-
when I tested demo ```150_16_dinat_l_oneformer_coco_100ep.pth``` with related config ```configs/coco/dinat/oneformer_dinat_large_bs16_100ep.yaml```
I got a ```natten``` error
```Input axes must be g…
-
### System Info
```
accelerate 0.29.3
torch 1.11.0+cu113
transformers 4.39.3
```
### Who can help?
_No response_
### Information
- [X] The offi…
-
> Loading config D:\Program Files\stable-diffusion-webui\extensions\sd-webui-controlnet\annotator\oneformer\configs/ade20k/oneformer_swin_large_IN21k_384_bs16_160k.yaml with yaml.unsafe_load. Your m…
-
@NielsRogge I'm trying to fine-tune Oneformer for instance segmentation and HF throws an exception. Here's a simple reproduction:
[inputs.zip](https://github.com/NielsRogge/Transformers-Tutorials/…
-
Thanks for opensource your fancy work.
I tried to run your code follow your three sh files.
The train script works fine after several tries of the package version in requirements.txt
But there ar…
-
In accordance with the PyTorch
environment and CUDA version you provided, I encountered this error. How can I resolve it? Thank you !
`RuntimeError: CUDA error: CUBLAS_STATUS_INVALID_VALUE when cal…
-
When I trying to reproduce the result, using following command:
`python train_net.py --dist-url 'tcp://127.0.0.1:50163' --num-gpus 2 --config-file configs/coco/swin/oneformer_swin_tiny_bs16_50ep.y…
-
This should load annotations as arrays converted to tensors in a format that can be accepted by the oneformer transformers model. see https://github.com/developmentseed/slickformer/blob/main/notebooks…
-
Hi, thanks for your awesome work!
I am wondering how to train segmentation controlnet with my customed dataset. I noticed that the Predictor of OneFormer must use `BGR` image in pre-trained seg-contr…
-
Hello, first of all, thank you for sharing your amazing work. However, I've noticed a difference in the results between the Hugging Face demo and running the demo.py code from the cloned GitHub reposi…