Xia Li

SeparableConvBnRelu instead of ConvBnRelu

2

https://github.com/lingtengqiu/Deeperlab-pytorch/blob/df58590f7f28e61956c62b676c3fc7006ed46174/model/deeperlab.py#L118 As written in the paper, `Similar to the encoder, the decoder uses two large kernel (7 x 7) depthwise convolutions to further increase the receptive field.` There should be...

The wrong imp of the inner-product operation

3

In Equation 2 of the paper, the query and the key are fed into inner-product operation, instead of point multiplication. So the follow line https://github.com/leaderj1001/Stand-Alone-Self-Attention/blob/e0a168ef8d4a7b93ae706a7d7c68b982e112821e/attention.py#L48 should be `out = (q_out...

A possible mistake in computing TPS

1

Hi, Aliaksandr. Your code is really nice. However, I find a small mistake here from L118 to L120: https://github.com/snap-research/articulated-animation/blob/db2c2135273f601a370e2b62754f9bb56cfd25d5/modules/model.py#L118 https://github.com/snap-research/articulated-animation/blob/db2c2135273f601a370e2b62754f9bb56cfd25d5/modules/model.py#L120 Shouldn't it be `result = (distances ** 2).sum(-1)`? With which...

Useful add-ons for Euler usage. Prefer not to merge it into master. Instead, just keep this PR as a reference

I see for validation on the PASCAL VOC dataset, you first train with stride 16, and then finetune with stride 8. But as I understood and experimented, original paper of...

Thanks for your paper and code! I have a problem here, which confused me a lot. KL (P || Q) = E_P[log(P/Q)] = \sum_i [p_i * (log p_i - log...