Zhe Chen
Do you mean https://github.com/OpenGVLab/InternImage/blob/master/segmentation/image_demo.py?
你好，DCNv3暂时还不支持windows系统
Thanks for your feedback. This error may be due to unenough GPU memory. How much GPU memory do you have? ------------------ Oh, I see, you have a single gpu A6000...
Hi, you can install DCNv3 following these instructions: - Compile CUDA operators ``` cd ./ops_dcnv3 sh ./make.sh # unit test (should see all checking is True) python test.py ``` -...
Hello, we are preparing the onnx for segmentation inference, could you please wait for some days?
You can change `core_op='DCNv3'` to `core_op='DCNv3_pytorch'` in the config to support CPU.
> same problem while using torch==1.9.1+cu111, and ./make.sh doesnt work as well Hi, please install PyTorch>=1.10.0.
> We will release pre-compiled whl packages today. Stay tuned. https://github.com/OpenGVLab/InternImage/releases/tag/whl_files
You should copy the whole folder of dcnv3_ops in your project, and then `from ops_dcnv3 import modules as opsm`. https://github.com/OpenGVLab/InternImage/tree/master/detection/ops_dcnv3 You can refer to this file to use DCNv3 in...
> set the "Classes" as 5 and reduce_zero_label=False