WisconsinAIVision / yolact_edge

The first competitive instance segmentation approach that runs on small edge devices at real-time speeds.
MIT License
1.28k stars 273 forks source link

How to run inference on cpu? #145

Open afrin321 opened 3 years ago

afrin321 commented 3 years ago

Hello, can yolact_edge inference be run on cpu with saved weights?

I tried to follow the colab notebook code in jupyter notebook. It is giving an error saying "Torch not compiled with Cuda enabled.

Please help. Thank you.

haotian-liu commented 3 years ago

Yes, but you need to modify the code and make sure all the tensors / model weights are on the CPU.

Gx1n commented 3 years ago

have you modified your code and trained on cpu?