chinayi / asrf_with_asformer Goto Github PK

I noticed that

asb = [
    copy.deepcopy(Decoder(n_layers, 2, 2, n_features, n_classes, n_classes, att_type='sliding_att', alpha=exponential_descrease(s))) for s in range(n_stages_asb - 1)
]

and

brb = [
    SingleStageTCN(1, n_features, 1, n_layers) for _ in range(n_stages_brb - 1)
]

What determines this difference? Why not use Decoder in the brb branch as well?

Thanks!

在您的project中没有找到train.py文件，请问作者大大可以提供一下嘛

In the paper it mentioned that

To demonstrate its effectiveness, we conduct a non-hierarchical version by setting the size of the local window in all attention layers to 512, which is the largest window size in the last encoder/decoder block (out of memory if we directly set the size of the local window in all attention layers to the video length).
I was not able to figure out where in the code the attention layer has windows of 512. can you please point me to the right direction?