WangZhennan

question about "visual sentinel"

3

Dear Jiasen Lu, Thank you for your work on "Knowing When to Look: Adaptive Attention via A Visual Sentinel for Image Captioning". I am writing to ask about the "visual...

pre-trained model?

7

Thanks for your work on this pytorch version of 'knowing when to look'. Can you public the pre-trained model?

why use the log function to regularize the scale?

4

Hi, I have a question about the implementation. In the Distribution().nllfun method, to regularize the scale to decrease, why you use the log function？ I think the l2 or l1...

Did the weight_decay needed?

2

Hi, thanks for your wanderful work. As I use your AdaptiveLossFunction, I found the alpha did not decrease, it keeps the highest value through the training process. So, I used...

Hi, thanks for your great work. Is there a pytorch version ?