sanhai77
sanhai77
ok, we use rpn_output.detach(). but why? is it possible to derivate roi() w.r.t the coordinate? > d(roi(feature_map , Rois))/d{x1,y1,x2,y2} = exist? i mean the crooping part of the roi pool....
I apologize for my many question. but i am confused and i cant give my answer during any research. but roi pooling involves non-differentiable operations like indexing(quantizing the coordinate(like 3.5)...
Thank you for the quick and complete answer
thanks for reply i mean the back path is back path as follows? > loss----> sibling(reg& classifier)----> FC---->FC---->RoiPooling---->((((DECODER))))----> 1x1_Conv_sibling(reg)---->3x3_Conv------>last-vgg-layer---->second-vgg-layer I want to find a path that can compute derivative of...
i just want know the gradients flow path in the break point(between RPN and detector). Is what I understood correct? > 1- gradients flow starting from last output layers of...
Sorry Is there the second direct backward route from the Roi pooling layer to the vgg? i know forward path. but i am confused in the break point(for gradient flow...
tanks. understood. but we use rpn_output.detach(). but why? is it possible to derivate roi(feature_map , Rois) w.r.t the coordinate? > d(roi(feature_map , Rois))/d{x1,y1,x2,y2} = exist? in [here](https://github.com/trzy/FasterRCNN/blob/1ab2d3cd1d00eee5a775987cefe963f9718b59c4/pytorch/FasterRCNN/models/detector.py#L72) i mean the...
I apologize for my many question. but i am confused and i cant give my answer during any research. but roi pooling involves non-differentiable operations like indexing(quantizing the coordinate(like 3.5)...
thank you for attention.