thebears/deepstream_yolo
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
416a8e0108398af4acac829e7f7ad260fd5478eb
deepstream_yolo/readme.md
Marcos Luciano 416a8e0108 Update gen_wts
2022-06-28 01:14:44 -03:00

20 KiB
Raw Blame History

DeepStream-Yolo

NVIDIA DeepStream SDK 6.1 / 6.0.1 / 6.0 configuration for YOLO models

Future updates

  • New documentation for multiple models
  • DeepStream tutorials
  • Native YOLOX support
  • Native PP-YOLO support
  • Dynamic batch-size

Improvements on this repository

  • Darknet CFG params parser (no need to edit nvdsparsebbox_Yolo.cpp or another file)
  • Support for new_coords, beta_nms and scale_x_y params
  • Support for new models
  • Support for new layers
  • Support for new activations
  • Support for convolutional groups
  • Support for INT8 calibration
  • Support for non square models
  • Support for reorg, implicit and channel layers (YOLOR)
  • YOLOv5 4.0, 5.0, 6.0 and 6.1 native support
  • YOLOR native support
  • Models benchmarks (outdated)
  • GPU YOLO Decoder (moved from CPU to GPU to get better performance) #138
  • GPU Batched NMS #142

Getting started

Requirements

DeepStream 6.1 on x86 platform

DeepStream 6.0.1 / 6.0 on x86 platform

DeepStream 6.1 on Jetson platform

DeepStream 6.0.1 / 6.0 on Jetson platform

For YOLOv5 and YOLOR

x86 platform

Jetson platform

Tested models

Benchmarks

New tests comming soon.

dGPU installation

To install the DeepStream on dGPU (x86 platform), without docker, we need to do some steps to prepare the computer.

DeepStream 6.1

1. Disable Secure Boot in BIOS

2. Install dependencies

sudo apt-get update
sudo apt-get install gcc make git libtool autoconf autogen pkg-config cmake
sudo apt-get install python3 python3-dev python3-pip
sudo apt-get install dkms
sudo apt-get install libssl1.1 libgstreamer1.0-0 gstreamer1.0-tools gstreamer1.0-plugins-good gstreamer1.0-plugins-bad gstreamer1.0-plugins-ugly gstreamer1.0-libav libgstrtspserver-1.0-0 libjansson4 libyaml-cpp-dev
sudo apt-get install linux-headers-$(uname -r)

NOTE: Purge all NVIDIA driver, CUDA, etc (replace $CUDA_PATH to your CUDA path).

sudo nvidia-uninstall
sudo $CUDA_PATH/bin/cuda-uninstaller
sudo apt-get remove --purge '*nvidia*'
sudo apt-get remove --purge '*cuda*'
sudo apt-get remove --purge '*cudnn*'
sudo apt-get remove --purge '*tensorrt*'
sudo apt autoremove --purge && sudo apt autoclean && sudo apt clean

3. Install CUDA Keyring

wget https://developer.download.nvidia.com/compute/cuda/repos/ubuntu1804/x86_64/cuda-keyring_1.0-1_all.deb
sudo dpkg -i cuda-keyring_1.0-1_all.deb
sudo apt-get update

4. Download and install NVIDIA Driver

  • TITAN, GeForce RTX / GTX series and RTX / Quadro series
wget https://us.download.nvidia.com/XFree86/Linux-x86_64/510.47.03/NVIDIA-Linux-x86_64-510.47.03.run
  • Data center / Tesla series
wget https://us.download.nvidia.com/tesla/510.47.03/NVIDIA-Linux-x86_64-510.47.03.run
  • Run
sudo sh NVIDIA-Linux-x86_64-510.47.03.run --silent --disable-nouveau --dkms --install-libglvnd

NOTE: This step will disable the nouveau drivers.

