Free Soul

Hi, I see ` batch_size =2` in all experiments of the paper. To make training faster, I set` batch_size =128 or 256` on my dataset with the same model, however,...

Hello, I want to know why new zsl papers and codes are not added after 2021. Btw, Is there any available space for research in this field? Thanks

Whether to use a lr scheduler when training from the scratch?

1

Hi, If we choose to train this model from the scratch on a custom dataset, should we warmup the learning rate in the begining and decrease it slowly? I could...

Hello, Thanks for sharing the codes. Could you please tell us the compatible version of pytorch? Thanks

Hello, Really thank you for releasing the code. However, I find several obvious mismatches between the code and the paper, and I also find some error. - https://github.com/shiming-chen/MSDN/blob/ec3598bc6639732dfc46205de0e4cb4958774a1e/core/MSDN.py#L316 the softmax...