MobileNet-SSD-TensorRT

To accelerate mobileNet-ssd with tensorRT

TensorRT-Mobilenet-SSD can run 50fps on jetson tx2

Requierments:

1.tensorRT4

2.cudnn7

3.opencv

Run:

cmake .
make
./build/bin/mobileNet

Reference:

https://github.com/saikumarGadde/tensorrt-ssd-easy

I replaced depthwise with group_conv,because group_conv has been optimized in cudnn7

I retrianed mobileNet-SSD,my number of classfication is 5

TODO:

To save serialized model
To solve the bug of getting different result with same input
The bottleneck of time cost lies in the decoding of pictures. "imread" cost too much ,to resolve it.
To modify the architecture, decrease the time cost

Name		Name	Last commit message	Last commit date
Latest commit History 14 Commits
CMakeFiles		CMakeFiles
build		build
model		model
testPic		testPic
util		util
.DS_Store		.DS_Store
CMakeCache.txt		CMakeCache.txt
CMakeLists.txt		CMakeLists.txt
Makefile		Makefile
README.md		README.md
cmake_install.cmake		cmake_install.cmake
common.cpp		common.cpp
common.h		common.h
cudaUtility.h		cudaUtility.h
kernel.cu		kernel.cu
main.cpp		main.cpp
mathFunctions.cpp		mathFunctions.cpp
mathFunctions.cu		mathFunctions.cu
mathFunctions.h		mathFunctions.h
mobileNetSSDTensorRT-Qt.pro		mobileNetSSDTensorRT-Qt.pro
mobileNetSSDTensorRT-Qt.pro.user		mobileNetSSDTensorRT-Qt.pro.user
mobileNet_screenshot_17.12.2018.png		mobileNet_screenshot_17.12.2018.png
pluginImplement.cpp		pluginImplement.cpp
pluginImplement.h		pluginImplement.h
tensorNet.cpp		tensorNet.cpp
tensorNet.h		tensorNet.h

Provide feedback