mmr/tkDNN
Archived
1
0
Fork 0
Code Issues 46 Pull Requests 12 Releases 4 Activity

yolov4tiny works on CUDNN

Browse Source 
Signed-off-by: Micaela Verucchi <micaelaverucchi@gmail.com>
This commit is contained in:
Micaela Verucchi
2020-06-30 15:19:03 +02:00
parent 6d9beb1ec5
commit 61aa24c6b7
6 changed files with 328 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/Route.cpp
+7 -3
View File
@@ -5,7 +5,7 @@
namespace tk { namespace dnn {
Route::Route(Network *net, Layer **layers, int layers_n) : Layer(net) {
Route::Route(Network *net, Layer **layers, int layers_n, int groups, int group_id) : Layer(net) {
// copy input layers
if(layers_n > MAX_LAYERS) {
@@ -15,6 +15,8 @@ Route::Route(Network *net, Layer **layers, int layers_n) : Layer(net) {
this->layers[i] = layers[i];
}
this->layers_n = layers_n;
this->groups = groups;
this->group_id = group_id;
//get dims
output_dim.l = 1;
@@ -32,6 +34,7 @@ Route::Route(Network *net, Layer **layers, int layers_n) : Layer(net) {
output_dim.c += layers[i]->output_dim.c;
}
output_dim.c /= this->groups;
input_dim = output_dim;
checkCuda( cudaMalloc(&dstData, output_dim.tot()*sizeof(dnnType)) );
@@ -49,8 +52,9 @@ dnnType* Route::infer(dataDim_t &dim, dnnType* srcData) {
for(int i=0; i<layers_n; i++) {
dnnType *input = layers[i]->dstData;
int in_dim = layers[i]->output_dim.tot();
checkCuda( cudaMemcpy(dstData + offset, input, in_dim*sizeof(dnnType), cudaMemcpyDeviceToDevice));
offset += in_dim;
int part_in_dim = in_dim / this->groups;
checkCuda( cudaMemcpy(dstData + offset, input + this->group_id*part_in_dim, part_in_dim*sizeof(dnnType), cudaMemcpyDeviceToDevice));
offset += part_in_dim;
}
//update data dimensions