WindVChen

It seems that SAHI is a inference strategy and have no much relation with the training phase, thus if it can work with YOLOv5, it should also work with DRENet,...

Hi, actually I have not tried to apply DRENet with larger backbone than YOLOv5s previously. But if you want to, it is very easy. Just change the **depth_multiple** and **width_multiple**...

For applying different size of YOLOv5, such as YOLOv5m, YOLOv5l, etc., you only need to change these two params in DRENet.yaml:  E.g., YOLOv5s is 0.33 and 0.5 respectively, YOLOv5m...

I'm glad that the method can help. Just feel free to use it as long as the source is indicated.

@tuoli9 同样的问题，感觉skip实际应该设成1吧

Hi @AndPuQing, Thank you for submitting this excellent PR! I've thoroughly tested the code, and it seamlessly integrates with the latest diffusers (0.25.0). However, during my testing, I observed a...

Hi @LinyeLyuNeo , You can run `pip install pretrainedmodels` to solve it.

Hi @jS5t3r , Thank you for pointing this out. I've just updated the code, and I'm optimistic that this update resolves the resolution parameter setting issue. Regarding parameter optimization, I...

Hi @youyuanyi , You can refer to the commit [here](https://github.com/WindVChen/DiffAttack/commit/fc8b7949dd5b5feaee1db2ed697f72c959c7b84a) for the details of the changes. Hope this can help.

Hi @Nikos-86, Thank you for reaching out. While I haven't extensively explored manipulating 1D data, I'll share my thoughts to hopefully bring some reference. In theory, DiffAttack should be adaptable...