defining caffe prototxt in python

Question

How to add a layer for both the TRAIN and TEST phase with different parameters in one prototxt file using caffe in python?

If you look at https://github.com/BVLC/caffe/blob/master/examples/mnist/lenet_train_test.prototxt, you will see the input layer for train and test phase with different parameters.

I followed this links
Where is layer module defined in PyCaffe
LSTM module for Caffe
to define caffe prototxt in python. But i can't define the same layer name with same blob names for different phases in one prototxt file.

Please help

Answer 1

This is an open issue https://github.com/BVLC/caffe/issues/4044
have a look at these links:
caffe: model definition: write same layer with different phase using caffe.NetSpec()
PyCaffe NetSpec, how to create layers with the same name but different phases?