hkzhang-git / st-clstm Goto Github PK

Hi, author!
We notice your another wonderful work published at CVPR2020: ' Memory-Efficient Hierarchical Neural Architecture Search for Image Denoising', which give us a lot inspiration.

Thanks for your wonderful work! I really want to learn the details of your code. Could you please tell me when the source code will be released? Thanks!****

Thanks for your excellent work. I am interested in your work, could you possiblly release your code? Thanks a lot!

Could you release the model trained on the KITTI dataset for evaluation?

Hi,
Thanks for your wonderful work! I really want to learn the details of your code. Could you please tell me when the source code will be released? Thanks!

Thanks for your excellent work. As you present in Readme.txt, there need a demo_main.py file, I didn't found in that path, could you please add this file? thanks a lot!

Hi Haokui,

In your paper, the equation (2) applied TanH function on the C_t before concatenation and feeding them to the refinement R_t. But when I was looking at your code, I noticed that you didn't apply the TanH function on C_t before the refinement (for example, line 363 in file "R_CLSTM_modules_2.py"). Please tell me which version is correct. I appreciate any help you can provide.

Regards,
Lucas

As you said in your paper, ◦ and × represent the Hadamard product and pointwise multiplication.
But according to my understanding, they mean the same thing.
Could you please help me understand their difference?