Python torch.nn.parallel.parallel_apply.get_a_var() Examples
The following are 13
code examples of torch.nn.parallel.parallel_apply.get_a_var().
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
torch.nn.parallel.parallel_apply
, or try the search function
.
.
Example #1
| Source File: EncodingDataParallel.py From torch-toolbox with BSD 3-Clause "New" or "Revised" License | 4 votes |
|
def criterion_parallel_apply(
modules,
inputs,
targets,
kwargs_tup=None,
devices=None):
assert len(modules) == len(inputs)
assert len(targets) == len(inputs)
if kwargs_tup is not None:
assert len(modules) == len(kwargs_tup)
else:
kwargs_tup = ({},) * len(modules)
if devices is not None:
assert len(modules) == len(devices)
else:
devices = [None] * len(modules)
devices = list(map(lambda x: _get_device_index(x, True), devices))
lock = threading.Lock()
results = {}
grad_enabled = torch.is_grad_enabled()
def _worker(i, module, input, target, kwargs, device=None):
torch.set_grad_enabled(grad_enabled)
if device is None:
device = get_a_var(input).get_device()
try:
with torch.cuda.device(device):
if not isinstance(input, (list, tuple)):
input = (input,)
if not isinstance(target, (list, tuple)):
target = (target,)
output = module(*input, *target, **kwargs)
with lock:
results[i] = output
except Exception:
with lock:
results[i] = ExceptionWrapper(
where="in replica {} on device {}".format(i, device))
if len(modules) > 1:
threads = [threading.Thread(target=_worker,
args=(i, module, input, target, kwargs, device))
for i, (module, input, target, kwargs, device) in
enumerate(zip(modules, inputs, kwargs_tup, devices))]
for thread in threads:
thread.start()
for thread in threads:
thread.join()
else:
_worker(0, modules[0], inputs[0], kwargs_tup[0], devices[0])
outputs = []
for i in range(len(inputs)):
output = results[i]
if isinstance(output, ExceptionWrapper):
output.reraise()
outputs.append(output)
return outputs
Example #2
| Source File: encoding.py From pytorch-segmentation-toolbox with MIT License | 4 votes |
|
def _criterion_parallel_apply(modules, inputs, targets, kwargs_tup=None, devices=None):
assert len(modules) == len(inputs)
assert len(targets) == len(inputs)
if kwargs_tup:
assert len(modules) == len(kwargs_tup)
else:
kwargs_tup = ({},) * len(modules)
if devices is not None:
assert len(modules) == len(devices)
else:
devices = [None] * len(modules)
lock = threading.Lock()
results = {}
if torch_ver != "0.3":
grad_enabled = torch.is_grad_enabled()
def _worker(i, module, input, target, kwargs, device=None):
if torch_ver != "0.3":
torch.set_grad_enabled(grad_enabled)
if device is None:
device = get_a_var(input).get_device()
try:
if not isinstance(input, tuple):
input = (input,)
with torch.cuda.device(device):
output = module(*(input + target), **kwargs)
with lock:
results[i] = output
except Exception as e:
with lock:
results[i] = e
if len(modules) > 1:
threads = [threading.Thread(target=_worker,
args=(i, module, input, target,
kwargs, device),)
for i, (module, input, target, kwargs, device) in
enumerate(zip(modules, inputs, targets, kwargs_tup, devices))]
for thread in threads:
thread.start()
for thread in threads:
thread.join()
else:
_worker(0, modules[0], inputs[0], kwargs_tup[0], devices[0])
outputs = []
for i in range(len(inputs)):
output = results[i]
if isinstance(output, Exception):
raise output
outputs.append(output)
