T.H. Tang

I have the same question !

Can I assign multi GPU for the Extraction?

Great it Works! Many thanks~

Do you use Pytorch==0.2.0 and torchvision==0.2.0 ?

Ok, so it seems that the errors are just caused by the different version of packages.

Try local testing

Do you use Pytorch==0.2.0 and torchvision==0.2.0 ?

Once you have the coordinates, functions in OpenCV could deal with the bounding box visualization.

What do you mean **_weights for each training batch_** ?

Yup, the weights are originally used for loss function as described in the paper. However, **there is no improvement regarding AUC score** but makes the training code messy. If you've...