Arsalan Younus

You downloaded pkl file is not downloaded correctly You can delete and try redownloading OR download manually from the shared GDrive link.

In your github cloned directory For example: Mine is D:\GitHub\neuspell\data\checkpoints\ This contains all the downloaded models, You do not need to uninstall and install neuspell Just delete weights from this...

``` def dice_loss(args): pred, gt, mask, weights = args pred = pred[..., 0] # weights = (weights - tf.reduce_min(weights)) / (tf.reduce_max(weights) - tf.reduce_min(weights)) + 1. # mask = mask *...

Hi, I was going to start Handwriting training now and thought to ask if someone made any progress on this. It would be really helpful. Thank you.

Did anyone make any progress on this feature?

I have already tried pytorch db_resnet50, It's better but still misses words. I will try fast_base with pytorch and see the results

Yep, It's better at detecting words However, I am back at the overlapping Bboxes from left (if it's not the first word) and right.