return outputs
###########################################################################
# Adapted from Synchronized-BatchNorm-PyTorch.
# https://github.com/vacancy/Synchronized-BatchNorm-PyTorch
#
Example #3
| Source File: parallel.py From MusicTransformer-pytorch with MIT License | 4 votes |
|
def _criterion_parallel_apply(modules, inputs, targets, kwargs_tup=None, devices=None):
assert len(modules) == len(inputs)
assert len(targets) == len(inputs)
if kwargs_tup:
assert len(modules) == len(kwargs_tup)
else:
kwargs_tup = ({},) * len(modules)
if devices is not None:
assert len(modules) == len(devices)
else:
devices = [None] * len(modules)
lock = threading.Lock()
results = {}
if torch_ver != "0.3":
grad_enabled = torch.is_grad_enabled()
def _worker(i, module, input, target, kwargs, device=None):
if torch_ver != "0.3":
torch.set_grad_enabled(grad_enabled)
if device is None:
device = get_a_var(input).get_device()
try:
with torch.cuda.device(device):
# output = module(*(input + target), **kwargs)
if type(input) == tuple:
input = input[0]
# print('module: {}\ninput: {}\ntarget:{}'.format(module, input, target))
output = module(input, target)
with lock:
results[i] = output
except Exception as e:
with lock:
results[i] = e
if len(modules) > 1:
threads = [threading.Thread(target=_worker,
args=(i, module, input, target,
kwargs, device), )
for i, (module, input, target, kwargs, device) in
enumerate(zip(modules, inputs, targets, kwargs_tup, devices))]
for thread in threads:
thread.start()
for thread in threads:
thread.join()
else:
_worker(0, modules[0], inputs[0], kwargs_tup[0], devices[0])
outputs = []
for i in range(len(inputs)):
output = results[i]
if isinstance(output, Exception):
raise output
outputs.append(output)
return outputs
Example #4
| Source File: encoding.py From CCNet with MIT License | 4 votes |
|
def _criterion_parallel_apply(modules, inputs, targets, kwargs_tup=None, devices=None):
assert len(modules) == len(inputs)
assert len(targets) == len(inputs)
if kwargs_tup:
assert len(modules) == len(kwargs_tup)
else:
kwargs_tup = ({},) * len(modules)
if devices is not None:
assert len(modules) == len(devices)
else:
devices = [None] * len(modules)
lock = threading.Lock()
results = {}
if torch_ver != "0.3":
grad_enabled = torch.is_grad_enabled()
def _worker(i, module, input, target, kwargs, device=None):
if torch_ver != "0.3":
torch.set_grad_enabled(grad_enabled)
if device is None:
device = get_a_var(input).get_device()
try:
if not isinstance(input, tuple):
input = (input,)
with torch.cuda.device(device):
output = module(*(input + target), **kwargs)
with lock:
results[i] = output
except Exception as e:
with lock:
results[i] = e
if len(modules) > 1:
threads = [threading.Thread(target=_worker,
args=(i, module, input, target,
kwargs, device),)
for i, (module, input, target, kwargs, device) in
enumerate(zip(modules, inputs, targets, kwargs_tup, devices))]
for thread in threads:
thread.start()
for thread in threads:
thread.join()
else:
_worker(0, modules[0], inputs[0], kwargs_tup[0], devices[0])
outputs = []
for i in range(len(inputs)):
output = results[i]
if isinstance(output, Exception):
raise output
outputs.append(output)
return outputs
###########################################################################
# Adapted from Synchronized-BatchNorm-PyTorch.
# https://github.com/vacancy/Synchronized-BatchNorm-PyTorch
#
Example #5
| Source File: parallel.py From PyTorch-Encoding with MIT License | 4 votes |
|
def _criterion_parallel_apply(modules, inputs, targets, kwargs_tup=None, devices=None):
assert len(modules) == len(inputs)
assert len(targets) == len(inputs)
if kwargs_tup:
assert len(modules) == len(kwargs_tup)
else:
kwargs_tup = ({},) * len(modules)
if devices is not None:
assert len(modules) == len(devices)
else:
devices = [None] * len(modules)
lock = threading.Lock()
results = {}
if torch_ver != "0.3":
grad_enabled = torch.is_grad_enabled()
def _worker(i, module, input, target, kwargs, device=None):
if torch_ver != "0.3":
torch.set_grad_enabled(grad_enabled)
if device is None:
device = get_a_var(input).get_device()
try:
with torch.cuda.device(device):
output = module(*(input + target), **kwargs)
with lock:
results[i] = output
except Exception as e:
with lock:
results[i] = e
if len(modules) > 1:
threads = [threading.Thread(target=_worker,
args=(i, module, input, target,
kwargs, device),)
for i, (module, input, target, kwargs, device) in
enumerate(zip(modules, inputs, targets, kwargs_tup, devices))]
for thread in threads:
thread.start()
for thread in threads:
thread.join()
else:
_worker(0, modules[0], inputs[0], kwargs_tup[0], devices[0])
outputs = []
for i in range(len(inputs)):
output = results[i]
if isinstance(output, Exception):
raise output
outputs.append(output)
return outputs
Example #6
| Source File: data_parallel.py From openseg.pytorch with MIT License | 4 votes |
|
def _criterion_parallel_apply(modules, inputs, targets, kwargs_tup=None, devices=None):
assert len(modules) == len(inputs)
assert len(targets) == len(inputs)
if kwargs_tup:
assert len(modules) == len(kwargs_tup)
else:
kwargs_tup = ({},) * len(modules)
if devices is not None:
assert len(modules) == len(devices)
else:
devices = [None] * len(modules)
lock = threading.Lock()
results = {}
if torch_ver != "0.3":
grad_enabled = torch.is_grad_enabled()
def _worker(i, module, input, target, kwargs, device=None):
if torch_ver != "0.3":
torch.set_grad_enabled(grad_enabled)
if device is None:
device = get_a_var(input).get_device()
try:
with torch.cuda.device(device):
output = module(input, *target, **kwargs)
with lock:
results[i] = output
except Exception as e:
with lock:
results[i] = e
if len(modules) > 1:
threads = [threading.Thread(target=_worker,
args=(i, module, input, target,
kwargs, device),)
for i, (module, input, target, kwargs, device) in
enumerate(zip(modules, inputs, targets, kwargs_tup, devices))]
for thread in threads:
thread.start()
for thread in threads:
thread.join()
else:
_worker(0, modules[0], inputs[0], targets[0], kwargs_tup[0], devices[0])
outputs = []
for i in range(len(inputs)):
output = results[i]
if isinstance(output, Exception):
raise output
outputs.append(output)
