Closed Yifan-Gao closed 7 years ago
Hi, Backpropagation is supported with both the theano and tensorflow backend.
Both libraries perform the backpropagation step automatically (you may want to read up on automatic differentiation / symbolic differentiation). As such it is not necessary to write extra code for the backwards pass.
I'm new to keras. It seems the spp pooling layer and RoI pooling layer just support forward operation. Can it be used to train a new network via back propagation?