  • Reboot
sudo reboot
  • Install
sudo sh NVIDIA-Linux-x86_64-510.47.03.run --silent --disable-nouveau --dkms --install-libglvnd

NOTE: If you are using a laptop with NVIDIA Optimius, run

sudo apt-get install nvidia-prime
sudo prime-select nvidia

5. Download and install CUDA

wget https://developer.download.nvidia.com/compute/cuda/11.6.1/local_installers/cuda_11.6.1_510.47.03_linux.run
sudo sh cuda_11.6.1_510.47.03_linux.run --silent --toolkit
  • Export environment variables
echo $'export PATH=/usr/local/cuda-11.6/bin${PATH:+:${PATH}}\nexport LD_LIBRARY_PATH=/usr/local/cuda-11.6/lib64${LD_LIBRARY_PATH:+:${LD_LIBRARY_PATH}}' >> ~/.bashrc && source ~/.bashrc

6. Download from NVIDIA website and install the TensorRT

TensorRT 8.2 GA Update 4 for Ubuntu 20.04 and CUDA 11.0, 11.1, 11.2, 11.3, 11.4 and 11.5 DEB local repo Package

sudo dpkg -i nv-tensorrt-repo-ubuntu2004-cuda11.4-trt8.2.5.1-ga-20220505_1-1_amd64.deb
sudo apt-key add /var/nv-tensorrt-repo-ubuntu2004-cuda11.4-trt8.2.5.1-ga-20220505/82307095.pub
sudo apt-get update
sudo apt install tensorrt

7. Download from NVIDIA website and install the DeepStream SDK

DeepStream 6.1 for Servers and Workstations (.deb)

sudo apt-get install ./deepstream-6.1_6.1.0-1_amd64.deb
rm ${HOME}/.cache/gstreamer-1.0/registry.x86_64.bin
sudo ln -snf /usr/local/cuda-11.6 /usr/local/cuda

8. Reboot the computer

sudo reboot
DeepStream 6.0.1 / 6.0

1. Disable Secure Boot in BIOS

If you are using a laptop with newer Intel/AMD processors and your Graphics in Settings->Details->About tab is llvmpipe, please update the kernel. 
wget https://kernel.ubuntu.com/~kernel-ppa/mainline/v5.11/amd64/linux-headers-5.11.0-051100_5.11.0-051100.202102142330_all.deb
wget https://kernel.ubuntu.com/~kernel-ppa/mainline/v5.11/amd64/linux-headers-5.11.0-051100-generic_5.11.0-051100.202102142330_amd64.deb
wget https://kernel.ubuntu.com/~kernel-ppa/mainline/v5.11/amd64/linux-image-unsigned-5.11.0-051100-generic_5.11.0-051100.202102142330_amd64.deb
wget https://kernel.ubuntu.com/~kernel-ppa/mainline/v5.11/amd64/linux-modules-5.11.0-051100-generic_5.11.0-051100.202102142330_amd64.deb
sudo dpkg -i  *.deb
sudo reboot

2. Install dependencies

sudo apt-get update
sudo apt-get install gcc make git libtool autoconf autogen pkg-config cmake
sudo apt-get install python3 python3-dev python3-pip
sudo apt install libssl1.0.0 libgstreamer1.0-0 gstreamer1.0-tools gstreamer1.0-plugins-good gstreamer1.0-plugins-bad gstreamer1.0-plugins-ugly gstreamer1.0-libav libgstrtspserver-1.0-0 libjansson4
sudo apt-get install linux-headers-$(uname -r)

NOTE: Install DKMS only if you are using the default Ubuntu kernel.

sudo apt-get install dkms

NOTE: Purge all NVIDIA driver, CUDA, etc (replace $CUDA_PATH to your CUDA path).

sudo nvidia-uninstall
sudo $CUDA_PATH/bin/cuda-uninstaller
sudo apt-get remove --purge '*nvidia*'
sudo apt-get remove --purge '*cuda*'
sudo apt-get remove --purge '*cudnn*'
sudo apt-get remove --purge '*tensorrt*'
sudo apt autoremove --purge && sudo apt autoclean && sudo apt clean

3. Install CUDA Keyring

wget https://developer.download.nvidia.com/compute/cuda/repos/ubuntu1804/x86_64/cuda-keyring_1.0-1_all.deb
sudo dpkg -i cuda-keyring_1.0-1_all.deb
sudo apt-get update

4. Download and install NVIDIA Driver

  • TITAN, GeForce RTX / GTX series and RTX / Quadro series
wget https://us.download.nvidia.com/XFree86/Linux-x86_64/470.129.06/NVIDIA-Linux-x86_64-470.129.06.run
  • Data center / Tesla series
wget https://us.download.nvidia.com/tesla/470.129.06/NVIDIA-Linux-x86_64-470.129.06.run
  • Run
sudo sh NVIDIA-Linux-x86_64-470.129.06.run --silent --disable-nouveau --dkms --install-libglvnd

NOTE: This step will disable the nouveau drivers.

