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

-Modified Dockerfile.base to cudagl

Browse Source 
-Changed demo to take in input from demoConfig.yaml file
-Readme changes for demo.md
This commit is contained in:
perseusdg
2021-11-24 03:39:57 +05:30
parent a8c98e3c31
commit 9cecc5051a
11 changed files with 422 additions and 124 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.gitignore
+1
View File
@@ -21,3 +21,4 @@ scripts/COCO_val2017/*
scripts/COCO_val2017.zip scripts/COCO_val2017.zip
scripts/all_labels.txt scripts/all_labels.txt
/cmake/cuda_script /cmake/cuda_script
/cmake-build-debug/
demo/demo/demo.cpp
+55 -57
View File
@@ -18,64 +18,57 @@ void sig_handler(int signo) {
int main(int argc, char *argv[]) { int main(int argc, char *argv[]) {
std::cout<<"detection\n";
signal(SIGINT, sig_handler); signal(SIGINT, sig_handler);
#ifdef __linux__
std::string config_file = "../demo/demoConfig.yaml";
#elif _WIN32
std::string config_file = "..\\..\\..\\demo\\demoConfig.yaml";
#endif
std::string net = "yolo4tiny_fp32.rt"; if(argc > 1){
#ifdef __linux__ config_file = argv[1];
std::string cfgPath = "../tests/darknet/cfg/yolo4tiny.cfg";
#elif _WIN32
std::string cfgPath = "..\\tests\\darknet\\cfg\\yolo4tiny.cfg";
#endif
#ifdef __linux__
std::string namePath = "../tests/darknet/names/coco.names";
#elif _WIN32
std::string namePath = "..\\tests\\darknet\\names\\coco.names";
#endif
if(argc > 1)
net = argv[1];
#ifdef __linux__
std::string input = "../demo/yolo_test.mp4";
#elif _WIN32
std::string input = "..\\demo\\yolo_test.mp4";
#endif
char ntype = 'y';
if(argc > 2)
input = argv[2];
if(argc > 3)
ntype = argv[3][0];
int n_classes = 80;
if(argc > 4)
n_classes = atoi(argv[4]);
if(argc > 5)
cfgPath = argv[5];
if(argc > 6)
namePath = argv[6];
int n_batch = 1;
if(argc > 7)
n_batch = atoi(argv[7]);
bool show = true;
if(argc > 8)
show = atoi(argv[8]);
float conf_thresh=0.3;
if(argc >= 9)
conf_thresh = atof(argv[9]);
if(n_batch < 1 || n_batch > 64)
FatalError("Batch dim not supported");
if(!show)
SAVE_RESULT = true;
if(ntype == 'c' || ntype == 'm'){
cfgPath = "";
namePath = "";
} }
YAML::Node conf = YAMLloadConf(config_file);
if(!conf){
FatalError("Problem with config file");
}
std::string net = YAMLgetConf<std::string>(conf,"net","yolo4tiny_fp32.rt");
if(!fileExist(net.c_str())) {
FatalError("The given network does not exist. Create the rt first.");
}
#ifdef __linux__
std::string input = YAMLgetConf<std::string>(conf, "input", "../demo/yolo_test.mp4");
std::string cfgPath = YAMLgetConf<std::string>(conf,"cfg_input", "../tests/darknet/cfg/yolo4tiny.cfg");
std::string namePath = YAMLgetConf<std::string>(conf,"name_input","../tests/darknet/names/coco.names");
#elif _WIN32
std::string input = YAMLgetConf(conf, "win_input", "..\\..\\..\\demo\\yolo_test.mp4");
std::string cfgPath = YAMLgetConf(conf,"cfg_win_input","..\\..\\..\\tests\\darknet\\cfg\\yolo4tiny.cfg");
std::string namePath = YAMLgetConf(conf,"name_win_input","..\\..\\..\\tests\\darknet\\names\\coco.names");
#endif
if(!fileExist(input.c_str()))
FatalError("The given input video does not exist.");
