search

javiribera / locating-objects-without-bboxes

PyTorch code for "Locating objects without bounding boxes" - Loss function and trained models
Other
249 stars 52 forks source link

need help for validation and locate.py #13

Closed 645873229 closed 4 years ago

645873229 commented 4 years ago

the train.py and locate.py are runing .new problem occurs.I found gpu is used when training.but code gets slow when validation.why gpu is not be used when validation. when locate.py is runing ,it has the same problem with the validation.I am sure my gpu is usable and I have inputed right arguments

javiribera commented 4 years ago

Only the neural network can use GPU. The thresholding and EM can only use CPU. What happens if you run it with --tau -1? Can you provide timings with and without --tau -1?

Acmenwangtuo commented 4 years ago

I have the same question ,the speed of validation is too slow

javiribera commented 4 years ago

Closing due to inactivity. If this is still an issue, reopen and post all the info requested in https://github.com/javiribera/locating-objects-without-bboxes#creating-an-issue