Hossein Jafarinia

[Bug]:

4

### 请认真检查以下清单中的每一项 - [X] 已经搜索过，没有发现类似issue - [x] 已经搜索过文档，没有发现相关内容 - [x] 已经尝试使用过最新版，问题依旧存在 - [x] 使用的是官方版本（未替换及修改过安装目录程序文件） ### 软件版本 0.20.5 ### 操作系统 macOS arm64(M1,M1*) ### 系统版本 macOS 12.6 ### 问题描述 macOS says: “Clash...

The average running time for each epoch in full-tuning is 2 minutes and for adaptformer 2:30 on a single gpu device with RTX 3090 and the results (as we can...

Hi I have a question about your pretreined mae vitb16 weights. When I use "https://github.com/ShoufaChen/AdaptFormer/releases/download/v0.1/mae_pretrain_vit_b.pth" which is the one on your GitHub repo and train on Cifar100 for 1 epoch...

Unstable learning

2

Hi Thank you for your great work. I have a problem with training of your model. This is the curve for score and test (validation) loss for some different hyper...

Overlapping patches

3

Hi Thanks for the wonderful paper and very clear code. I have a question. Do you think that your model will still work if we give it overlapping patches? (I...

Multiple Instance Learning

1

Hi. Thanks again for the wonderful work. One thing that is extremely vague in your paper is what exactly the "Model" in Figure 1? Is is a multiple instance method?...

Has anyone coded this in Pytroch?

How to compute the loss

1

Hi Thanks for the great work. I'm trying to implement a "cancer"/"healthy" classifier from your code on PyTorch but there is something I don't understand about training the model itself...

Hi. Thanks for the great work. In you paper in Stage 2: 4096 × 4096 Region-Level Pretraining you state: We apply standard dropout (p = 0.10) to all views following...

PMSN Loss

3

Hi, Thank you for the wonderful repository, and I truly appreciate your implementation of PMSN loss—something even the original author did not provide. As you can see, the loss function...