  • Reboot
sudo reboot
  • Install
sudo sh NVIDIA-Linux-x86_64-470.129.06.run --silent --disable-nouveau --dkms --install-libglvnd

NOTE: If you are using a laptop with NVIDIA Optimius, run

sudo apt-get install nvidia-prime
sudo prime-select nvidia

5. Download and install CUDA

wget https://developer.download.nvidia.com/compute/cuda/11.4.1/local_installers/cuda_11.4.1_470.57.02_linux.run
sudo sh cuda_11.4.1_470.57.02_linux.run --silent --toolkit
  • Export environment variables
echo $'export PATH=/usr/local/cuda-11.4/bin${PATH:+:${PATH}}\nexport LD_LIBRARY_PATH=/usr/local/cuda-11.4/lib64${LD_LIBRARY_PATH:+:${LD_LIBRARY_PATH}}' >> ~/.bashrc && source ~/.bashrc

6. Download from NVIDIA website and install the TensorRT

TensorRT 8.0.1 GA for Ubuntu 18.04 and CUDA 11.3 DEB local repo package

sudo dpkg -i nv-tensorrt-repo-ubuntu1804-cuda11.3-trt8.0.1.6-ga-20210626_1-1_amd64.deb
sudo apt-key add /var/nv-tensorrt-repo-ubuntu1804-cuda11.3-trt8.0.1.6-ga-20210626/7fa2af80.pub
sudo apt-get update
sudo apt-get install libnvinfer8=8.0.1-1+cuda11.3 libnvinfer-plugin8=8.0.1-1+cuda11.3 libnvparsers8=8.0.1-1+cuda11.3 libnvonnxparsers8=8.0.1-1+cuda11.3 libnvinfer-bin=8.0.1-1+cuda11.3 libnvinfer-dev=8.0.1-1+cuda11.3 libnvinfer-plugin-dev=8.0.1-1+cuda11.3 libnvparsers-dev=8.0.1-1+cuda11.3 libnvonnxparsers-dev=8.0.1-1+cuda11.3 libnvinfer-samples=8.0.1-1+cuda11.3 libnvinfer-doc=8.0.1-1+cuda11.3

7. Download from NVIDIA website and install the DeepStream SDK

  • DeepStream 6.0.1 for Servers and Workstations (.deb)
sudo apt-get install ./deepstream-6.0_6.0.1-1_amd64.deb
  • DeepStream 6.0 for Servers and Workstations (.deb)
sudo apt-get install ./deepstream-6.0_6.0.0-1_amd64.deb
  • Run
rm ${HOME}/.cache/gstreamer-1.0/registry.x86_64.bin
sudo ln -snf /usr/local/cuda-11.4 /usr/local/cuda

8. Reboot the computer

sudo reboot

Basic usage

1. Download the repo

git clone https://github.com/marcoslucianops/DeepStream-Yolo.git
cd DeepStream-Yolo

2. Download cfg and weights files from your model and move to DeepStream-Yolo folder

3. Compile lib

  • DeepStream 6.1 on x86 platform
CUDA_VER=11.6 make -C nvdsinfer_custom_impl_Yolo
  • DeepStream 6.0.1 / 6.0 on x86 platform
CUDA_VER=11.4 make -C nvdsinfer_custom_impl_Yolo
  • DeepStream 6.1 on Jetson platform
CUDA_VER=11.4 make -C nvdsinfer_custom_impl_Yolo
  • DeepStream 6.0.1 / 6.0 on Jetson platform
CUDA_VER=10.2 make -C nvdsinfer_custom_impl_Yolo

4. Edit config_infer_primary.txt for your model (example for YOLOv4)

[property]
...
# 0=RGB, 1=BGR, 2=GRAYSCALE
model-color-format=0
# YOLO cfg
custom-network-config=yolov4.cfg
# YOLO weights
model-file=yolov4.weights
# Generated TensorRT model (will be created if it doesn't exist)
model-engine-file=model_b1_gpu0_fp32.engine
# Model labels file
labelfile-path=labels.txt
# Batch size
batch-size=1
# 0=FP32, 1=INT8, 2=FP16 mode
network-mode=0
# Number of classes in label file
num-detected-classes=80
...