char ntype = YAMLgetConf<char>(conf, "ntype", 'y');
int n_classes = YAMLgetConf<int>(conf, "n_classes", 80);
int n_batch = YAMLgetConf<int>(conf, "n_batch", 1);
if(n_batch < 1 || n_batch > 64)
FatalError("Batch dim not supported");
float conf_thresh = YAMLgetConf<float>(conf, "conf_thresh", 0.3);
bool show = YAMLgetConf<bool>(conf, "show", true);
bool save = YAMLgetConf<bool>(conf, "save", false);
tk::dnn::Yolo3Detection yolo; tk::dnn::Yolo3Detection yolo;
tk::dnn::CenternetDetection cnet; tk::dnn::CenternetDetection cnet;
tk::dnn::MobilenetDetection mbnet; tk::dnn::MobilenetDetection mbnet;
@@ -98,6 +91,11 @@ int main(int argc, char *argv[]) {
FatalError("Network type not allowed (3rd parameter)\n"); FatalError("Network type not allowed (3rd parameter)\n");
} }
if(ntype == 'c' || ntype == 'm'){
cfgPath = "";
namePath = "";
}
detNN->init(net,cfgPath,namePath,n_classes,n_batch,conf_thresh); detNN->init(net,cfgPath,namePath,n_classes,n_batch,conf_thresh);
gRun = true; gRun = true;
@@ -109,7 +107,7 @@ int main(int argc, char *argv[]) {
std::cout<<"camera started\n"; std::cout<<"camera started\n";
cv::VideoWriter resultVideo; cv::VideoWriter resultVideo;
if(SAVE_RESULT) { if(save) {
int w = cap.get(cv::CAP_PROP_FRAME_WIDTH); int w = cap.get(cv::CAP_PROP_FRAME_WIDTH);
int h = cap.get(cv::CAP_PROP_FRAME_HEIGHT); int h = cap.get(cv::CAP_PROP_FRAME_HEIGHT);
resultVideo.open("result.mp4", cv::VideoWriter::fourcc('M','P','4','V'), 30, cv::Size(w, h)); resultVideo.open("result.mp4", cv::VideoWriter::fourcc('M','P','4','V'), 30, cv::Size(w, h));
@@ -149,7 +147,7 @@ int main(int argc, char *argv[]) {
cv::waitKey(1); cv::waitKey(1);
} }
} }
if(n_batch == 1 && SAVE_RESULT) if(n_batch == 1 && save)
resultVideo << frame; resultVideo << frame;
} }
@@ -157,7 +155,7 @@ int main(int argc, char *argv[]) {
double mean = 0; double mean = 0;
std::cout<<COL_GREENB<<"\n\nTime stats:\n"; std::cout<<COL_GREENB<<"\n\nTime stats:\n";
std::cout<<"Min: "<<*std::min_element(detNN->stats.begin(), detNN->stats.end())/n_batch<<" ms\n"; std::cout<<"Min: "<<*std::min_element(detNN->stats.begin(), detNN->stats.end())/n_batch<<" ms\n";
std::cout<<"Max: "<<*std::max_element(detNN->stats.begin(), detNN->stats.end())/n_batch<<" ms\n"; std::cout<<"Max: "<<*std::max_element(detNN->stats.begin(), detNN->stats.end())/n_batch<<" ms\n";
for(int i=0; i<detNN->stats.size(); i++) mean += detNN->stats[i]; mean /= detNN->stats.size(); for(int i=0; i<detNN->stats.size(); i++) mean += detNN->stats[i]; mean /= detNN->stats.size();
std::cout<<"Avg: "<<mean/n_batch<<" ms\t"<<1000/(mean/n_batch)<<" FPS\n"<<COL_END; std::cout<<"Avg: "<<mean/n_batch<<" ms\t"<<1000/(mean/n_batch)<<" FPS\n"<<COL_END;
demo/demoConfig.yaml
+22
View File
@@ -0,0 +1,22 @@
# video input
input : "../demo/yolo_test.mp4"
win_input : "..\\..\\..\\demo\\yolo_test.mp4"
#cfg input
cfg_input : "../tests/darknet/cfg/yolo4tiny.cfg"
cfg_win_input : "..\\..\\..\\tests\\darknet\\cfg\\yolo4tiny.cfg"
#name input
name_input : "../tests/darknet/names/coco.names"
name_win_input : "..\\..\\..\\tests\\darknet\\names\\coco.names"
# network config
net : "yolo4tiny_fp32.rt"
