size):
tmp_file = osp.join(runner.work_dir, 'temp_{}.pkl'.format(i))
tmp_results = mmcv.load(tmp_file)
for idx in range(i, len(results), runner.world_size):
results[idx] = tmp_results[idx]
os.remove(tmp_file)
self.evaluate(runner, results)
else:
tmp_file = osp.join(runner.work_dir,
'temp_{}.pkl'.format(runner.rank))
mmcv.dump(results, tmp_file)
dist.barrier()
dist.barrier()
