Can anyone share the code mentioned in the closed issue #6 which is used to combine features to h5 format?

kracwarlock / action-recognition-visual-attention

Action recognition using soft attention based deep recurrent neural networks

http://www.cs.toronto.edu/~shikhar/projects/action-recognition-attention

350 stars 157 forks source link

Can anyone share the code mentioned in the closed issue #6 which is used to combine features to h5 format? #20

Closed YinRui1991 closed 6 years ago

YinRui1991 commented 6 years ago

I am interested in combination of deep learning and attention mechanism. I think this is a good way to know what deep learning focus on. I have got the features extracted by convolution layer of GoogLeNet, but the second link in issue #6 is not available (To combine the individual files generated by this script that he sent me I used https://gist.github.com/kracwarlock/96499936487d6125dd010319669c6648). Can anyone share this code again? Thanks very much!

GerardoHH commented 6 years ago

Hi @YinRui1991 Sorry but long time I stopped working on this project, and I already lost the code you tell me, but the link you mentioned is working.

Hope you solve the problem.

YinRui1991 commented 6 years ago

Thanks for your reply. I can't open the link because it is blocked by the government. I asked my friend in America to send the code. Benefiting from the discussion in #1, #2 and #6 questions, I have replicated the experiments. Thanks again!

vicely07 commented 6 years ago

@YinRui1991 Can you send me the code? I have problem creating the file in issue #6