vsubhashini / caption-eval Goto Github PK

I am using cuda-8 and tried cudnn 5.1 and 6 but was unable to compile
https://github.com/vsubhashini/caffe/tree/recurrent/examples/s2vt.
(Cannot create an issue there so raising it here)

Also, can you elaborate on the caffe model shared on your page is trained on all only MVSD dataset?.

Lastly, is there any specific steps to follow to test on new videos other than extracting VGG features.

Thanks for your work.

When I run the s2vt_captioner.py I get the following error:

mkldnn_concat_layer.cpp:139] Check failed: dim_src == bottom[i]->shape().size() (4 vs. 3)

I am running on intel caffe version 1.1.0 in cpu only mode.

How can I resolve the same?

in https://vsubhashini.github.io/noc.html,The code to prepare data and train the model can be found in: is empty

What beam_size_1 means and why it should be there in the .txt file?