caffe: model definition: write same layer with different phase using caffe.NetSpec()

by

I assume you mean how to define phase when writing a prototxt using caffe.NetSpec?

from caffe import layers as L, params as P, to_proto
import caffe

ns = caffe.NetSpec()
ns.data = L.Data(name="data", 
                 data_param={'source':'/path/to/lmdb','batch_size':32},
                 include={'phase':caffe.TEST})

If you want to have BOTH train and test layers in the same prototxt, what I usually do is making one ns for train with ALL layers and another ns_test with only the test version of the duplicate layers only. Then, when writing the actual prototxt file:

with open('model.prototxt', 'w') as W:
  W.write('%s\n' % ns_test.to_proto())
  W.write('%s\n' % ns.to_proto())

This way you’ll have BOTH phases in the same prototxt. A bit hacky, I know.

More Related Contents:

  1. Test labels for regression caffe, float not allowed?
  2. LSTM module for Caffe
  3. caffe data layer example step by step
  4. scale the loss value according to “badness” in caffe
  5. should I use float or classes as output for the final layer in my neural network?
  6. Keras input explanation: input_shape, units, batch_size, dim, etc
  7. Common causes of nans during training of neural networks
  8. What is a `”Python”` layer in caffe?
  9. InfogainLoss layer
  10. How to interpret caffe log with debug_info?
  11. How to training/testing my own dataset in caffe?
  12. [caffe]: check fails: Check failed: hdf_blobs_[i]->shape(0) == num (200 vs. 6000)
  13. Caffe | solver.prototxt values setting strategy
  14. How to calculate the number of parameters for convolutional neural network?
  15. What is `weight_decay` meta parameter in Caffe?
  16. How do I load a caffe model and convert to a numpy array?
  17. How to feed caffe multi label data in HDF5 format?
  18. Does Caffe need data to be shuffled?
  19. Tackling Class Imbalance: scaling contribution to loss and sgd
  20. Caffe: What can I do if only a small batch fits into memory?
  21. How to create caffe.deploy from train.prototxt
  22. How to reduce a fully-connected (`”InnerProduct”`) layer using truncated SVD
  23. What is `lr_policy` in Caffe?
  24. 2-D convolution as a matrix-matrix multiplication [closed]
  25. Why binary_crossentropy and categorical_crossentropy give different performances for the same problem?
  26. A guide to convert_imageset.cpp
  27. Neural network always predicts the same class
  28. Why must a nonlinear activation function be used in a backpropagation neural network? [closed]
  29. What is the purpose of the add_loss function in Keras?
  30. What is right batch normalization function in Tensorflow?

Leave a Comment