5. Run

deepstream-app -c deepstream_app_config.txt

NOTE: If you want to use YOLOv2 or YOLOv2-Tiny models, change the deepstream_app_config.txt file before run it

...
[primary-gie]
enable=1
gpu-id=0
gie-unique-id=1
nvbuf-memory-type=0
config-file=config_infer_primary_yoloV2.txt
...

YOLOv5 usage

NOTE: Make sure to change the YOLOv5 repo version to your model version before conversion.

1. Copy gen_wts_yoloV5.py from DeepStream-Yolo/utils to ultralytics/yolov5 folder

2. Open the ultralytics/yolov5 folder

3. Download pt file from ultralytics/yolov5 website (example for YOLOv5n 6.1)

wget https://github.com/ultralytics/yolov5/releases/download/v6.1/yolov5n.pt

4. Generate cfg and wts files (example for YOLOv5n)

python3 gen_wts_yoloV5.py -w yolov5n.pt -c models/yolov5n.yaml

5. Copy generated cfg and wts files to DeepStream-Yolo folder

6. Open DeepStream-Yolo folder

7. Compile lib

  • DeepStream 6.1 on x86 platform
CUDA_VER=11.6 make -C nvdsinfer_custom_impl_Yolo
  • DeepStream 6.0.1 / 6.0 on x86 platform
CUDA_VER=11.4 make -C nvdsinfer_custom_impl_Yolo
  • DeepStream 6.1 on Jetson platform
CUDA_VER=11.4 make -C nvdsinfer_custom_impl_Yolo
  • DeepStream 6.0.1 / 6.0 on Jetson platform
CUDA_VER=10.2 make -C nvdsinfer_custom_impl_Yolo

8. Edit config_infer_primary_yoloV5.txt for your model (example for YOLOv5n)

[property]
...
# 0=RGB, 1=BGR, 2=GRAYSCALE
model-color-format=0
# CFG
custom-network-config=yolov5n.cfg
# WTS
model-file=yolov5n.wts
# Generated TensorRT model (will be created if it doesn't exist)
model-engine-file=model_b1_gpu0_fp32.engine
# Model labels file
labelfile-path=labels.txt
# Batch size
batch-size=1
# 0=FP32, 1=INT8, 2=FP16 mode
network-mode=0
# Number of classes in label file
num-detected-classes=80
...

8. Change the deepstream_app_config.txt file

...
[primary-gie]
enable=1
gpu-id=0
gie-unique-id=1
nvbuf-memory-type=0
config-file=config_infer_primary_yoloV5.txt

9. Run

deepstream-app -c deepstream_app_config.txt

NOTE: For YOLOv5 P6 or custom models, check the gen_wts_yoloV5.py args and use them according to your model

  • Input weights (.pt) file path (required)
-w or --weights
  • Input cfg (.yaml) file path
-c or --yaml
  • Inference size [size] or [height , weight] (default [640] / [1280] if --p6)
-s or --size

Example for 1280

-s 1280

or

-s 1280 1280

YOLOR usage

1. Copy gen_wts_yolor.py from DeepStream-Yolo/utils to yolor folder

2. Open the yolor folder

3. Download pt file from yolor website

4. Generate wts file (example for YOLOR-CSP)

python3 gen_wts_yolor.py -w yolor_csp.pt -c cfg/yolor_csp.cfg

5. Copy cfg and generated wts files to DeepStream-Yolo folder

6. Open DeepStream-Yolo folder

7. Compile lib

  • DeepStream 6.1 on x86 platform
CUDA_VER=11.6 make -C nvdsinfer_custom_impl_Yolo
  • DeepStream 6.0.1 / 6.0 on x86 platform
CUDA_VER=11.4 make -C nvdsinfer_custom_impl_Yolo
  • DeepStream 6.1 on Jetson platform
CUDA_VER=11.4 make -C nvdsinfer_custom_impl_Yolo
  • DeepStream 6.0.1 / 6.0 on Jetson platform
CUDA_VER=10.2 make -C nvdsinfer_custom_impl_Yolo

