A minimal PyTorch implementation of YOLOv4.
Paper Yolo v4: https://arxiv.org/abs/2004.10934
Source code:https://github.com/AlexeyAB/darknet
More details: http://pjreddie.com/darknet/yolo/
Inference
Train
├── README.md
├── dataset.py dataset
├── demo.py demo to run pytorch --> tool/darknet2pytorch
├── demo_darknet2onnx.py tool to convert into onnx --> tool/darknet2pytorch
├── demo_pytorch2onnx.py tool to convert into onnx
├── models.py model for pytorch
├── train.py train models.py
├── cfg.py cfg.py for train
├── cfg cfg --> darknet2pytorch
├── data
├── weight --> darknet2pytorch
├── tool
│ ├── camera.py a demo camera
│ ├── coco_annotation.py coco dataset generator
│ ├── config.py
│ ├── darknet2pytorch.py
│ ├── region_loss.py
│ ├── utils.py
│ └── yolo_layer.py
you can use darknet2pytorch to convert it yourself, or download my converted model.
use yolov4 to train your own data
Download weight
Transform data
For coco dataset,you can use tool/coco_annotation.py.
# train.txt
image_path1 x1,y1,x2,y2,id x1,y1,x2,y2,id x1,y1,x2,y2,id ...
image_path2 x1,y1,x2,y2,id x1,y1,x2,y2,id x1,y1,x2,y2,id ...
...
...
Train
you can set parameters in cfg.py.
python train.py -g [GPU_ID] -dir [Dataset direction] ...
ONNX and TensorRT models are converted from Pytorch (TianXiaomo): Pytorch->ONNX->TensorRT. See following sections for more details of conversions.
Image input size is NOT restricted in 320 * 320, 416 * 416, 512 * 512 and 608 * 608. You can adjust your input sizes for a different input ratio, for example: 320 * 608. Larger input size could help detect smaller targets, but may be slower and GPU memory exhausting.
height = 320 + 96 * n, n in {0, 1, 2, 3, ...}
width = 320 + 96 * m, m in {0, 1, 2, 3, ...} 2.3 Different inference options
Load the pretrained darknet model and darknet weights to do the inference (image size is configured in cfg file already)
python demo.py -cfgfile <cfgFile> -weightfile <weightFile> -imgfile <imgFile>
Load pytorch weights (pth file) to do the inference
python models.py <num_classes> <weightfile> <imgfile> <IN_IMAGE_H> <IN_IMAGE_W> <namefile(optional)>
Load converted ONNX file to do inference (See section 3 and 4)
Load converted TensorRT engine file to do inference (See section 5)
There are 2 inference outputs.
[batch, num_boxes, 1, 4] which represents x1, y1, x2, y2 of each bounding box.[batch, num_boxes, num_classes] indicating scores of all classes for each bounding box.Until now, still a small piece of post-processing including NMS is required. We are trying to minimize time and complexity of post-processing.
This script is to convert the official pretrained darknet model into ONNX
Pytorch version Recommended:
Install onnxruntime
Run python script to generate ONNX model and run the demo
python demo_darknet2onnx.py <cfgFile> <namesFile> <weightFile> <imageFile> <batchSize>
You can convert your trained pytorch model into ONNX using this script
Pytorch version Recommended:
Install onnxruntime
Run python script to generate ONNX model and run the demo
python demo_pytorch2onnx.py <weight_file> <image_path> <batch_size> <n_classes> <IN_IMAGE_H> <IN_IMAGE_W>
For example:
python demo_pytorch2onnx.py yolov4.pth dog.jpg 8 80 416 416
Run the following command to convert YOLOv4 ONNX model into TensorRT engine
trtexec --onnx=<onnx_file> --explicitBatch --saveEngine=<tensorRT_engine_file> --workspace=<size_in_megabytes> --fp16
Run the following command to convert YOLOv4 ONNX model into TensorRT engine
trtexec --onnx=<onnx_file> \ --minShapes=input:<shape_of_min_batch> --optShapes=input:<shape_of_opt_batch> --maxShapes=input:<shape_of_max_batch> \ --workspace=<size_in_megabytes> --saveEngine=<engine_file> --fp16
For example:
trtexec --onnx=yolov4_-1_3_320_512_dynamic.onnx \ --minShapes=input:1x3x320x512 --optShapes=input:4x3x320x512 --maxShapes=input:8x3x320x512 \ --workspace=2048 --saveEngine=yolov4_-1_3_320_512_dynamic.engine --fp16
python demo_trt.py <tensorRT_engine_file> <input_image> <input_H> <input_W>
This demo here only works when batchSize is dynamic (1 should be within dynamic range) or batchSize=1, but you can update this demo a little for other dynamic or static batch sizes.
Note1: input_H and input_W should agree with the input size in the original ONNX file.
Note2: extra NMS operations are needed for the tensorRT output. This demo uses python NMS code from tool/utils.py.
First:Conversion to ONNX
tensorflow >=2.0
1: Thanks:github:https://github.com/onnx/onnx-tensorflow
2: Run git clone https://github.com/onnx/onnx-tensorflow.git && cd onnx-tensorflow Run pip install -e .
Note:Errors will occur when using "pip install onnx-tf", at least for me,it is recommended to use source code installation
For single batch,
trtexec --onnx=<onnx_file> --explicitBatch --saveEngine=<tensorRT_engine_file> --workspace=<size_in_megabytes> --fp16
For multi-batch,
trtexec --onnx=<onnx_file> --explicitBatch --shapes=input:Xx3xHxW --optShapes=input:Xx3xHxW --maxShapes=input:Xx3xHxW --minShape=input:1x3xHxW --saveEngine=<tensorRT_engine_file> --fp16
Note :The maxShapes could not be larger than model original shape.
Reference:
@article{yolov4,
title={YOLOv4: YOLOv4: Optimal Speed and Accuracy of Object Detection},
author={Alexey Bochkovskiy, Chien-Yao Wang, Hong-Yuan Mark Liao},
journal = {arXiv},
year={2020}
}
RetroSearch is an open source project built by @garambo | Open a GitHub Issue
Search and Browse the WWW like it's 1997 | Search results from DuckDuckGo
HTML:
3.2
| Encoding:
UTF-8
| Version:
0.7.4