search

kentaroy47 / frcnn-from-scratch-with-keras

:collision:Faster R-CNN from scratch written with Keras
Apache License 2.0
168 stars 106 forks source link

@tossy-yossy @mtlouie-unm @franyoadam #38

Closed jia101728 closed 5 years ago

jia101728 commented 5 years ago

@tossy-yossy @mtlouie-unm @franyoadam This issues have been fixed. The cause was the positive-negative ratio of the detections. I fixed the number of RPNs so that the postive-negative ratio will be about 1:3, as in other implementations. Please pull the newest version to activate this.

The training will be stable with using pretrained RPN models.

The pretrained RPN for VGG is uploaded to: https://drive.google.com/file/d/1teuXIRN4mvmbnIfWlxAAM69hJEceTpUm/view?usp=sharing The trained vgg frcnn model is uploaded (is underfitting..): https://drive.google.com/file/d/1IgxPP0aI5pxyPHVSM2ZJjN1p9dtE4_64/view?usp=sharing

Here is the example command.

python train_frcnn.py --network vgg -p to/your/voc --load rpn-mode.pth

Originally posted by @kentaroy47 in https://github.com/kentaroy47/frcnn-from-scratch-with-keras/issues/6#issuecomment-532649121