Unused nn.Linear in classification model and paper inaccuracy?

[Snonky]

Hi, great work, thank you!

I found an orphaned nn.Linear module that was presumably replaced by the PatchEmbed layer in the classification model. I believe this line should be removed.

TSLANet/Classification/TSLANet_classification.py

Line 158 in ca0e884

self.input_layer = nn.Linear(args.patch_size, args.emb_dim)

Slightly related: in section 3.3 of the paper it is stated that P_𝑖 → P'_𝑖 ∈ ℝ^C⨯𝑝' with C being the number of channels. As far as I understand 𝑝' is the embedding size (--emb_dim in the code) and that is used to embed all dimensions into one so it should be P'_𝑖 ∈ ℝ^𝑝' dropping the channel dimension. I apologize if I missed something here that proves my remark as wrong.

[luojike2333]

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?

[luojike2333]

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?