ntype : 'y'
n_classes : 80
n_batch : 1
conf_thresh : 0.3
# demo config
show : true
save : false
docker/Dockerfile.base
+121 -38
View File
@@ -1,57 +1,140 @@
FROM nvidia/cuda:11.3.1-devel-ubuntu20.04 FROM nvidia/cudagl:11.3.1-devel-ubuntu20.04
LABEL maintainer "Francesco Gatti"
ENV DEBIAN_FRONTEND=noninteractive LABEL maintainer "TKDNN AUTHORS"
RUN apt-get update && apt-get install libcudnn8-dev=8.2.1.32-1+cuda11.3 libcudnn8=8.2.1.32-1+cuda11.3 libnvinfer-dev=8.0.3-1+cuda11.3 libnvinfer8=8.0.3-1+cuda11.3 LABEL Description="tkDNN+cudagl"
RUN DEBIAN_FRONTEND=noninteractive apt-get update && apt install -y git wget libeigen3-dev libyaml-cpp-dev gcc-9 g++-9 libopengl-dev libgl-dev LABEL com.tkdnn.nvidia.version="11.3.1"
RUN cd /tmp && \
wget https://github.com/Kitware/CMake/releases/download/v3.21.4/cmake-3.21.4-Linux-x86_64.sh && \ ENV DEBIAN_FRONTEND noninteractive
chmod +x cmake-3.21.4-Linux-x86_64.sh && \ ENV CC gcc
./cmake-3.21.4-Linux-x86_64.sh --prefix=/usr/local --exclude-subdir --skip-license && \ ENV CXX g++
rm ./cmake-3.21.4-Linux-x86_64.sh
RUN apt-get update && apt-get install -y \
libblkid-dev && apt-get clean && rm -rf /var/lib/apt/lists/*
RUN apt-get update && apt-get install -y \
libcudnn8-dev=8.2.1.32-1+cuda11.3 \
libcudnn8=8.2.1.32-1+cuda11.3 \
libnvinfer-dev=8.0.3-1+cuda11.3 \
libnvinfer8=8.0.3-1+cuda11.3 && apt-get clean && rm -rf /var/lib/apt/lists/*
RUN apt-get update && apt-get install -y --no-install-recommends \
libblkid-dev \
locales \
lsb-release \
mesa-utils \
git \
nano \
terminator \
wget \
curl \
libssl-dev \
htop \
dbus-x11 \
libqt5opengl5-dev \
libgtk-3-dev \
libvtk7-dev \
libv4l-dev \
tar \
libgoogle-glog-dev \
libgflags-dev \
gfortran-9 \
libtbb-dev \
libgstreamer1.0-dev \
libgstreamer-plugins-base1.0-dev \
libdc1394-22-dev \
libavresample-dev \
libatlas-cpp-0.6-dev \
python3-dev \
gdb \
python3-pip \
unzip libtbb-dev && \
apt-get clean && rm -rf /var/lib/apt/lists/*
RUN apt-get update && apt-get install -y --no-install-recommends \
software-properties-common && apt-get clean && rm -rf /var/lib/apt/lists/*
RUN apt-add-repository universe
RUN apt-get update && apt-get install -y python3-pip python3 openssh-server ssh pyqt5-dev sip-dev && apt-get clean && rm -rf /var/lib/apt/lists/*
RUN pip3 install --upgrade pip
RUN pip3 install --upgrade virtualenv
RUN pip3 install --upgrade paramiko
RUN pip3 install --ignore-installed --upgrade numpy protobuf
RUN cd ~ && mkdir build
RUN cd ~/build && wget https://github.com/Kitware/CMake/releases/download/v3.21.4/cmake-3.21.4.tar.gz && \
tar -xvf cmake-3.21.4.tar.gz && cd cmake-3.21.4 && ./configure --prefix=/usr/local --qt-gui --parallel=12 && \
make -j8 && make install
RUN apt-get update && apt-get install -y automake autoconf pkg-config libevent-dev libncurses5-dev bison && \
apt-get clean && rm -rf /var/lib/apt/lists/
RUN git clone https://github.com/tmux/tmux.git && \
cd tmux && git checkout tags/3.2 && ls -la && sh autogen.sh && ./configure && make -j8 && make install
RUN apt-get update && apt-get install -y zsh && apt-get clean && rm -rf /var/lib/apt/lists/*
