PyTorch-Pretrained-ViT
PyTorch-Pretrained-ViT copied to clipboard
lukemelas
Vision Transformer (ViT) in PyTorch
Excuse me, I want to know what are the parameters in transforms.Normalize(, ) when fine-tune on the ImageNet-1k dataset.
In **transformer.py,** in class **MultiHeadedSelfAttention()** we have the var declaration: self.proj_q = nn.Linear(dim, dim) self.proj_k = nn.Linear(dim, dim) self.proj_v = nn.Linear(dim, dim) but wasn't suposed to be Q, K and...
Hey! First of all, thanks for your contribution! I have looked at multiple ViT implementations and yours seems like the most straightforward, well-organized and simple to use. I'd like to...
Hi, I noticed that it: your code: ``` x = self.positional_embedding(x) # b,gh*gw+1,d x = self.transformer(x) # b,gh*gw+1,d ``` Vision Transformer(from https://github.com/lucidrains/vit-pytorch/blob/main/vit_pytorch/vit.py)： ``` x += self.pos_embedding[:, :(n + 1)] x...
Will you release the L_16 pretrained model?
I think that this line is what is stopping a user from creating a custom model. I don't think the referenced variable is available in the scope that it is...
I can't find he evaluation performance in the readme. Do you have them written somewhere?
By some reason, the output of B_16 model is only zeros. I tested B_32 and L_32, seems like they work properly
Hi, I was wondering if there would be a way to load the weights from google's saved checkpoint directly, instead of having to download them. I see that in the...
I was trying to load the whole model with pretrained=True and representation layer = True but I get an error Further inspection by looking at the keys of the state_dict...