Cheng Han

### Checklist - I have searched related issues but cannot get the expected help. - I have read related documents and don't know what to do. ### Describe the question...

How can I tune the fgvc or vtab datasets as mentioned in Table. 1

3

Thanks for the great work. I am trying to rerun some of the work you mentioned in Table. 1. As I have already gone through the FGVC datasets separately, how...

- Area: Prompt - Title: E^2VPT: An Effective and Efficient Approach for Visual Prompt Tuning - Paper: [https://arxiv.org/abs/2307.13770](https://arxiv.org/abs/2307.13770) - Code: [https://github.com/ChengHan111/E2VPT](https://github.com/ChengHan111/E2VPT)

How can I get the visualization results as in Fig. 2 in the paper

1

Looking forward to your reply. Thanks.

运行pretrain模型时遇到的问题

6

您好我在运行pretrain模型运行predict函数时，出现了shape不匹配的问题，我使用resnet同样进行了测试不会出现 请问我需要先根据你的pretrain模型进行重新训练吗？谢谢 `ValueError: Layer #99 (named "batch_normalization_5"), weight has shape (32,), but the saved weight has shape (64,).`

How many iterations do you train to get the ade20k result

1

Hi, I am curious on how many iterations are you training on ade20k result. I looked for Segformer paper using 160K iters to reach the performance of mIOU 37.4(MiT_B0). But...

Hi, I am wondering if there is any chance you could update the code on induction accuracy on FC7 layer(Seems that section 5.3 is trained on VGG?)