Open AIprogrammer opened 4 years ago
@AIprogrammer " In order to re-duce the loss of efficiency as much as possible, we do notchange convolutional layers in backbone, and only replacethe 1x1 convolution layer in FPN and the first convolutionlayer in detection head with CoordCon" from pp-yolo paper.
Does anyone know where should we add the coord conv layers if we do regression task?