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

AlexeyAB

2018-04-16 9bae70b22549b68f5cdeece8b6c3b3de00c22714

 src/utils.h

@@ -25,6 +25,7 @@
#endif
#endif

double what_time_is_it_now();
int *read_map(char *filename);
void shuffle(void *arr, size_t n, size_t size);
void sorta_shuffle(void *arr, size_t n, size_t size, size_t sections);