Strange behavior in "rpn_to_roi" function

kentaroy47 / frcnn-from-scratch-with-keras

:collision:Faster R-CNN from scratch written with Keras

Apache License 2.0

168 stars 107 forks source link

Strange behavior in "rpn_to_roi" function #61

Open k1l1 opened 4 years ago

k1l1 commented 4 years ago

I have seen a strange behaviour when calculating y_rpn_regr with a ground truth (green) and apply rpn_to_roi() on it, it does not project on ground truth again. (bbox with prob=1 is red)

I made an example in my fork https://github.com/k1l1/frcnn-from-scratch-with-keras/blob/7da9fe4d512a41fc37efe42bcba429fea331f091/rpn_error_example.py#L4 where I simply reversed the regression myself.

Figure_1

Can you take a look? Is this an implementation error or a design limitation?

kentaroy47 commented 4 years ago

thanks for raising this, since this seems to be an implementation error. I will look into this.

FrancescoManigrass commented 3 years ago

did you solve ?