Implementing tensorflow functionality in deeplearning4j

Question

I'm trying to implement the code described in this blogpost with deeplearning4j.

http://www.wildml.com/2015/12/implementing-a-cnn-for-text-classification-in-tensorflow/

I'm having problems implementing multiple kernels on the same channel and concatenating the resulting tensors. Is there even a concat function in deeplearning4j? And is it even possible to have different kernels on the same channel?

Tank you in advance.

Please join our Gitter channel. Skymind engineers are there answering questions: https://gitter.im/deeplearning4j/deeplearning4j — racknuf, Jun 01 '16 at 18:54

score 2 · Accepted Answer · edited Oct 25 '16 at 22:53

2

You will have to use our computation graph api: http://deeplearning4j.org/compgraph

edited Oct 25 '16 at 22:53

James Moore

8,636
5
71
90

answered Jul 25 '16 at 12:11

Adam Gibson

3,055
1
10
12

Implementing tensorflow functionality in deeplearning4j

1 Answers1