8. Edit config_infer_primary_yolor.txt for your model (example for YOLOR-CSP)

[property]
...
# 0=RGB, 1=BGR, 2=GRAYSCALE
model-color-format=0
# CFG
custom-network-config=yolor_csp.cfg
# WTS
model-file=yolor_csp.wts
# Generated TensorRT model (will be created if it doesn't exist)
model-engine-file=model_b1_gpu0_fp32.engine
# Model labels file
labelfile-path=labels.txt
# Batch size
batch-size=1
# 0=FP32, 1=INT8, 2=FP16 mode
network-mode=0
# Number of classes in label file
num-detected-classes=80
...

8. Change the deepstream_app_config.txt file

...
[primary-gie]
enable=1
gpu-id=0
gie-unique-id=1
nvbuf-memory-type=0
config-file=config_infer_primary_yolor.txt

9. Run

deepstream-app -c deepstream_app_config.txt

NMS Configuration

To change the iou-threshold, score-threshold and topk values, modify the config_nms.txt file and regenerate the model engine file.

NOTE: Lower topk values will result in more performance.

NOTE: Make sure to set cluster-mode=4 in config_infer file.

NOTE: You are still able to change the pre-cluster-threshold values in the config_infer.txt file.

[property]
iou-threshold=0.45
score-threshold=0.25
topk=300

INT8 calibration

1. Install OpenCV

sudo apt-get install libopencv-dev

2. Compile/recompile the nvdsinfer_custom_impl_Yolo lib with OpenCV support

  • DeepStream 6.1 on x86 platform
cd DeepStream-Yolo
CUDA_VER=11.6 OPENCV=1 make -C nvdsinfer_custom_impl_Yolo
  • DeepStream 6.0.1 / 6.0 on x86 platform
cd DeepStream-Yolo
CUDA_VER=11.4 OPENCV=1 make -C nvdsinfer_custom_impl_Yolo
  • DeepStream 6.1 on Jetson platform
cd DeepStream-Yolo
CUDA_VER=11.4 OPENCV=1 make -C nvdsinfer_custom_impl_Yolo
  • DeepStream 6.0.1 / 6.0 on Jetson platform
cd DeepStream-Yolo
CUDA_VER=10.2 OPENCV=1 make -C nvdsinfer_custom_impl_Yolo

3. For COCO dataset, download the val2017, extract, and move to DeepStream-Yolo folder

Select 1000 random images from COCO dataset to run calibration
mkdir calibration

for jpg in $(ls -1 val2017/*.jpg | sort -R | head -1000); do \
    cp ${jpg} calibration/; \
done
Create the calibration.txt file with all selected images
realpath calibration/*jpg > calibration.txt
Set environment variables
export INT8_CALIB_IMG_PATH=calibration.txt
export INT8_CALIB_BATCH_SIZE=1
Change config_infer_primary.txt file
...
model-engine-file=model_b1_gpu0_fp32.engine
#int8-calib-file=calib.table
...
network-mode=0
...
  • To
...
model-engine-file=model_b1_gpu0_int8.engine
int8-calib-file=calib.table
...
network-mode=1
...
Run
deepstream-app -c deepstream_app_config.txt

NOTE: NVIDIA recommends at least 500 images to get a good accuracy. In this example I used 1000 images to get better accuracy (more images = more accuracy). Higher INT8_CALIB_BATCH_SIZE values will increase the accuracy and calibration speed. Set it according to you GPU memory. This process can take a long time.

Extract metadata

You can get metadata from deepstream in Python and C/C++. For C/C++, you need edit deepstream-app or deepstream-test code. For Python your need install and edit deepstream_python_apps.

Basically, you need manipulate NvDsObjectMeta (Python/C/C++) and NvDsFrameMeta (Python/C/C++) to get label, position, etc. of bboxes.

My projects: https://www.youtube.com/MarcosLucianoTV