marcoslucianops / deepstream-yolo-face Goto Github PK

View Code? Open in Web Editor NEW

48.0 3.0 9.0 23 KB

NVIDIA DeepStream SDK 6.3 / 6.2 / 6.1.1 / 6.1 / 6.0.1 / 6.0 application for YOLO-Face models

License: MIT License

Makefile 6.53% C 41.82% Python 36.86% C++ 14.79%

deepstream face-detection nvidia nvidia-deepstream-sdk pytorch tensorrt ultralytics yolo yolov5 yolov7

deepstream-yolo-face's Introduction

DeepStream-Yolo-Face

NVIDIA DeepStream SDK application for YOLO-Face models

YOLO objetct detection models and other infos: https://github.com/marcoslucianops/DeepStream-Yolo

Getting started

Supported models
Instructions
YOLOv5-Face usage
YOLOv7-Face usage
YOLOv8-Face usage
NMS configuration
Detection threshold configuration

Supported models

Instructions

1. Download the DeepStream-Yolo-Face repo

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

2. Compile the libs

Export the CUDA_VER env according to your DeepStream version and platform:

DeepStream 6.3 on x86 platform
```
export CUDA_VER=12.1
```
DeepStream 6.2 on x86 platform
```
export CUDA_VER=11.8
```
DeepStream 6.1.1 on x86 platform
```
export CUDA_VER=11.7
```
DeepStream 6.1 on x86 platform
```
export CUDA_VER=11.6
```
DeepStream 6.0.1 / 6.0 on x86 platform
```
export CUDA_VER=11.4
```
DeepStream 6.3 / 6.2 / 6.1.1 / 6.1 on Jetson platform
```
export CUDA_VER=11.4
```
DeepStream 6.0.1 / 6.0 on Jetson platform
```
export CUDA_VER=10.2
```

Compile the libs

make -C nvdsinfer_custom_impl_Yolo_face
make

NOTE: To use the Python code, you need to install the DeepStream Python bindings.

Reference: https://github.com/NVIDIA-AI-IOT/deepstream_python_apps

x86 platform:

wget https://github.com/NVIDIA-AI-IOT/deepstream_python_apps/releases/download/v1.1.8/pyds-1.1.8-py3-none-linux_x86_64.whl
pip3 install pyds-1.1.8-py3-none-linux_x86_64.whl

Jetson platform:

wget https://github.com/NVIDIA-AI-IOT/deepstream_python_apps/releases/download/v1.1.8/pyds-1.1.8-py3-none-linux_aarch64.whl
pip3 install pyds-1.1.8-py3-none-linux_aarch64.whl

NOTE: It is recommended to use Python virtualenv.

NOTE: The steps above only work on DeepStream 6.3. For previous versions, please check the files on the NVIDIA-AI-IOT/deepstream_python_apps repo.

3. Run

C code

./deepstream -s file:///opt/nvidia/deepstream/deepstream/samples/streams/sample_1080p_h264.mp4 -c config_infer_primary_yoloV8_face.txt

Python code

python3 deepstream.py -s file:///opt/nvidia/deepstream/deepstream/samples/streams/sample_1080p_h264.mp4 -c config_infer_primary_yoloV8_face.txt

NOTE: The TensorRT engine file may take a very long time to generate (sometimes more than 10 minutes).

NOTE: To change the source

-s file:// or rtsp:// or http://
--source file:// or rtsp:// or http://

NOTE: To change the config infer file (example for config_infer.txt file)

-c config_infer.txt
--config-infer config_infer.txt

NOTE: To change the nvstreammux batch-size (example for 2; default: 1)

-b 2
--streammux-batch-size 2

NOTE: To change the nvstreammux width (example for 1280; default: 1920)

-w 1280
--streammux-width 1280

NOTE: To change the nvstreammux height (example for 720; default: 1080)

-e 720
--streammux-height 720

NOTE: To change the GPU id (example for 1; default: 0)

-g 1
--gpu-id 1

NOTE: To change the FPS measurement interval (example for 10; default: 5)

-f 10
--fps-interval 10

NMS configuration

For now, the nms-iou-threshold is fixed to 0.45.

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

Detection threshold configuration

[class-attrs-all]
pre-cluster-threshold=0.25
topk=300

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

deepstream-yolo-face's People

Contributors

Stargazers

Watchers

Forkers

elephantclock ginochenhj madesh1997 atoms-1 dungmn akemid betsyalan skyceeee peopleyoung

deepstream-yolo-face's Issues

Deep stream has face recognition

i want do a project with face recognition . i want use one shotlearning and use siamese network.
can use this face detection(with deepstream) and use pretrained model in deepstream for feature extraction and compare it ?
Thanku

AttributeError: 'pyds.NvOSD_Masis:issue is:open kParams' object has no attribute 'get_mask_array'

AttributeError: 'pyds.NvOSD_MaskParams' object has no attribute 'get_mask_array'

Segmentation Fault ERROR

Hello.
I am trying to run the Python file from this repository using the given command: python3 deepstream.py -s file:///opt/nvidia/deepstream/deepstream/samples/streams/sample_1080p_h264.mp4 -c config_infer_primary_yoloV8_face.txt

