Haoqing-Wang

Good job! I find an interesting phenomenon that the accuracy of ProtoNet's linear-layer form (w=2c, b=-c^2) is significantly lower than that of ProtoNet. However, theoretically the accuracy of the two...

Have you meet some problem like this? `RuntimeError: lu: For batch 0: U(30,30) is zero, singular U.`

Nice work! I want to know the specific configs or code for semantic segmentation in ADE20K and object detection in COCO. When would you release the configs or code for...

The transfer accuracy on LSUN and CelebA datasets are reported in the paper, but I can not find the corresponding code. Could you release them?

您好，您的这篇工作好像代码里和论文实验中都没用Forward Predictive Learning模块对吗？

A little question about layer decay

1

Good job! I notice this poject rescale `layer_decay` using ` layer_decay = layer_decay ** (13 / num_layers) ` I wonder why doing this? In fact, we can directly set the...

Wonderful job! I recently read you code and have some questions in Swin model which is shown in swin_transformer.py. Concretely, I can't understand the calculation formula of relative_position_index and attn_mask....

How can the driven-audio feature a and the landmark representation l be used for cross-attention module?

1

As we all know, the driven-audio feature a and the landmark representation l are just a vector, not a batch of vectors, so how can they be used in cross-attention...

Can you provide the processed data or the related processing code?

9

Nice job! Can you released the used dataset?