Use new BiRefNet with massive training and IoU fine-tuning. f229b07 verified ZhengPeng7 commited on Jul 10
Set presion of torch to high for consistency with training and faster inference. 6be00d8 verified ZhengPeng7 commited on Jun 26
Update the weights to the one for general use with massive training. 21603dc verified ZhengPeng7 commited on Jun 5
Make the comparison effect of the results more obvious (#3) cf6fe1a verified ZhengPeng7 skyatgit commited on Apr 20
Update the approximated time cost from 500s to 40s. The long time cost may be caused by the unnecessary part of our_ref in inference. df154af ZhengPeng7 commited on Mar 14
Adapt the resize to cv2 version to keep consistent with that used in training. 327742a ZhengPeng7 commited on Mar 14
Add option for resolution in text box to do worse but faster prediction. f406b44 ZhengPeng7 commited on Mar 7
