[Bug]: 2台机器相同的 towhee 版本0.6.1, pipeline('towhee/image-embedding-resnet50') 下载不同的pth

[angelapytao]

Is there an existing issue for this?

• [X] I have searched the existing issues

Current Behavior

2台机器相同的 towhee 版本0.6.1, pipeline('towhee/image-embedding-resnet50') 下载不同的pth.
一台下载日志：
2022-07-13 16:36:30,310 ｜ INFO ｜ helpers.py ｜ load_pretrained ｜ 188 ｜ Loading pretrained weights from url (https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-rsb-weights/resnet50_a1_0-14fe96d1.pth)

另外一台下载日志：
2022-07-13 16:18:17,810 - 140194222282496 - helpers.py-helpers:183 - INFO: Loading pretrained weights from url (https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-weights/resnet50_ram-a26f946b.pth)
Downloading: "https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-weights/resnet50_ram-a26f946b.pth" to /root/.cache/torch/hub/checkpoints/resnet50_ram-a26f946b.pth


### Expected Behavior

下载相同的pth

### Steps To Reproduce

_No response_

### Environment

```markdown
- Towhee version(e.g. v0.1.3 or 8b23a93):0.6.1
- OS(Ubuntu or CentOS):CentOS
- CPU/Memory:
- GPU:  GeForce RTX 3090
- Others: (NVIDIA-SMI 460.73.01    Driver Version: 460.73.01    CUDA Version: 11.2)

Anything else?

No response

[jaelgu]

@angelapytao Can you check timm version on both machines? pip show timm

[angelapytao]

diff timm, maybe the reason？

[jaelgu]

diff timm, maybe the reason？

I think so. Can you try timm 0.5.4 on both machines?

[GuoRentong]

@angelapytao We suggest writing issues in English, so that more people in our community can read this. Thanks.

[stale[bot]]

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions. Rotten issues close after 30d of inactivity. Close the stale issues and pull requests after 7 days of inactivity. Reopen the issue with /reopen.