我希望拥有一个多层ConvNet,以便在每个阶段我只训练一层。我的代码草图如下所示:
def MyConvNet(training_phase, input):
# conv1 structure
...
# conv2 structure
...
# conv3 structure
...
if(training_phase == 1):
return conv1_out
if(training_phase == 2):
return conv2_out
if(training_phase == 3):
return conv3_out
问题是此代码无效,我收到以下错误:
ValueError: None values not supported.
如何在TensorFlow中实现实现多层ConvNet的功能,并能够在不同的训练阶段获得每一层的输出?