RUN wget https://github.com/robbyrussell/oh-my-zsh/raw/master/tools/install.sh -O - | zsh || true
RUN chsh -s /usr/bin/zsh root
RUN git clone https://github.com/sindresorhus/pure /root/.oh-my-zsh/custom/pure
RUN ln -s /root/.oh-my-zsh/custom/pure/pure.zsh-theme /root/.oh-my-zsh/custom/
RUN ln -s /root/.oh-my-zsh/custom/pure/async.zsh /root/.oh-my-zsh/custom/
RUN sed -i -e 's/robbyrussell/refined/g' /root/.zshrc
RUN sed -i '/plugins=(/c\plugins=(git git-flow adb pyenv tmux)' /root/.zshrc
RUN mkdir -p /root/.config/terminator/
COPY assets/terminator_config /root/.config/terminator/config
RUN echo "/usr/local/nvidia/lib" >> /etc/ld.so.conf.d/nvidia.conf && \
echo "/usr/local/nvidia/lib64" >> /etc/ld.so.conf.d/nvidia.conf && \
echo "/usr/local/cuda/lib64" >> /etc/ld.so.conf.d/nvidia.conf
ENV PATH /usr/local/nvidia/bin:/usr/local/cuda/bin:${PATH}
ENV LD_LIBRARY_PATH /usr/local/nvidia/lib:/usr/local/nvidia/lib64:/usr/local/cuda/lib64:/usr/lib:/usr/lib/x86_64-linux-gnu:/usr/local/lib:${LD_LIBRARY_PATH}
ENV NVIDIA_VISIBLE_DEVICES all ENV NVIDIA_VISIBLE_DEVICES all
RUN echo "INSTALL OPENCV" ENV NVIDIA_DRIVER_CAPABILITIES compute,utility,graphics
RUN apt-get install -y build-essential \
unzip \
pkg-config \
libjpeg-dev \ RUN cd ~/build && wget https://github.com/opencv/opencv/archive/4.5.4.tar.gz && tar -xf 4.5.4.tar.gz && rm 4.5.4.tar.gz
libpng-dev \ RUN cd ~/build && wget https://github.com/opencv/opencv_contrib/archive/4.5.4.tar.gz && tar -xf 4.5.4.tar.gz && rm 4.5.4.tar.gz
libtiff-dev \ RUN cd ~/build && \
libavcodec-dev \
libavformat-dev \
libswscale-dev \
libv4l-dev \
libxvidcore-dev \
libx264-dev \
libgtk-3-dev \
libatlas-base-dev \
gfortran-9 \
libtbb-dev \
libgstreamer1.0-dev \
libgstreamer-plugins-base1.0-dev \
libdc1394-22-dev \
libavresample-dev
RUN cd && wget https://github.com/opencv/opencv/archive/4.5.4.tar.gz && tar -xf 4.5.4.tar.gz && rm *.tar.gz
RUN cd && wget https://github.com/opencv/opencv_contrib/archive/4.5.4.tar.gz && tar -xf 4.5.4.tar.gz && rm *.tar.gz
RUN cd && \
cd opencv-4.5.4 && mkdir build && cd build && \ cd opencv-4.5.4 && mkdir build && cd build && \
cmake -D CMAKE_BUILD_TYPE=RELEASE \ cmake -D CMAKE_BUILD_TYPE=RELEASE \
-D CMAKE_INSTALL_PREFIX=/usr/local \ -D CMAKE_INSTALL_PREFIX=/usr/local \
-D INSTALL_PYTHON_EXAMPLES=OFF \ -D INSTALL_PYTHON_EXAMPLES=OFF \
-D INSTALL_C_EXAMPLES=OFF \ -D INSTALL_C_EXAMPLES=OFF \
-D OPENCV_EXTRA_MODULES_PATH='~/opencv_contrib-4.5.4/modules' \ -D OPENCV_EXTRA_MODULES_PATH='~/build/opencv_contrib-4.5.4/modules' \
-D BUILD_EXAMPLES=OFF \ -D BUILD_EXAMPLES=OFF \
-D BUILD_TESTS=OFF \
-D BUILD_PERF_TESTS=OFF \
-D BUILD_DOCS=OFF \
-D WITH_CUDA=ON \ -D WITH_CUDA=ON \
-D WITH_OPENGL=ON \
-D WITH_NVCUVID=ON \
-D CUDA_ARCH_BIN=7.2 \ -D CUDA_ARCH_BIN=7.2 \
-D CUDA_ARCH_PTX="" \ -D CUDA_ARCH_PTX=7.2 \
-D ENABLE_FAST_MATH=ON \ -D ENABLE_FAST_MATH=ON \
-D CUDA_FAST_MATH=ON \ -D CUDA_FAST_MATH=ON \
-D WITH_CUBLAS=ON \ -D WITH_CUBLAS=ON \
-D WITH_CUDNN=ON \
-D WITH_OPENMP=ON \ -D WITH_OPENMP=ON \
-D WITH_NONFREE=ON \
-D WITH_LIBV4L=ON \ -D WITH_LIBV4L=ON \
-D WITH_GSTREAMER=ON \ -D WITH_GSTREAMER=ON \
-D WITH_GSTREAMER_0_10=OFF \ -D WITH_GSTREAMER_0_10=OFF \
