Embed layer error

[abrahamyan-lusine]

Hi, I'm trying to run 5th captioning example, but stack with error

WARNING: Logging before InitGoogleLogging() is written to STDERR
F1221 08:09:06.817744 21017 embed_layer.cu:61] Check failed: !propagate_down[0] Can't backpropagate to EmbedLayer input.
*** Check failure stack trace: ***
./5_caption_conditional_sampling.sh: line 52: 21017 Aborted (core dumped) python ./sampling_caption.py --act_layer ${act_layer} --opt_layer ${opt_layer} --sentence ${sentence} --xy ${xy} --n_iters ${n_iters} --save_every ${save_every} --reset_every ${reset_every} --lr ${lr} --lr_end ${lr_end} --seed ${seed} --output_dir ${output_dir} --init_file ${init_file} --epsilon1 ${epsilon1} --epsilon2 ${epsilon2} --epsilon3 ${epsilon3} --threshold ${threshold} --net_weights ${net_weights} --net_definition ${net_definition} --captioner_definition ${captioner_definition}

I'm using master version from caffe repo instead of Yours, because forked branch older and so I have compatibility problems with cuDNN , but I check that there is no differences in both Embed_layer files. So please can You help me with this problem, or prompt what layers or files do I need from Your caffe branch to make script work.

[anguyen8]

@abrahamyan-lusine Hi, my suggestion would be to try compile the caffe version that I suggested, i.e. this: https://github.com/anguyen8/caffe_lrcn

This repo is from 2015 (Donahue et al) where the LRCN model came from and this version has many differences from the current master. I'm not sure if I know all the things that should be fixed.

[thommiano]

@abrahamyan-lusine Were you able to fix this problem? If so, how? I'm encountering a similar problem.