metadata

language: en
tags:
  - object detection
  - computer vision
  - darknet
  - yolo
datasets:
  - coco
  - imagenette
license: mit
thumbnail: https://github.com/hunglc007/tensorflow-yolov4-tflite
pipeline_tag: object-detection

YOLOv4

YOLO, for You Only Look Once, is an object detection system in real-time, introduced in this paper, that recognizes various objects in a single enclosure. It identifies objects more rapidly and more precisely than other recognition systems. Three authors Alexey Bochkovskiy, the Russian developer who built the YOLO Windows version, Chien-Yao Wang, and Hong-Yuan Mark Liao, are accounted for in this work and the entire code is available on Github.

This YOLOv4 library, inspired by previous YOLOv3 implementations here:

Yolov3 tensorflow
Yolov3 tf2uses Tensorflow 2.0 and is available on this Github.

Evaluate on COCO 2017 Dataset

# run script in /script/get_coco_dataset_2017.sh to download COCO 2017 Dataset
# preprocess coco dataset
cd data
mkdir dataset
cd ..
cd scripts
python coco_convert.py --input ./coco/annotations/instances_val2017.json --output val2017.pkl
python coco_annotation.py --coco_path ./coco 
cd ..

# evaluate yolov4 model
python evaluate.py --weights ./data/yolov4.weights
cd mAP/extra
python remove_space.py
cd ..
python main.py --output results_yolov4_tf

mAP50 on COCO 2017 Dataset

Detection	512x512	416x416	320x320
YoloV3	55.43	52.32
YoloV4	61.96	57.33

Benchmark

python benchmarks.py --size 416 --model yolov4 --weights ./data/yolov4.weights

TensorRT performance

YoloV4 416 images/s	FP32	FP16	INT8
Batch size 1	55	116
Batch size 8	70	152

Tesla P100

Detection	512x512	416x416	320x320
YoloV3 FPS	40.6	49.4	61.3
YoloV4 FPS	33.4	41.7	50.0

Tesla K80

Detection	512x512	416x416	320x320
YoloV3 FPS	10.8	12.9	17.6
YoloV4 FPS	9.6	11.7	16.0

Tesla T4

Detection	512x512	416x416	320x320
YoloV3 FPS	27.6	32.3	45.1
YoloV4 FPS	24.0	30.3	40.1

Tesla P4

Detection	512x512	416x416	320x320
YoloV3 FPS	20.2	24.2	31.2
YoloV4 FPS	16.2	20.2	26.5

Macbook Pro 15 (2.3GHz i7)

Detection	512x512	416x416	320x320
YoloV3 FPS
YoloV4 FPS

Traning your own model

# Prepare your dataset
# If you want to train from scratch:
In config.py set FISRT_STAGE_EPOCHS=0 
# Run script:
python train.py
# Transfer learning: 
python train.py --weights ./data/yolov4.weights

The training performance is not fully reproduced yet, so I recommended to use Alex's Darknet to train your own data, then convert the .weights to tensorflow or tflite.

References

YOLOv4: Optimal Speed and Accuracy of Object Detection YOLOv4.
darknet