Closed ksv87 closed 1 month ago
你在报错的load_tuning_state位置里torch.load加上参数weights_only=True
试一下
I encountered the same problem. Adding the parameter weights_only=True
still doesn't solve the issue.
D:\Projects\ObjectDetectionStudy\RT-DETR\venv\lib\site-packages\torch_utils.py:776: UserWarning: TypedStorage is deprecated. It will be removed in the future and UntypedStorage will be the only storage class. This should only matter to you if you are using storages directly. To access UntypedStorage directly, use tensor.untyped_storage() instead of tensor.storage()
return self.fget.get(instance, owner)()
Traceback (most recent call last):
File "D:\Projects\ObjectDetectionStudy\RT-DETR\rtdetrv2_pytorch\tools\export_onnx.py", line 99, in
I updated weight
link. You can remove downloaded weight
firstly and try it agian.
@Jerry-Chang975 @ksv87
I updated weight link. You can remove downloaded weight firstly and try it agian. @lyuwenyu thanks! it's helped!
Dont work tuning from checkpoint from README.txt
ModuleNotFoundError: No module named 'cvperception'
To Reproduce
python tools\train.py -c configs\rtdetrv2\rtdetrv2_r18vd_120e_coco.yml --use-amp -t "D:\research\RT-DETR\rtdetrv2_pytorch\rtdetrv2_r18vd_120e_coco_rerun_48.1.pth"