return outputs
###########################################################################
# Adapted from Synchronized-BatchNorm-PyTorch.
# https://github.com/vacancy/Synchronized-BatchNorm-PyTorch
#
Example #7
| Source File: _parallel_utils.py From fastNLP with Apache License 2.0 | 4 votes |
|
def parallel_apply(modules, func_name, inputs, kwargs_tup=None, devices=None):
r"""Applies each `module` in :attr:`modules` in parallel on arguments
contained in :attr:`inputs` (positional) and :attr:`kwargs_tup` (keyword)
on each of :attr:`devices`.
:attr:`modules`, :attr:`inputs`, :attr:`kwargs_tup` (if given), and
:attr:`devices` (if given) should all have same length. Moreover, each
element of :attr:`inputs` can either be a single object as the only argument
to a module, or a collection of positional arguments.
"""
assert len(modules) == len(inputs)
if kwargs_tup is not None:
assert len(modules) == len(kwargs_tup)
else:
kwargs_tup = ({},) * len(modules)
if devices is not None:
assert len(modules) == len(devices)
else:
devices = [None] * len(modules)
lock = threading.Lock()
results = {}
grad_enabled = torch.is_grad_enabled()
def _worker(i, module, input, kwargs, device=None):
torch.set_grad_enabled(grad_enabled)
if device is None:
device = get_a_var(input).get_device()
try:
with torch.cuda.device(device):
# this also avoids accidental slicing of `input` if it is a Tensor
if not isinstance(input, (list, tuple)):
input = (input,)
output = getattr(module, func_name)(*input, **kwargs)
with lock:
results[i] = output
except Exception as e:
with lock:
results[i] = e
if len(modules) > 1:
threads = [threading.Thread(target=_worker,
args=(i, module, input, kwargs, device))
for i, (module, input, kwargs, device) in
enumerate(zip(modules, inputs, kwargs_tup, devices))]
for thread in threads:
thread.start()
for thread in threads:
thread.join()
else:
_worker(0, modules[0], inputs[0], kwargs_tup[0], devices[0])
outputs = []
for i in range(len(inputs)):
output = results[i]
if isinstance(output, Exception):
raise output
outputs.append(output)
return outputs
Example #8
| Source File: parallel.py From structure_knowledge_distillation with BSD 2-Clause "Simplified" License | 4 votes |
|
def _criterion_parallel_apply(modules, inputs, targets, kwargs_tup=None, devices=None):
assert len(modules) == len(inputs)
assert len(targets) == len(inputs)
if kwargs_tup:
assert len(modules) == len(kwargs_tup)
else:
kwargs_tup = ({},) * len(modules)
if devices is not None:
assert len(modules) == len(devices)
else:
devices = [None] * len(modules)
lock = threading.Lock()
results = {}
if torch_ver != "0.3":
grad_enabled = torch.is_grad_enabled()
def _worker(i, module, input, target, kwargs, device=None):
#import pdb;pdb.set_trace()
if torch_ver != "0.3":
torch.set_grad_enabled(grad_enabled)
if device is None:
device = get_a_var(input).get_device()
try:
if not isinstance(input, tuple):
input = (input,)
if not isinstance(target, tuple):
target = (target,)
with torch.cuda.device(device):
output = module(*(input + target), **kwargs)
with lock:
results[i] = output
except Exception as e:
with lock:
results[i] = e
if len(modules) > 1:
threads = [threading.Thread(target=_worker,
args=(i, module, input, target,
kwargs, device),)
for i, (module, input, target, kwargs, device) in
