I am trying to set up the SAM-Model from segment_anything_fast by pytorch. I have followed the installation instructions and also added “export SEGMENT_ANYTHING_FAST_USE_FLASH_4=0” as an environment variable.
I have read in an image with cv2 and rand the cv2.cvtColor on it. Now I’m trying to generate masks but every time I run it, I get a BackendCompilerFailed-Error with the following message:
“You can suppress this exception and fall back to eager by setting:
import torch._dynamo
torch._dynamo.config.suppress_errors = True”
Even after setting this to true it throws another error.