user41pp comments

Repositories
Issues
Comments

Results 3 comments of


                                            user41pp

Errors enountered when fine tuning models (RuntimeError: No such operator aten::cudnn_convolution_backward_weight)

Update: I downgraded some packages, now it works. New env: ``` PyTorch: 1.10.2+cu111 TorchVision: 0.11.3+cu111 OpenCV: 4.6.0 MMCV: 1.5.3 MMGen: 0.7.1+3542102 MMCV Compiler: GCC 9.4 MMCV CUDA Compiler: 11.1 ```...

TensorRT segmentation probabilities scores

> @user41pp Hi, exporting to onnx with score map(without argmax) is OK and easy to implement, but setting thresholds for each class at runtime is a little confused. Maybe you...

TensorRT segmentation probabilities scores

> @user41pp Hi, if you only need to operate on onnx, it's a customized exporting. You could refer to [here](https://mmdeploy.readthedocs.io/en/latest/07-developer-guide/partition_model.html) for how to get a sub-graph onnx file. We use...