-D WITH_TBB=ON \ -D WITH_TBB=ON \
../ && make -j12 && make install ../ && make -j12 && make install && ldconfig
RUN apt clean
RUN cd ~ && rm -rf build
RUN cd ~ && mkdir Development && cd Development && \
git clone https://github.com/ceccocats/tkDNN.git && cd tkDNN && \
mkdir build && cd build && \
cmake -DCMAKE_BUILD_TYPE=Release .. && \
make -j6
RUN apt-get clean && rm -rf /var/lib/apt/lists/*
COPY assets/entrypoint_setup.sh /
ENTRYPOINT ["/entrypoint_setup.sh"]
CMD ["terminator"]
docker/README.md
+1 -4
View File
@@ -9,13 +9,10 @@ docker build -t tkdnn:build -f Dockerfile .
# make nvidia docker working # make nvidia docker working
# follow this guide: https://github.com/NVIDIA/nvidia-docker # follow this guide: https://github.com/NVIDIA/nvidia-docker
# dowload tensorrt
# from: https://developer.nvidia.com/compute/machine-learning/tensorrt/secure/7.0/7.0.0.11/local_repo/nv-tensorrt-repo-ubuntu1804-cuda10.2-trt7.0.0.11-ga-20191216_1-1_amd64.deb
# build image # build image
docker build -t ceccocats/tkdnn:latest -f Dockerfile.base . docker build -t ceccocats/tkdnn:latest -f Dockerfile.base .
# run image # run image
docker run -ti --gpus all --rm ceccocats/tkdnn:latest bash ./docker_launch.sh
``` ```
docker/assets/entrypoint_setup.sh
Executable
+123
View File
@@ -0,0 +1,123 @@
#! /bin/bash
CMD=
# Functions
# TOOD: Check if we can use: getent passwd $USER to extract all variables
# TODO: Check for valid inputs, cause now it will go through even with bad inputs
check_envs () {
DOCKER_CUSTOM_USER_OK=true;
if [ -z ${DOCKER_USER_NAME+x} ]; then
DOCKER_CUSTOM_USER_OK=false;
return;
fi
if [ -z ${DOCKER_USER_ID+x} ]; then
DOCKER_CUSTOM_USER_OK=false;
return;
else
if ! [ -z "${DOCKER_USER_ID##[0-9]*}" ]; then
echo -e "\033[1;33mWarning: User-ID should be a number. Falling back to defaults.\033[0m"
DOCKER_CUSTOM_USER_OK=false;
return;
fi
fi
if [ -z ${DOCKER_USER_GROUP_NAME+x} ]; then
DOCKER_CUSTOM_USER_OK=false;
return;
fi
if [ -z ${DOCKER_USER_GROUP_ID+x} ]; then
DOCKER_CUSTOM_USER_OK=false;
return;
else
if ! [ -z "${DOCKER_USER_GROUP_ID##[0-9]*}" ]; then
echo -e "\033[1;33mWarning: Group-ID should be a number. Falling back to defaults.\033[0m"
DOCKER_CUSTOM_USER_OK=false;
return;
fi
fi
}
setup_env_user () {
USER=$1
USER_ID=$2
GROUP=$3
GROUP_ID=$4
## Create user
useradd -m $USER
## Copy zsh/sh configs
cp /root/.profile /home/$USER/
cp /root/.bashrc /home/$USER/
cp /root/.zshrc /home/$USER/
## Copy terminator configs
mkdir -p /home/$USER/.config/terminator
cp /root/.config/terminator/config /home/$USER/.config/terminator/config
cp /root/.config/terminator/background.png /home/$USER/.config/terminator/background.png
cp -rf /root/.oh-my-zsh /home/$USER/
cp -rf /root/tkDNN /home/$USER/
rm -rf /home/$USER/.oh-my-zsh/custom/pure.zsh-theme /home/$USER/.oh-my-zsh/custom/async.zsh
ln -s /home/$USER/.oh-my-zsh/custom/pure/pure.zsh-theme /home/$USER/.oh-my-zsh/custom/
ln -s /home/$USER/.oh-my-zsh/custom/pure/async.zsh /home/$USER/.oh-my-zsh/custom/
sed -i -e 's@ZSH=\"/root@ZSH=\"/home/$USER@g' /home/$USER/.zshrc
# Copy SSH keys & fix owner
if [ -d "/root/.ssh" ]; then
