How to 3d visualize output layers during training phase

问题

My final goal is to find a way to 3d visualize all layers during the training something like tensorSpace but real time during the training phase .

I am using tensorflow and google colab.

I managed to get each output like a tensor by creating a custom callback and creating this method

def on_train_batch_end(self, batch, logs=None):
 for i in range(len(model_inception.layers)):
   get_layer_output = K.function(inputs = self.model.layers[i].input, outputs = self.model.layers[i].output)
   print('\n Training: output of the layer {} is {} ends at {}'.format(i, get_layer_output.outputs , datetime.datetime.now().time()))

Would it be an option to save he tensors somehow and try to visualize with openGL or there is a better option ?

My full colab code copy is here https://colab.research.google.com/drive/1iMAMyE544EXcEn94kxAMngJFnshqX0pw

来源：https://stackoverflow.com/questions/59559784/how-to-3d-visualize-output-layers-during-training-phase

标签

tensorflow