slice/split a layer in keras as in caffe

Question

I have used this converter to convert a Caffe model to Keras. But one of my layers is of type slice and it needs to be converted as well but the converter currently does not support this and raises an exception. Is there any work around for it? Here is my layer:

layer {
    name: "slice_label"
    type: SLICE
    bottom: "label"
    top: "label_wpqr"
    top: "label_xyz"
    slice_param {
        slice_dim: 1
        slice_point: 4
    }
}

score 8 · Accepted Answer · edited Feb 14 '18 at 05:32

8

It seems that you want to use a Lambda layer. In this case you may do the following:

sliced = Lambda(lambda x: x[:,slicing_indeces], output_shape=(sliced_shape))(input)

Note that in x you need to take into account the samples axis whereas in output_shape it's not needed anymore.

edited Feb 14 '18 at 05:32

HugoMailhot

1,275
1
10
19

answered Mar 27 '17 at 13:07

Marcin Możejko

39,542
10
109
120

slice/split a layer in keras as in caffe

1 Answers1

Linked