could this eval by CPU?

Tramac / Lightweight-Segmentation

Lightweight models for real-time semantic segmentation(include mobilenetv1-v3, shufflenetv1-v2, igcv3, efficientnet).

Apache License 2.0

352 stars 77 forks source link

could this eval by CPU? #13

Closed sybil12 closed 4 years ago

sybil12 commented 4 years ago

rt, I want to eval at a CPU machine, how to do it?

Tramac commented 4 years ago

Please change this to model.load_state_dict(torch.load(get_model_file('mobilenet_%s_best_model' % (acronyms[dataset]), root=root)), map_location='cpu') if you want to use mobilenet.