Squeeze net conversion about keras

[MarcBS]

You can try it.
If it only has "classical" layers like Conv, RELU, Pooling, etc. then it should work without a problem.

[AliaMYH]

I'm currently trying to convert squeeze net and I get the following error

Alias-MacBook-Air:caffe Alia$ python caffe2keras.py -load_path '/Users/Alia/Documents/Spring 2017/Thesis/converting/' -prototxt 'converter.prototxt' -caffemodel 'squeezenet_v1.1.caffemodel'
Using TensorFlow backend.
Converting model...
CREATING MODEL
Traceback (most recent call last):
File "caffe2keras.py", line 45, in
main(args)
File "caffe2keras.py", line 34, in main
model = convert.caffe_to_keras(args.load_path+'/'+args.prototxt, args.load_path+'/'+args.caffemodel, debug=args.debug)
File "/Users/Alia/Desktop/converter/keras/keras/caffe/convert.py", line 43, in caffe_to_keras
debug)
File "/Users/Alia/Desktop/converter/keras/keras/caffe/convert.py", line 259, in create_model
net_node[layer_nb] = Activation('softmax', name=name)(input_layers)
File "/Users/Alia/Desktop/converter/keras/keras/engine/topology.py", line 569, in call
self.add_inbound_node(inbound_layers, node_indices, tensor_indices)
File "/Users/Alia/Desktop/converter/keras/keras/engine/topology.py", line 632, in add_inbound_node
Node.create_node(self, inbound_layers, node_indices, tensor_indices)
File "/Users/Alia/Desktop/converter/keras/keras/engine/topology.py", line 164, in create_node
output_tensors = to_list(outbound_layer.call(input_tensors[0], mask=input_masks[0]))
File "/Users/Alia/Desktop/converter/keras/keras/layers/core.py", line 250, in call
return self.activation(x)
File "/Users/Alia/Desktop/converter/keras/keras/activations.py", line 17, in softmax
'Here, ndim=' + str(ndim))
ValueError: Cannot apply softmax to a tensor that is not 2D or 3D. Here, ndim=4

Any advice or insight?

[akshaychawla]

Hi Alia,
The softmax layer in keras expects a tensor with the shape (batch_size, num_classes) however, the output from pool10 layer in case of squeezenet is (batch_size, num_filters, height, width). I recently submitted a PR that handles this, basically, it reshapes a 4-dim output to a 2-dim one.