AlexeyAB
2018-04-16 9bae70b22549b68f5cdeece8b6c3b3de00c22714
refs
author AlexeyAB <alexeyab84@gmail.com>
Monday, April 16, 2018 23:51 +0000
committer AlexeyAB <alexeyab84@gmail.com>
Monday, April 16, 2018 23:51 +0000
commit9bae70b22549b68f5cdeece8b6c3b3de00c22714
tree a236c3023ab9078ecbde6b473e0152a5f6a72368 tree | zip | gz | tar | bzip2 | xz
parent 701f4fab63b3f6826ae6095ce32b9b99b3ece203 view | diff
Accelerated by another 5% using FP16/32 Batch-norm for Tensor Cores.
5 files modified
125 ■■■■ changed files
Makefile 1 ●●●● diff | view | raw | blame | history
src/batchnorm_layer.c 28 ●●●● diff | view | raw | blame | history
src/convolutional_kernels.cu 91 ●●●●● diff | view | raw | blame | history
src/convolutional_layer.c 3 ●●●●● diff | view | raw | blame | history
src/layer.h 2 ●●● diff | view | raw | blame | history