Have you guys ever meet the error Error: can't convert cuda:0 device type tensor to numpy. Use Tensor.cpu() to copy the tensor to host memory first. when running the demo bash test_autoencoder_single_gpu.sh? I havn't modify anything and I locate the error inside the extract_geometry_by_diffdmc function. How to solve this?
Have you guys ever meet the error
Error: can't convert cuda:0 device type tensor to numpy. Use Tensor.cpu() to copy the tensor to host memory first.when running the demobash test_autoencoder_single_gpu.sh? I havn't modify anything and I locate the error inside theextract_geometry_by_diffdmcfunction. How to solve this?