CRATE
CRATE copied to clipboard
Code for CRATE (Coding RAte reduction TransformEr).
I really appreciate your work bro, will you release more pretrained weights in the future?
在attention代码中,我发现有一个名为to_out的操作,我无法理解这个操作是用来实现什么功能的 具体代码为: class Attention(nn.Module): def __init__(self, dim, heads = 8, dim_head = 64, dropout = 0.): super().__init__() inner_dim = dim_head * heads project_out = not (heads == 1 and dim_head...
I'm really appreciate your work.I would like to draw a graph similar to Figure 13 and 14. Can you provide me with the code?
Thanks for the great work! I noticed there is model size difference ~300MB (crate-demo.pth) vs. ~100MB (re-trained model_best.pth.tar). Because I retrained the model using the repo code here but the...
where can i get the pretrained CRATE weight?
Not sure which one was meant to be the correct one. Changing help message is definitely safer.
Does that mean what I need to do is training a specific unsupervised task like MAE? Does that equal contrastive learning?
Firstly, thank you for your valuable work. The URL (https://drive.google.com/file/d/1hYgDJl4EKHYfKprwhEjmWmWHuxnK6_h8/view?usp=share_link) for weights for CRATE-SMALL on ImageNet-1K is not working. The G-Drive link says "URL does not exist." Could you please...