T2T-ViT

T2T-ViT copied to clipboard

I see that the entire main.py file also does not change arg.num_gpu to a value greater than 1. Under what circumstances does this value change to a value greater than...

yu868

Fail to obtain the reported MACs for performer-based models.

5

Hi, Thank you for this repo! It is really helpful. However, we fail to obtain the reported MACs for performer-based models (T2T-ViT-7/10/12). **Importantly, we found a strange phenomenon.** Both the...

blackfeather-wang

TransferLearning Cifar10

3

thanks for your nice work! I have some issue following the repo and run the code for transfer learning. I get the pretrain model for cifar10 from the link and...

maryamag85

gained 0.094 for eval_top1, and 0.33 for eval_top5, after 36-epoch training on 8 gpus

4

hi, would you mind releasing the training log for T2t-vit-t-14 training with 8 GPUs? I tried to rerun the script for training T2t-vit-t-14 with 8 GPUs. It gained 0.094 for...

CheerM

Downloads all say "tar: This does not look like a tar archive" when I try to un-tar

2

I've tried several tools, and downloaded all the files just to see if maybe the first one was corrupt, but every file I try I get this error (from multiple...

lowfuel

[maybe a bug] loss nan

4

https://github.com/yitu-opensource/T2T-ViT/blob/main/models/token_performer.py#L18 My code has turned on fp16, so the 1e-8 on this line to prevent division by 0 is not enough for my code... the loss of the network calculation...

xmy0916

training T2T-ViT is slower than training resnet?

1

Have you compaired the inference speed of T2T-ViT and resnet? At the same accuracy, which famaliy of models achieve higher FPS?

lixincn2015

'bool' object has no attribute 'pos_embed

2

 When I want to use the pretrained model, I got a problem likes this. Could you tell me how to slove it? Thanks!

helloworld-wu

My case to solve NaN loss when using AMP

2

When I tried to train t2t-vit-14 with hyperparameter that was released, I had a NaN loss problem. After AMP was turned off, loss became stable. But, I want to know...

CreamNuts

chenhui2016