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

performance improvements for yolo based networks,significant reduction in inference time can be seen yolo4tiny ,yolo4 and minor reduction in inference time can be seen in yolo4_berkeley_f1 and yolo4_berkeley - tested with a batchsize of 1 and 2 and on gtx 1070,it is possible that the performance improvement is more signficant in newer hardware

Browse Source
This commit is contained in:
perseusdg
2022-01-03 13:52:16 +05:30
parent a4781244f4
commit dcf4054bc6
2 changed files with 57 additions and 44 deletions
Download Patch File Download Diff File Expand all files Collapse all files
include/tkDNN/NetworkRT.h
+1 -1
View File
@@ -93,7 +93,7 @@ public:
nvinfer1::IPluginV2Layer* convert_layer(nvinfer1::ITensor *input, Region *l);
nvinfer1::ILayer* convert_layer(nvinfer1::ITensor *input, Shortcut *l);
nvinfer1::IPluginV2Layer* convert_layer(nvinfer1::ITensor *input, Yolo *l);
nvinfer1::IPluginV2Layer* convert_layer(nvinfer1::ITensor *input, Upsample *l);
nvinfer1::IResizeLayer* convert_layer(nvinfer1::ITensor *input, Upsample *l);
nvinfer1::ILayer* convert_layer(nvinfer1::ITensor *input, DeformConv2d *l);
#if NV_TENSORRT_MAJOR > 5 && NV_TENSORRT_MAJOR < 8