for conv_layer in self.conv_layers:
test_mat = conv_layer(test_mat)
self.conv_norm_layers.append(nn.BatchNorm2d(test_mat.shape[1]))
我的pytorch多处理在上述代码中挂起。非多重处理可以完美地工作。下面是启动多重处理的代码:
for idx in range(num_worker):
work = mp.Process(
target=run_experiment,
args=(experiment,),
kwargs=dict(...
)
)
work.start()
works.append(work)
for idx in range(num_worker):
works[idx].join()