Do you mean the method theano is using? Anyway, the performance bottleneck often lies in matrix multiplication or 2D-CNN (which can be reduced to matmul). Compiler autograd wouldn't save much time.
Do you mean the method theano is using? Anyway, the performance bottleneck often lies in matrix multiplication or 2D-CNN (which can be reduced to matmul). Compiler autograd wouldn't save much time.