Emmanuel Benazera
Emmanuel Benazera
> same error So one thing you might want to try is to rebuild deepdetect in the following manner: - clear up your build ``` cd build rm -rf *...
> (let me know if you want a copy of my deploy.prototxt used with DeepDetect) Yes, this would be useful because DD uses `MemoryDataLayer` and I don't see it listed...
I can't comment on digits models specifically besides a warning since it uses the Nvidia version of Caffe afaik. Most discrepancies may come from wrongly scaled or preprocessed inputs (bgr...
Could you please check #430 and see whether it fixes the issue, or some of the discrepancies with color images ? My apologies, I should have checked for this potential...
The crop probably did it as the commit was reverted (the mean was already correctly subtracted as you found out)
This is a good example to start working on and to reproduce: https://github.com/fchollet/keras/blob/master/examples/imdb_bidirectional_lstm.py
Good link to get started with: http://christopher5106.github.io/deep/learning/2016/06/07/recurrent-neural-net-with-Caffe.html
Sure @kyrs. I'd suggest as a first goal that you take the keras example and try to get similar results with DD. To do this, you may have to go...
~~What do you mean more exactly by integrating a new lib ?~~ Ok I believe I understand: yes it'd be better to use the original Caffe lstm implementation. But if...
@kyrs OK thanks. Let me know if you need help, and reach out on gitter for instance. We can coordinate there.