Open Snonky opened 2 weeks ago
Good question! Have you tried conducting experiments to explore the differences between using nn.Linear and not using it? Whether there is a difference in the results of the experiment?
Good question! Have you tried conducting experiments to explore the differences between using nn.Linear and not using it? Whether there is a difference in the results of the experiment?
Hi, great work, thank you!
I found an orphaned
nn.Linear
module that was presumably replaced by thePatchEmbed
layer in the classification model. I believe this line should be removed.https://github.com/emadeldeen24/TSLANet/blob/ca0e88416d3ae49fd50e399c44ae94868378a94d/Classification/TSLANet_classification.py#L158
Slightly related: in section 3.3 of the paper it is stated that Pš ā P'š ā āCāØÆš' with C being the number of channels. As far as I understand š' is the embedding size (
--emb_dim
in the code) and that is used to embed all dimensions into one so it should be P'š ā āš' dropping the channel dimension. I apologize if I missed something here that proves my remark as wrong.