jssprz / attentive_specialized_network_video_captioning Goto Github PK

which are the tunable parameters in this model??

Please provide the training code. You had mentioned that you will be providing the training code after Nov 16. Its been a month and no reply from you regarding the training code.

I request you to provide the training code.
Waiting for the reply from you.
Thank You

Thanks for sharing your codes.

It seems that you did not upload the training codes, can you share them please? Thanks.

I tried to create the training code myself, but the results don't match the paper. Perhaps I missed something, but I'm not sure. I followed the exact hyperparameters and procedures mentioned in the paper. I would greatly appreciate it if you could provide the training code. Thank you.

I am very interested in ur work. But I can't find the original paper. Could you please share a link to read your paper"Attentive Visual Semantic Specialized Network for Video Captioning", Thanks a lot!

can you tell how to train the model for more epochs?

Can you provide the training code? thank you

hi ~ Could you provide how to deal with the caption.json file into the input format? I wonder how to do this preprocessing.
your code would be very helpful, thanks!

Thanks for you work on this project!

I followed the instructions in the readme to get your code running, and I wasn't able to reproduce the results from the paper:

MSVD:
RESULTS: Bleu_1: 0.858 Bleu_2: 0.756 Bleu_3: 0.665 Bleu_4: 0.573 METEOR: 0.385 ROUGE_L: 0.749 CIDEr: 0.992
Expected: Bleu_4: 62.3 METEOR: 39.2 CIDEr: 107.7 ROUGE_L: 78.3

MSR-VTT:
RESULTS: Bleu_1: 0.812 Bleu_2: 0.679 Bleu_3: 0.547 Bleu_4: 0.428 METEOR: 0.288 ROUGE_L: 0.617 CIDEr: 0.469
Expected: Bleu_4: 45.5 METEOR: 31.4 CIDEr: 50.6 ROUGE_L: 64.3

I noticed that these are epoch 15 checkpoints, but in the paper, the models were trained for ~70 epochs, are you willing to make these final models available, or the code infrastructure for training a new model?

Hello, thank you very much for the code you provided, but I found that I could not download these two files:
MSR-VTT/corpus.pkl
MSR-VTT/captioning_chkpt_15.pt