Every time I run the command I'm getting Segmentation fault ERROR with a black screen, below is the log I get while running the file:

+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
ubuntu@ubuntu-Blade-15-2022-RZ09-0421:~/Documents/DeepStream-Yolo-Face$ python3 deepstream.py -s file:///opt/nvidia/deepstream/deepstream/samples/streams/sample_1080p_h264.mp4 -c config_infer_primary_yoloV8_face.txt

SOURCE: file:///opt/nvidia/deepstream/deepstream/samples/streams/sample_1080p_h264.mp4
CONFIG_INFER: config_infer_primary_yoloV8_face.txt
STREAMMUX_BATCH_SIZE: 1
STREAMMUX_WIDTH: 1920
STREAMMUX_HEIGHT: 1080
GPU_ID: 0
PERF_MEASUREMENT_INTERVAL_SEC: 5
JETSON: FALSE

gstnvtracker: Loading low-level lib at /opt/nvidia/deepstream/deepstream/lib/libnvds_nvmultiobjecttracker.so
[NvMultiObjectTracker] Initialized
0:00:03.122840037 24409 0x3042a60 INFO nvinfer gstnvinfer.cpp:682:gst_nvinfer_logger: NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:1988> [UID = 1]: deserialized trt engine from :/home/ubuntu/Documents/DeepStream-Yolo-Face/yolov8n-face.onnx_b1_gpu0_fp32.engine
WARNING: [TRT]: The getMaxBatchSize() function should not be used with an engine built from a network created with NetworkDefinitionCreationFlag::kEXPLICIT_BATCH flag. This function will always return 1.
INFO: ../nvdsinfer/nvdsinfer_model_builder.cpp:610 [Implicit Engine Info]: layers num: 2
0 INPUT kFLOAT images 3x640x640
1 OUTPUT kFLOAT output0 5x8400

0:00:03.173926305 24409 0x3042a60 INFO nvinfer gstnvinfer.cpp:682:gst_nvinfer_logger: NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:2091> [UID = 1]: Use deserialized engine model: /home/ubuntu/Documents/DeepStream-Yolo-Face/yolov8n-face.onnx_b1_gpu0_fp32.engine
0:00:03.175549029 24409 0x3042a60 INFO nvinfer gstnvinfer_impl.cpp:328:notifyLoadModelStatus: [UID 1]: Load new model:config_infer_primary_yoloV8_face.txt sucessfully

Segmentation fault (core dumped)

+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++

Please, I wonder if anyone could help me with this issue, how can I fix it?

DeepStream Version = 6.3
YOLO MODEL = Yolov8n-face
CUDA = 12.3
TensorRT = 8.5.3.1
NVIDIA GRAPHIC = GeForce RTX 3080 Ti
32GB RAM and 1TB SSD

getting "libpython3.8.so.1.0 cannot open shared object file: No such file or directory" error while running deepstream.py

deepstream.py", line 13, in <module>
    import pyds
ImportError: libpython3.8.so.1.0: cannot open shared object file: No such file or directory

can you please help me solve this issue! I have python 3.10 install and i dont know why its trying to find python 3.8

Error While Running the python code

+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
ubuntu@ubuntu-Blade-15-2022-RZ09-0421:~/Documents/DeepStream-Yolo-Face$ python3 deepstream.py -s file:///opt/nvidia/deepstream/deepstream/samples/streams/sample_1080p_h264.mp4 -c config_infer_primary_yoloV8_face.txt

gstnvtracker: Loading low-level lib at /opt/nvidia/deepstream/deepstream/lib/libnvds_nvmultiobjecttracker.so
[NvMultiObjectTracker] Initialized
0:00:03.153337617 31142 0x2ae9860 INFO nvinfer gstnvinfer.cpp:682:gst_nvinfer_logger: NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:1988> [UID = 1]: deserialized trt engine from :/home/ubuntu/Documents/DeepStream-Yolo-Face/yolov8n-face.onnx_b1_gpu0_fp32.engine
WARNING: [TRT]: The getMaxBatchSize() function should not be used with an engine built from a network created with NetworkDefinitionCreationFlag::kEXPLICIT_BATCH flag. This function will always return 1.
INFO: ../nvdsinfer/nvdsinfer_model_builder.cpp:610 [Implicit Engine Info]: layers num: 4
0 INPUT kFLOAT input 3x640x640
1 OUTPUT kFLOAT boxes 8400x4
2 OUTPUT kFLOAT scores 8400x1
3 OUTPUT kFLOAT landmarks 8400x0

0:00:03.208580298 31142 0x2ae9860 INFO nvinfer gstnvinfer.cpp:682:gst_nvinfer_logger: NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:2091> [UID = 1]: Use deserialized engine model: /home/ubuntu/Documents/DeepStream-Yolo-Face/yolov8n-face.onnx_b1_gpu0_fp32.engine
python3: nvdsinfer_context_impl.cpp:1377: NvDsInferStatus nvdsinfer::NvDsInferContextImpl::resizeOutputBufferpool(uint32_t): Assertion `bindingDims.numElements > 0' failed.
Aborted (core dumped)
+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++