From dda993f3dd3c753dfd580d485b39c1001830fee4 Mon Sep 17 00:00:00 2001
From: AlexeyAB <alexeyab84@gmail.com>
Date: Thu, 22 Feb 2018 19:54:40 +0000
Subject: [PATCH] Use half_float16 instead of float32 if defined both CUDNN and CUDNN_HALF. Use Tensor Cores.
---
src/region_layer.c | 14 +++++++++-----
1 files changed, 9 insertions(+), 5 deletions(-)
diff --git a/src/region_layer.c b/src/region_layer.c
index f7eaef6..e8bbd5c 100644
--- a/src/region_layer.c
+++ b/src/region_layer.c
@@ -53,6 +53,8 @@
void resize_region_layer(layer *l, int w, int h)
{
+ int old_w = l->w;
+ int old_h = l->h;
l->w = w;
l->h = h;
@@ -63,11 +65,13 @@
l->delta = realloc(l->delta, l->batch*l->outputs*sizeof(float));
#ifdef GPU
- cuda_free(l->delta_gpu);
- cuda_free(l->output_gpu);
+ if (old_w < w || old_h < h) {
+ cuda_free(l->delta_gpu);
+ cuda_free(l->output_gpu);
- l->delta_gpu = cuda_make_array(l->delta, l->batch*l->outputs);
- l->output_gpu = cuda_make_array(l->output, l->batch*l->outputs);
+ l->delta_gpu = cuda_make_array(l->delta, l->batch*l->outputs);
+ l->output_gpu = cuda_make_array(l->output, l->batch*l->outputs);
+ }
#endif
}
@@ -170,7 +174,7 @@
for (b = 0; b < l.batch; ++b){
for(i = 0; i < l.h*l.w*l.n; ++i){
int index = size*i + b*l.outputs;
- softmax(l.output + index + 5, l.classes, 1, l.output + index + 5);
+ softmax(l.output + index + 5, l.classes, 1, l.output + index + 5, 1);
}
}
}
--
Gitblit v1.10.0