video_to_sequence
video_to_sequence copied to clipboard
jazzsaxmafia
Implementation of "Sequence to Sequence – Video to Text"
It would be better if you put requirements.txt within this repository. It's not a big deal, but I hope you add that file. :) Thanks in advance.
Stop the code from removing the last word in current_caption_ind according to this #5 .
Hi! Thank you for your excellent work! I learn a lot from your implementation. But there is a little question about [n_lstm_steps](https://github.com/jazzsaxmafia/video_to_sequence/blob/master/model.py#L69). You make the encode and decode stage have...
First, thanks for your hard work on the code, it's very generous of you to share the code. :) But, when I use the model which have been trained to...
And how much is the best number about loss_val? In my lab ,there is not enough machine and resource to run the code again ,so i want to compare my...
When I tested the trained model, this error arose. I think this error occurs when video sequence is shorter than 80. Is there someway to use zero-padding to get the...
Hi: when i run python download_video.py ,after a day , the code leads to wrong . can you tell me how to download_videos ?
Dear jazz, ``` very good work. I have seen your both applications based on tensor flow and caffe. I am a student and i am very beginner. i installed tensor...
Metadata
Owner
Metadata
Implementation of "Sequence to Sequence – Video to Text"