CUDA error: no kernel image is available for execution on the device
## pytorch reinstall (keras) [min@ai grecognition]$ conda uninstall pytorch Collecting package metadata (repodata.json): done Solving environment: done ==> WARNING: A newer version of conda exists. <== current version: 4.10.3 latest version: 4.13.0 Please update conda by running $ conda update -n base -c defaults conda ## Package Plan ## environment location: /home/min/anaconda3/envs/keras removed specs: - pytorch The following packages will be downloaded: package | build ---------------------------|----------------- debugpy-1.5.1 | py37h295c915_0 1.7 MB entrypoints-0.4 | py37h06a4308_0 16 KB ipython-7.31.1 | py37h06a4308_0 1013 KB jedi-0.18.1 | py37h06a4308_1 980 KB jupyter_client-7.2.2 | py37h06a4308_0 190 KB jupyter_core-4.10.0 | py37h06a4308_0 75 KB nest-asyn