enumerate(zip(modules, inputs, targets, kwargs_tup, devices))]
for thread in threads:
thread.start()
for thread in threads:
thread.join()
else:
_worker(0, modules[0], inputs[0], kwargs_tup[0], devices[0])
outputs = []
for i in range(len(inputs)):
output = results[i]
if isinstance(output, Exception):
raise output
outputs.append(output)
return outputs
Example #9
| Source File: parallel.py From evaluating_bdl with MIT License | 4 votes |
|
def _criterion_parallel_apply(modules, inputs, targets, kwargs_tup=None, devices=None):
assert len(modules) == len(inputs)
assert len(targets) == len(inputs)
if kwargs_tup:
assert len(modules) == len(kwargs_tup)
else:
kwargs_tup = ({},) * len(modules)
if devices is not None:
assert len(modules) == len(devices)
else:
devices = [None] * len(modules)
lock = threading.Lock()
results = {}
if torch_ver != "0.3":
grad_enabled = torch.is_grad_enabled()
def _worker(i, module, input, target, kwargs, device=None):
if torch_ver != "0.3":
torch.set_grad_enabled(grad_enabled)
if device is None:
device = get_a_var(input).get_device()
try:
with torch.cuda.device(device):
output = module(input, target, **kwargs)
# output = module(*(input + target), **kwargs)
with lock:
results[i] = output
except Exception as e:
with lock:
results[i] = e
if len(modules) > 1:
threads = [threading.Thread(target=_worker,
args=(i, module, input, target,
kwargs, device),)
for i, (module, input, target, kwargs, device) in
enumerate(zip(modules, inputs, targets, kwargs_tup, devices))]
for thread in threads:
thread.start()
for thread in threads:
thread.join()
else:
_worker(0, modules[0], inputs[0], kwargs_tup[0], devices[0])
outputs = []
for i in range(len(inputs)):
output = results[i]
if isinstance(output, Exception):
raise output
outputs.append(output)
return outputs
###########################################################################
# Adapted from Synchronized-BatchNorm-PyTorch.
# https://github.com/vacancy/Synchronized-BatchNorm-PyTorch
#
Example #10
| Source File: parallel.py From LightNetPlusPlus with MIT License | 4 votes |
|
def _criterion_parallel_apply(modules, inputs, targets, kwargs_tup=None, devices=None):
assert len(modules) == len(inputs)
assert len(targets) == len(inputs)
if kwargs_tup:
assert len(modules) == len(kwargs_tup)
else:
kwargs_tup = ({},) * len(modules)
if devices is not None:
assert len(modules) == len(devices)
else:
devices = [None] * len(modules)
lock = threading.Lock()
results = {}
if torch_ver != "0.3":
grad_enabled = torch.is_grad_enabled()
def _worker(i, module, input, target, kwargs, device=None):
if torch_ver != "0.3":
torch.set_grad_enabled(grad_enabled)
if device is None:
device = get_a_var(input).get_device()
try:
with torch.cuda.device(device):
output = module(input, target)
with lock:
results[i] = output
except Exception as e:
with lock:
results[i] = e
if len(modules) > 1:
threads = [threading.Thread(target=_worker,
args=(i, module, input, target,
kwargs, device),)
for i, (module, input, target, kwargs, device) in
enumerate(zip(modules, inputs, targets, kwargs_tup, devices))]
for thread in threads:
thread.start()
for thread in threads:
thread.join()
else:
_worker(0, modules[0], inputs[0], kwargs_tup[0], devices[0])
outputs = []
for i in range(len(inputs)):
output = results[i]
if isinstance(output, Exception):
raise output
outputs.append(output)
