本文整理汇总了Python中torch.nn.parallel._functions.ReduceAddCoalesced.apply方法的典型用法代码示例。如果您正苦于以下问题：Python ReduceAddCoalesced.apply方法的具体用法？Python ReduceAddCoalesced.apply怎么用？Python ReduceAddCoalesced.apply使用的例子？那么恭喜您, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类torch.nn.parallel._functions.ReduceAddCoalesced的用法示例。
在下文中一共展示了ReduceAddCoalesced.apply方法的6个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: forward
# 需要导入模块: from torch.nn.parallel._functions import ReduceAddCoalesced [as 别名]
# 或者: from torch.nn.parallel._functions.ReduceAddCoalesced import apply [as 别名]
def forward(self, inputs, *targets, **kwargs):
# input should be already scatterd
# scattering the targets instead
if not self.device_ids:
return self.module(inputs, *targets, **kwargs)
targets, kwargs = self.scatter(targets, kwargs, self.device_ids)
if len(self.device_ids) == 1:
return self.module(inputs, *targets, **kwargs)
replicas = self.replicate(self.module, self.device_ids[:len(inputs)])
outputs = self.criterion_apply(replicas, inputs, targets, kwargs)
return ReduceAddCoalesced.apply(
self.device_ids[0],
len(outputs),
*outputs) / len(outputs) 示例2: _data_parallel_master
# 需要导入模块: from torch.nn.parallel._functions import ReduceAddCoalesced [as 别名]
# 或者: from torch.nn.parallel._functions.ReduceAddCoalesced import apply [as 别名]
def _data_parallel_master(self, intermediates):
"""Reduce the sum and square-sum, compute the statistics, and broadcast it."""
# Always using same "device order" makes the ReduceAdd operation faster.
# Thanks to:: Tete Xiao (http://tetexiao.com/)
intermediates = sorted(intermediates, key=lambda i: i[1].sum.get_device())
to_reduce = [i[1][:2] for i in intermediates]
to_reduce = [j for i in to_reduce for j in i] # flatten
target_gpus = [i[1].sum.get_device() for i in intermediates]
sum_size = sum([i[1].sum_size for i in intermediates])
sum_, ssum = ReduceAddCoalesced.apply(target_gpus[0], 2, *to_reduce)
mean, inv_std = self._compute_mean_std(sum_, ssum, sum_size)
broadcasted = Broadcast.apply(target_gpus, mean, inv_std)
outputs = []
for i, rec in enumerate(intermediates):
outputs.append((rec[0], _MasterMessage(*broadcasted[i * 2:i * 2 + 2])))
return outputs 示例3: _data_parallel_master
# 需要导入模块: from torch.nn.parallel._functions import ReduceAddCoalesced [as 别名]
# 或者: from torch.nn.parallel._functions.ReduceAddCoalesced import apply [as 别名]
def _data_parallel_master(self, intermediates):
"""Reduce the sum and square-sum, compute the statistics, and broadcast it."""
intermediates = sorted(intermediates, key=lambda i: i[1].sum.get_device())
to_reduce = [i[1][:2] for i in intermediates]
to_reduce = [j for i in to_reduce for j in i] # flatten
target_gpus = [i[1].sum.get_device() for i in intermediates]
sum_size = sum([i[1].sum_size for i in intermediates])
sum_, ssum = ReduceAddCoalesced.apply(target_gpus[0], 2, *to_reduce)
mean, inv_std = self._compute_mean_std(sum_, ssum, sum_size)
broadcasted = Broadcast.apply(target_gpus, mean, inv_std)
outputs = []
for i, rec in enumerate(intermediates):
outputs.append((rec[0], _MasterMessage(*broadcasted[i*2:i*2+2])))
return outputs 示例4: _data_parallel_master
# 需要导入模块: from torch.nn.parallel._functions import ReduceAddCoalesced [as 别名]
# 或者: from torch.nn.parallel._functions.ReduceAddCoalesced import apply [as 别名]
def _data_parallel_master(self, intermediates):
"""Reduce the sum and square-sum, compute the statistics, and broadcast it."""
# Always using same "device order" makes the ReduceAdd operation faster.
# Thanks to:: Tete Xiao (http://tetexiao.com/)
intermediates = sorted(intermediates, key=lambda i: i[1].sum.get_device())
to_reduce = [i[1][:2] for i in intermediates]
to_reduce = [j for i in to_reduce for j in i] # flatten
target_gpus = [i[1].sum.get_device() for i in intermediates]
sum_size = sum([i[1].sum_size for i in intermediates])
sum_, ssum = ReduceAddCoalesced.apply(target_gpus[0], 2, *to_reduce)
mean, inv_std = self._compute_mean_std(sum_, ssum, sum_size)
broadcasted = Broadcast.apply(target_gpus, mean, inv_std)
outputs = []
for i, rec in enumerate(intermediates):
outputs.append((rec[0], _MasterMessage(*broadcasted[i*2:i*2+2])))
return outputs 示例5: batchnormtrain
# 需要导入模块: from torch.nn.parallel._functions import ReduceAddCoalesced [as 别名]
# 或者: from torch.nn.parallel._functions.ReduceAddCoalesced import apply [as 别名]
def batchnormtrain(input, mean, std, gamma, beta):
r"""Applies Batch Normalization over a 3d input that is seen as a
mini-batch.
.. _encoding.batchnormtrain:
.. math::
y = \frac{x - \mu[x]}{ \sqrt{var[x] + \epsilon}} * \gamma + \beta
Shape:
- Input: :math:`(N, C)` or :math:`(N, C, L)`
- Output: :math:`(N, C)` or :math:`(N, C, L)` (same shape as input)
"""
return _batchnormtrain.apply(input, mean, std, gamma, beta) 示例6: _data_parallel_master
# 需要导入模块: from torch.nn.parallel._functions import ReduceAddCoalesced [as 别名]
# 或者: from torch.nn.parallel._functions.ReduceAddCoalesced import apply [as 别名]
def _data_parallel_master(self, intermediates):
"""Reduce the sum and square-sum, compute the statistics, and broadcast it."""
# Always using same "device order" makes the ReduceAdd operation faster.
# Thanks to:: Tete Xiao (http://tetexiao.com/)
intermediates = sorted(intermediates, key=lambda i: i[1].sum.get_device())
to_reduce = [i[1][:2] for i in intermediates]
to_reduce = [j for i in to_reduce for j in i] # flatten
target_gpus = [i[1].sum.get_device() for i in intermediates]
sum_size = sum([i[1].sum_size for i in intermediates])
sum_, ssum = ReduceAddCoalesced.apply(target_gpus[0], 2, *to_reduce)
mean, inv_std = self._compute_mean_std(sum_, ssum, sum_size)
broadcasted = Broadcast.apply(target_gpus, mean, inv_std)
outputs = []
for i, rec in enumerate(intermediates):
outputs.append((rec[0], _MasterMessage(*broadcasted[i*2:i*2+2])))
return outputs