duan8/yolov5

YOLOv5

TensorRTx inference code base for ultralytics/yolov5.

Contributors

Different versions of yolov5

Currently, we support yolov5 v1.0, v2.0, v3.0, v3.1, v4.0, v5.0, v6.0, v6.2, v7.0

• For yolov5 v7.0, download .pt from yolov5 release v7.0, git clone -b v7.0 https://github.com/ultralytics/yolov5.git and git clone -b yolov5-v7.0 https://github.com/wang-xinyu/tensorrtx.git, then follow how-to-run in tensorrtx/yolov5-v7.0
• For yolov5 v6.2, download .pt from yolov5 release v6.2, git clone -b v6.2 https://github.com/ultralytics/yolov5.git and git clone -b yolov5-v6.2 https://github.com/wang-xinyu/tensorrtx.git, then follow how-to-run in tensorrtx/yolov5-v6.2
• For yolov5 v6.0, download .pt from yolov5 release v6.0, git clone -b v6.0 https://github.com/ultralytics/yolov5.git and git clone -b yolov5-v6.0 https://github.com/wang-xinyu/tensorrtx.git, then follow how-to-run in tensorrtx/yolov5-v6.0.
• For yolov5 v5.0, download .pt from yolov5 release v5.0, git clone -b v5.0 https://github.com/ultralytics/yolov5.git and git clone -b yolov5-v5.0 https://github.com/wang-xinyu/tensorrtx.git, then follow how-to-run in tensorrtx/yolov5-v5.0.
• For yolov5 v4.0, download .pt from yolov5 release v4.0, git clone -b v4.0 https://github.com/ultralytics/yolov5.git and git clone -b yolov5-v4.0 https://github.com/wang-xinyu/tensorrtx.git, then follow how-to-run in tensorrtx/yolov5-v4.0.
• For yolov5 v3.1, download .pt from yolov5 release v3.1, git clone -b v3.1 https://github.com/ultralytics/yolov5.git and git clone -b yolov5-v3.1 https://github.com/wang-xinyu/tensorrtx.git, then follow how-to-run in tensorrtx/yolov5-v3.1.
• For yolov5 v3.0, download .pt from yolov5 release v3.0, git clone -b v3.0 https://github.com/ultralytics/yolov5.git and git clone -b yolov5-v3.0 https://github.com/wang-xinyu/tensorrtx.git, then follow how-to-run in tensorrtx/yolov5-v3.0.
• For yolov5 v2.0, download .pt from yolov5 release v2.0, git clone -b v2.0 https://github.com/ultralytics/yolov5.git and git clone -b yolov5-v2.0 https://github.com/wang-xinyu/tensorrtx.git, then follow how-to-run in tensorrtx/yolov5-v2.0.
• For yolov5 v1.0, download .pt from yolov5 release v1.0, git clone -b v1.0 https://github.com/ultralytics/yolov5.git and git clone -b yolov5-v1.0 https://github.com/wang-xinyu/tensorrtx.git, then follow how-to-run in tensorrtx/yolov5-v1.0.

Config

• Choose the model n/s/m/l/x/n6/s6/m6/l6/x6 from command line arguments.
• Input shape defined in yololayer.h
• Number of classes defined in yololayer.h, DO NOT FORGET TO ADAPT THIS, If using your own model
• INT8/FP16/FP32 can be selected by the macro in yolov5.cpp, INT8 need more steps, pls follow How to Run first and then go the INT8 Quantization below
• GPU id can be selected by the macro in yolov5.cpp
• NMS thresh in yolov5.cpp
• BBox confidence thresh in yolov5.cpp
• Batch size in yolov5.cpp

Build and Run

Detection

1. generate .wts from pytorch with .pt, or download .wts from model zoo

// clone code according to above #Different versions of yolov5
// download https://github.com/ultralytics/yolov5/releases/download/v7.0/yolov5s.pt
cp {tensorrtx}/yolov5/gen_wts.py {ultralytics}/yolov5
cd {ultralytics}/yolov5
python gen_wts.py -w yolov5s.pt -o yolov5s.wts
// a file 'yolov5s.wts' will be generated.

2. build tensorrtx/yolov5 and run

cd {tensorrtx}/yolov5/
// update CLASS_NUM in yololayer.h if your model is trained on custom dataset
mkdir build
cd build
cp {ultralytics}/yolov5/yolov5s.wts {tensorrtx}/yolov5/build
cmake ..
make
sudo ./yolov5_det -s [.wts] [.engine] [n/s/m/l/x/n6/s6/m6/l6/x6 or c/c6 gd gw]  // serialize model to plan file
sudo ./yolov5_det -d [.engine] [image folder]  // deserialize and run inference, the images in [image folder] will be processed.
// For example yolov5s
sudo ./yolov5_det -s yolov5s.wts yolov5s.engine s
sudo ./yolov5_det -d yolov5s.engine ../samples
// For example Custom model with depth_multiple=0.17, width_multiple=0.25 in yolov5.yaml
sudo ./yolov5_det -s yolov5_custom.wts yolov5.engine c 0.17 0.25
sudo ./yolov5_det -d yolov5.engine ../samples

3. check the images generated, as follows. _zidane.jpg and _bus.jpg

4. optional, load and run the tensorrt model in python

// install python-tensorrt, pycuda, etc.
// ensure the yolov5s.engine and libmyplugins.so have been built
python yolov5_det_trt.py

// Another version of python script, which is using CUDA Python instead of pycuda.
python yolov5_det_trt_cuda_python.py

Classification

# Download ImageNet labels
wget https://github.com/joannzhang00/ImageNet-dataset-classes-labels/blob/main/imagenet_classes.txt

# Build and serialize TensorRT engine
./yolov5_cls -s yolov5s-cls.wts yolov5s-cls.engine s

# Run inference
./yolov5_cls -d yolov5s-cls.engine ../samples

Instance Segmentation

# Build and serialize TensorRT engine
./yolov5_seg -s yolov5s-seg.wts yolov5s-seg.engine s

# Run inference
./yolov5_seg -d yolov5s-seg.engine ../samples

INT8 Quantization

1. Prepare calibration images, you can randomly select 1000s images from your train set. For coco, you can also download my calibration images coco_calib from GoogleDrive or BaiduPan pwd: a9wh

2. unzip it in yolov5/build

3. set the macro USE_INT8 in yolov5.cpp and make

4. serialize the model and test

More Information

See the readme in home page.