TsingW

The meaning of num_feature_levels.

2

Thanks for your great and detailed code! In `dab_deformable_detr.py`, is this part about dealing with the insufficient channel of features (for Deformable DETR)? > https://github.com/IDEA-opensource/DAB-DETR/blob/309f6ad92af7a62d7732c1bdf1e0c7a69a7bdaef/models/dab_deformable_detr/dab_deformable_detr.py#L169-L181 It seems that the last...

Can we visualize the intermediate result of Query Selection？

1

I think it is fun to have the visualization on the top-k boxes selected from the Encoder's output.

As title says, it seems that none of the code using that parameter?

About 'no object' in the labels.

6

In the code of making one-hot targets for class prediction, the `no-object` class prediction seems not to be supervised: https://github.com/IDEA-Research/DINO/blob/3ffda400b0f1d4a919fbe2a9cf567e79d210ffde/models/dino/dino.py#L362-L374 Especially, https://github.com/IDEA-Research/DINO/blob/3ffda400b0f1d4a919fbe2a9cf567e79d210ffde/models/dino/dino.py#L372 According to this, if a query is assigned...

Is w&h ratio in propasals a hyperparameter?

1

I found the wh is hard-coded and fixed by default in `gen_encoder_output_proposals()`. Have you tried the settings of different size ratios? I noticed there is an option for learned wh...

Why padding in attention?

4

https://github.com/mit-han-lab/efficientvit/blob/f47de541358135d646779c90c64cd698cddd5394/efficientvit/models/nn/ops.py#L425-L428 Just wondering why padding one element in `v` and then dropping the last element of `out`.