how to set arg.weights: when I test the network?

Chiaraplizz / ST-TR

Spatial Temporal Transformer Network for Skeleton-Based Activity Recognition

MIT License

294 stars 57 forks source link

how to set arg.weights: when I test the network? #28

Closed jianghongcheng closed 2 years ago

jianghongcheng commented 3 years ago

Becasue I did not load the model's weight when I test the code, the loss is too large. I am wondering how to load the trained model to test process. Whould you please solve it?

yogeshr59 commented 3 years ago

Hi @jianghongcheng, Assuming from this question you've trained the network. Can you please help me with running the code for the same? I would be greatful.

Chiaraplizz commented 3 years ago

Hi,

You should pass to the model the args.weights by selecting the path where you are storing your weights.

Chiara