cp -rf /root/.ssh /home/$USER/
chown -R $USER:$GROUP /home/$USER/.ssh
fi
## Fix owner
chown $USER:$GROUP /home/$USER
chown -R $USER:$GROUP /home/$USER/.config
chown $USER:$GROUP /home/$USER/.profile
chown $USER:$GROUP /home/$USER/.bashrc
chown $USER:$GROUP /home/$USER/.zshrc
chown -R $USER:$GROUP /home/$USER/.oh-my-zsh
chown -R $USER:$GROUP /home/$USER/tkDNN
## This a trick to keep the evnironmental variables of root which is important!
echo "if ! [ \"$DOCKER_USER_NAME\" = \"$(id -un)\" ]; then" >> /root/.bashrc
echo " cd /home/$DOCKER_USER_NAME" >> /root/.bashrc
echo " su $DOCKER_USER_NAME" >> /root/.bashrc
echo "fi" >> /root/.bashrc
echo "if ! [ \"$DOCKER_USER_NAME\" = \"$(id -un)\" ]; then" >> /root/.zshrc
echo " cd /home/$DOCKER_USER_NAME" >> /root/.zshrc
echo " su $DOCKER_USER_NAME" >> /root/.zshrc
echo "fi" >> /root/.zshrc
## Setup Password-file
PASSWDCONTENTS=$(grep -v "^${USER}:" /etc/passwd)
GROUPCONTENTS=$(grep -v -e "^${GROUP}:" -e "^docker:" /etc/group)
(echo "${PASSWDCONTENTS}" && echo "${USER}:x:$USER_ID:$GROUP_ID::/home/$USER:/bin/bash") > /etc/passwd
(echo "${GROUPCONTENTS}" && echo "${GROUP}:x:${GROUP_ID}:") > /etc/group
(if test -f /etc/sudoers ; then echo "${USER} ALL=(ALL) NOPASSWD: ALL" >> /etc/sudoers ; fi)
}
# ---Main---
# Create new user
## Check Inputs
check_envs
## Determine user & Setup Environment
if [ $DOCKER_CUSTOM_USER_OK == true ]; then
echo " -->DOCKER_USER Input is set to '$DOCKER_USER_NAME:$DOCKER_USER_ID:$DOCKER_USER_GROUP_NAME:$DOCKER_USER_GROUP_ID'";
echo -e "\033[0;32mSetting up environment for user=$DOCKER_USER_NAME\033[0m"
setup_env_user $DOCKER_USER_NAME $DOCKER_USER_ID $DOCKER_USER_GROUP_NAME $DOCKER_USER_GROUP_ID
else
echo " -->DOCKER_USER* variables not set. Using 'root'.";
echo -e "\033[0;32mSetting up environment for user=root\033[0m"
DOCKER_USER_NAME="root"
fi
# Change shell to zsh
chsh -s /usr/bin/zsh $DOCKER_USER_NAME
# Run CMD from Docker
"$@"
docker/assets/terminator_config
+18
View File
@@ -0,0 +1,18 @@
[global_config]
title_transmit_bg_color = "#2e3436"
[keybindings]
[layouts]
[[default]]
[[[child1]]]
parent = window0
type = Terminal
[[[window0]]]
parent = ""
type = Window
[plugins]
[profiles]
[[default]]
background_color = "#282828"
cursor_color = "#aaaaaa"
foreground_color = "#f3f3f3"
palette = "#000000:#aa0000:#00aa00:#c4a000:#3465a4:#75507b:#06989a:#d3d7cf:#88807c:#f15d22:#73c48f:#ffce51:#48b9c7:#ad7fa8:#34e2e2:#eeeeec"
docker/docker_launch.sh
Executable
+9
View File
@@ -0,0 +1,9 @@
xhost local:root
docker run --rm -it --runtime=nvidia --privileged --net=host --cap-add sys_ptrace -d --ipc=host \
-v /tmp/.X11-unix:/tmp/.X11-unix -e DISPLAY=$DISPLAY \
-v $HOME/.Xauthority:/home/$(id -un)/.Xauthority -e XAUTHORITY=/home/$(id -un)/.Xauthority \
-e DOCKER_USER_NAME=$(id -un) \
-e DOCKER_USER_ID=$(id -u) \
-e DOCKER_USER_GROUP_NAME=$(id -gn) \
-e DOCKER_USER_GROUP_ID=$(id -g) \
-v $HOME/.ssh:/home/$(id -un)/.ssh ceccocats/tkdnn
docs/demo.md
+19 -24
View File
@@ -30,31 +30,24 @@ cmake .. -DCMAKE_BUILD_TYPE=Debug -DDEBUG=True
make make
``` ```
