Detection_eval of shared pretrained model is very less

MhLiao / TextBoxes_plusplus

TextBoxes++: A Single-Shot Oriented Scene Text Detector

Other

956 stars 281 forks source link

Detection_eval of shared pretrained model is very less #133

Open manogna-s opened 5 years ago

manogna-s commented 5 years ago

I evaluated the pretrained model 'model_icdar15.caffemodel' shared on ICDAR15 test set with 500 images . The detection_eval is observed to be:

Resolution: 768x768 , IoU threshold: 0.5, detection_eval=0.463 Resolution: 1024x1024 , IoU threshold: 0.5, detection_eval=0.469

However, in the paper the precision is mentioned to be 0.872 for 1024x1024 while I get 0.469. The metrics used are Pascal VOC based 11-point method to get mAP right?

github14343 commented 4 years ago

Have you solved the problem? Thanks!