Hi, I am new to the use of graphics cards and trying to use a software created by a third party (Cellpose). I have followed the steps they provide on installing Cellpose in an Anaconda environment and setting up the CUDA so that the program can use the GPU. I have an NVIDIA GForce GT 730 which is supposed to work with CUDA.
It recognises I have one, that it is available and can be used. However when it tries to use it I get the following error:
(cellpose) C:\Users\Miguel>python -m cellpose
2023-11-10 17:25:09,037 [INFO] WRITING LOG OUTPUT TO C:\Users\Miguel.cellpose\run.log
2023-11-10 17:25:09,037 [INFO]
cellpose version: 2.2.3
platform: win32
python version: 3.8.18
torch version: 2.1.0
2023-11-10 17:25:09,315 [INFO] ** TORCH CUDA version installed and working. **
GUI_INFO: loading image:
(2421, 2421, 4)
GUI_INFO: auto-adjust enabled, computing saturation levels
2023-11-10 17:26:06,281 [INFO] >> livecell << model set to be used
2023-11-10 17:26:06,287 [INFO] ** TORCH CUDA version installed and working. **
2023-11-10 17:26:06,287 [INFO] >>>> using GPU
2023-11-10 17:26:06,521 [INFO] >>>> model diam_mean = 30.000 (ROIs rescaled to this size during training)
NET ERROR: CUDA error: no kernel image is available for execution on the device
CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.
For debugging consider passing CUDA_LAUNCH_BLOCKING=1.
Compile with TORCH_USE_CUDA_DSA to enable device-side assertions.
Would you be able to help me with this?