no kernel image is available for execution on the device

[YanhaoZhang]

Thanks for releasing the code. I found that after switching the device to cuda:0, I got the following error. May I ask for any suggestions, please?

  File "/home/yanhao/anaconda3/envs/nailseg/lib/python3.8/site-packages/torch/nn/modules/batchnorm.py", line 148, in forward
    self.num_batches_tracked.add_(1)  # type: ignore[has-type]
RuntimeError: CUDA error: no kernel image is available for execution on the device

[EdsonWong]

Thanks for releasing the code. I found that after switching the device to cuda:0, I got the following error. May I ask for any suggestions, please?

  File "/home/yanhao/anaconda3/envs/nailseg/lib/python3.8/site-packages/torch/nn/modules/batchnorm.py", line 148, in forward
    self.num_batches_tracked.add_(1)  # type: ignore[has-type]
RuntimeError: CUDA error: no kernel image is available for execution on the device

your cuda and pytorch version is not suitable to your GPU

[ademakdogan]

Thanks for releasing the code. I found that after switching the device to cuda:0, I got the following error. May I ask for any suggestions, please?

  File "/home/yanhao/anaconda3/envs/nailseg/lib/python3.8/site-packages/torch/nn/modules/batchnorm.py", line 148, in forward
    self.num_batches_tracked.add_(1)  # type: ignore[has-type]
RuntimeError: CUDA error: no kernel image is available for execution on the device

Verify that your GPU is compatible with the CUDA version and PyTorch requirements. Older or incompatible GPUs may encounter issues with CUDA execution.