Accelerated by another 5% using FP16/32 Batch-norm for Tensor Cores.

AlexeyAB

2018-04-16 9bae70b22549b68f5cdeece8b6c3b3de00c22714

 src/batchnorm_layer.h

@@ -12,6 +12,8 @@
#ifdef GPU
void forward_batchnorm_layer_gpu(layer l, network_state state);
void backward_batchnorm_layer_gpu(layer l, network_state state);
void pull_batchnorm_layer(layer l);
void push_batchnorm_layer(layer l);
#endif

#endif