return outputs
###########################################################################
# Adapted from Synchronized-BatchNorm-PyTorch.
# https://github.com/vacancy/Synchronized-BatchNorm-PyTorch
#
Example #11
| Source File: parallel.py From pretraining-for-language-understanding with Apache License 2.0 | 4 votes |
|
def _criterion_parallel_apply(modules, inputs, targets, kwargs_tup=None, devices=None):
assert len(modules) == len(inputs)
assert len(targets) == len(inputs)
if kwargs_tup:
assert len(modules) == len(kwargs_tup)
else:
kwargs_tup = ({},) * len(modules)
if devices is not None:
assert len(modules) == len(devices)
else:
devices = [None] * len(modules)
lock = threading.Lock()
results = {}
if torch_ver != "0.3":
grad_enabled = torch.is_grad_enabled()
def _worker(i, module, input, target, kwargs, device=None):
if torch_ver != "0.3":
torch.set_grad_enabled(grad_enabled)
if device is None:
device = get_a_var(input).get_device()
try:
with torch.cuda.device(device):
output = module(input, target)
with lock:
results[i] = output
except Exception as e:
with lock:
results[i] = e
if len(modules) > 1:
threads = [threading.Thread(target=_worker,
args=(i, module, input, target,
kwargs, device),)
for i, (module, input, target, kwargs, device) in
enumerate(zip(modules, inputs, targets, kwargs_tup, devices))]
for thread in threads:
thread.start()
for thread in threads:
thread.join()
else:
_worker(0, modules[0], inputs[0], kwargs_tup[0], devices[0])
outputs = []
for i in range(len(inputs)):
output = results[i]
if isinstance(output, Exception):
raise output
outputs.append(output)
return outputs
Example #12
| Source File: parallel.py From open-solution-googleai-object-detection with MIT License | 4 votes |
|
def _criterion_parallel_apply(modules, inputs, targets, kwargs_tup=None, devices=None):
assert len(modules) == len(inputs)
assert len(targets) == len(inputs)
if kwargs_tup:
assert len(modules) == len(kwargs_tup)
else:
kwargs_tup = ({},) * len(modules)
if devices is not None:
assert len(modules) == len(devices)
else:
devices = [None] * len(modules)
lock = threading.Lock()
results = {}
if torch_ver != "0.3":
grad_enabled = torch.is_grad_enabled()
def _worker(i, module, input, target, kwargs, device=None):
if torch_ver != "0.3":
torch.set_grad_enabled(grad_enabled)
if device is None:
device = get_a_var(input).get_device()
try:
with torch.cuda.device(device):
output = module(*(input + target), **kwargs)
with lock:
results[i] = output
except Exception as e:
with lock:
results[i] = e
if len(modules) > 1:
threads = [threading.Thread(target=_worker,
args=(i, module, input, target,
kwargs, device),)
for i, (module, input, target, kwargs, device) in
enumerate(zip(modules, inputs, targets, kwargs_tup, devices))]
for thread in threads:
thread.start()
for thread in threads:
thread.join()
else:
_worker(0, modules[0], inputs[0], kwargs_tup[0], devices[0])
outputs = []
for i in range(len(inputs)):
output = results[i]
if isinstance(output, Exception):
raise output
outputs.append(output)
return outputs
###########################################################################
# Adapted from Synchronized-BatchNorm-PyTorch.
# https://github.com/vacancy/Synchronized-BatchNorm-PyTorch
#
Example #13
| Source File: parallel.py From OCNet.pytorch with MIT License | 4 votes |
|
def _criterion_parallel_apply(modules, inputs, targets, kwargs_tup=None, devices=None):
assert len(modules) == len(inputs)
assert len(targets) == len(inputs)
if kwargs_tup:
assert len(modules) == len(kwargs_tup)
else:
kwargs_tup = ({},) * len(modules)
if devices is not None:
assert len(modules) == len(devices)
else:
devices = [None] * len(modules)
lock = threading.Lock()
results = {}
if torch_ver != "0.3":
grad_enabled = torch.is_grad_enabled()
def _worker(i, module, input, target, kwargs, device=None):
if torch_ver != "0.3":
torch.set_grad_enabled(grad_enabled)
if device is None:
device = get_a_var(input).get_device()
try:
with torch.cuda.device(device):
output = module(input, target, **kwargs)
# output = module(*(input + target), **kwargs)
with lock:
results[i] = output
except Exception as e:
with lock:
results[i] = e
if len(modules) > 1:
threads = [threading.Thread(target=_worker,
args=(i, module, input, target,
kwargs, device),)
for i, (module, input, target, kwargs, device) in
enumerate(zip(modules, inputs, targets, kwargs_tup, devices))]
for thread in threads:
thread.start()
for thread in threads:
thread.join()
else:
_worker(0, modules[0], inputs[0], kwargs_tup[0], devices[0])
outputs = []
for i in range(len(inputs)):
output = results[i]
if isinstance(output, Exception):
raise output
outputs.append(output)
return outputs
###########################################################################
# Adapted from Synchronized-BatchNorm-PyTorch.
# https://github.com/vacancy/Synchronized-BatchNorm-PyTorch
#