Once you have successfully created your rt file, run the demo(yolo) : Once you have successfully created your rt file, run the demo:
``` ```
./demo yolo4_fp32.rt ../demo/yolo_test.mp4 y 80 ../tests/darknet/cfg/yolo4.cfg ../tests/darknet/names/coco.names ./ demo <path-to-config>
``` ```
In general the demo program takes 1 parameter, the ```<path-to-config>``` that is the path to che configuration file. The parameter is optional and its default value is ```"../demo/demoConfig.yaml"```.
To run demo for mobilenet and centernet for the created rt file : The config file is a yaml file with the following attributes:
``` * ```net``` is the rt file generated by a test
./demo mobilenetv2ssd_fp32.rt m 20 * ```input``` is the path to a video file or a camera input (on Linux)
``` * ```win_input``` is the path to a video file or a camera input (on Windows)
* ```ntype``` is the type of network. Thee types are currently supported: ```y``` (YOLO family), ```c``` (CenterNet family) and ```m``` (MobileNet-SSD family)
In general the demo program takes 7 parameters: * ```n_classes``` is the number of classes the network is trained on
``` * ```n_batch``` number of batches to use in inference (N.B. you should first export TKDNN_BATCHSIZE to the required n_batches and create again the rt file for the network).
./demo <network-rt-file> <path-to-video> <kind-of-network> <number-of-classes> <cfg-path> <name-path> <n-batches> <show-flag> <conf-thresh> * ```conf_thresh``` confidence threshold for the detector. Only bounding boxes with threshold greater than conf-thresh will be displayed.
``` * ```show``` if set to 0 the demo will not show the visualization (if n-batches ==1)
where * ```save``` if set to 1 the demo will save the video of the demo into result.mp4 (if n-batches ==1)
* ```cfg_input``` (for linux) \ ```cfg_win_input``` (for windows) is the location of the cfg path of the network for mobilenet and centernet networks use ```" "```
* ```<network-rt-file>``` is the rt file generated by a test * ```name_input``` (for linux) \ ```name_win_input``` (for windows) is the location of the name path of the network for mobilenet and centernet networks use ```" "```
* ```<<path-to-video>``` is the path to a video file or a camera input
* ```<kind-of-network>``` is the type of network. Thee types are currently supported: ```y``` (YOLO family), ```c``` (CenterNet family) and ```m``` (MobileNet-SSD family)
* ```<number-of-classes>```is the number of classes the network is trained on
* ```<cfg-path> ```is the relative path to the config file (only for darknet based networks) used to train the network
* ```<name-path>```is the relative path to the names file (only for darknet based networks) used to train the network
* ```<n-batches>``` number of batches to use in inference (N.B. you should first export TKDNN_BATCHSIZE to the required n_batches and create again the rt file for the network).
* ```<show-flag>``` if set to 0 the demo will not show the visualization but save the video into result.mp4 (if n-batches ==1)
* ```<conf-thresh>``` confidence threshold for the detector. Only bounding boxes with threshold greater than conf-thresh will be displayed.
