Matrix-Vector Library Designed for Neural Network Construction. cuda (gpu) support, openmp (multithreaded cpu) support, partial support of BLAS, expression template based implementation PTX code generation identical to hand written kernels, and support for auto-differentiation
how to set batch_size value? Default is 32, but when i set it to 16,seems the output result is better than 32, but same epochs==5000, train it need more time.
how to set batch_size value? Default is 32, but when i set it to 16,seems the output result is better than 32, but same epochs==5000, train it need more time.