N.B. By default it is used FP32 inference N.B. By default it is used FP32 inference
@@ -69,7 +62,8 @@ To run the demo with FP16 inference follow these steps (example with yolov3):
export TKDNN_MODE=FP16 # set the half floating point optimization export TKDNN_MODE=FP16 # set the half floating point optimization
rm yolo4_fp16.rt # be sure to delete(or move) old tensorRT files rm yolo4_fp16.rt # be sure to delete(or move) old tensorRT files
./test_yolo4 # run the yolo test (is slow) ./test_yolo4 # run the yolo test (is slow)
./demo yolo4_fp16.rt ../demo/yolo_test.mp4 y 80 ../tests/darknet/cfg/yolo4.cfg ../tests/darknet/names/coco.names #set net: yolo4_fp16.rt in the config file
./demo
``` ```
N.B. Using FP16 inference will lead to some errors in the results (first or second decimal). N.B. Using FP16 inference will lead to some errors in the results (first or second decimal).
@@ -94,7 +88,8 @@ export TKDNN_CALIB_LABEL_PATH=../demo/COCO_val2017/all_labels.txt
export TKDNN_CALIB_IMG_PATH=../demo/COCO_val2017/all_images.txt export TKDNN_CALIB_IMG_PATH=../demo/COCO_val2017/all_images.txt
rm yolo4_int8.rt # be sure to delete(or move) old tensorRT files rm yolo4_int8.rt # be sure to delete(or move) old tensorRT files
./test_yolo4 # run the yolo test (is slow) ./test_yolo4 # run the yolo test (is slow)
./demo yolo4_int8.rt ../demo/yolo_test.mp4 y 80 ../tests/darknet/cfg/yolo4.cfg ../tests/darknet/names/coco.names #set net: yolo4_int8.rt in the config file
./demo
``` ```
N.B. N.B.
include/tkDNN/utils.h
+16 -1
View File
@@ -6,6 +6,8 @@
#include <fstream> #include <fstream>
#include <iomanip> #include <iomanip>
#include <stdlib.h> #include <stdlib.h>
#include <yaml-cpp/yaml.h>
#include "cuda.h" #include "cuda.h"
#include "cuda_runtime_api.h" #include "cuda_runtime_api.h"
@@ -16,7 +18,6 @@
#ifdef __linux__ #ifdef __linux__
#include <unistd.h> #include <unistd.h>
#endif #endif
#include <ios> #include <ios>
@@ -161,5 +162,19 @@ static inline bool isCudaPointer(void *data) {
return cudaPointerGetAttributes(&attr, data) == 0; return cudaPointerGetAttributes(&attr, data) == 0;
} }
inline YAML::Node YAMLloadConf(const std::string& conf_file) {
std::cerr<<"Loading YAML: "<<conf_file<<"\n";
return YAML::LoadFile(conf_file);
}
template<typename T>
inline T YAMLgetConf(YAML::Node conf, std::string key, T defaultVal) {
T val = defaultVal;
if(conf && conf[key]) {
val = conf[key].as<T>();
}
return val;
}
#endif //UTILS_H #endif //UTILS_H
scripts/checkExecTimes.py
+37
View File
@@ -0,0 +1,37 @@
import sys
import pandas as pd
if len(sys.argv) < 3:
print("Error: two csv files are needed, old first new second")
exit(1)
old_perf_file = str(sys.argv[1])
new_perf_file = str(sys.argv[2])
verbose = False
if len(sys.argv) == 4:
verbose = bool(sys.argv[3])
print("Comparing {} vs {}".format(old_perf_file, new_perf_file))
df_old = pd.read_csv (old_perf_file, sep=';', header=None, index_col=0)
df_new = pd.read_csv (new_perf_file, sep=';', header=None, index_col=0)
for index, row in df_new.iterrows():
if index in df_old.index:
if verbose:
print("New: ",row[1], row[2], row[3])
print("Old: ",df_old.loc[index][1], df_old.loc[index][2], df_old.loc[index][3])
print(index, end=': ')
if abs(row[1] - df_old.loc[index][1]) < df_old.loc[index][1]*0.1:
print("similar performance")
elif (row[1] < df_old.loc[index][1]):
print('\x1b[3;30;42m' + 'faster' + '\x1b[0m')
elif (row[1] > df_old.loc[index][1]):
if row[1] > df_old.loc[index][1] + df_old.loc[index][1] * 0.5 :
print('\x1b[3;30;41m' + 'WAY SLOWER' + '\x1b[0m')
else:
print('\x1b[3;30;41m' + 'slower' + '\x1b[0m')