Introduction

This directory contains PyTorch YOLOv3 software developed by Ultralytics LLC, and is freely available for redistribution under the GPL-3.0 license. For more information please visit https://www.ultralytics.com.

Description

The https://github.com/ultralytics/yolov3 repo contains inference and training code for YOLOv3 in PyTorch. The code works on Linux, MacOS and Windows. Training is done on the COCO dataset by default: https://cocodataset.org/#home. Credit to Joseph Redmon for YOLO: https://pjreddie.com/darknet/yolo/.

Requirements

Python 3.7 or later with the following pip3 install -U -r requirements.txt packages:

• numpy
• torch >= 1.1.0
• opencv-python
• tqdm

Tutorials

• GCP Quickstart
• Transfer Learning
• Train Single Image
• Train Single Class
• Train Custom Data

Jupyter Notebook

Our Jupyter notebook provides quick training, inference and testing examples.

Training

Start Training: python3 train.py to begin training after downloading COCO data with data/get_coco_dataset.sh. Each epoch trains on 117,263 images from the train and validate COCO sets, and tests on 5000 images from the COCO validate set.

Resume Training: python3 train.py --resume to resume training from weights/last.pt.

Plot Training: from utils import utils; utils.plot_results() plots training results from coco_16img.data, coco_64img.data, 2 example datasets available in the data/ folder, which train and test on the first 16 and 64 images of the COCO2014-trainval dataset.

Image Augmentation

datasets.py applies random OpenCV-powered (https://opencv.org/) augmentation to the input images in accordance with the following specifications. Augmentation is applied only during training, not during inference. Bounding boxes are automatically tracked and updated with the images. 416 x 416 examples pictured below.

Augmentation	Description
Translation	+/- 10% (vertical and horizontal)
Rotation	+/- 5 degrees
Shear	+/- 2 degrees (vertical and horizontal)
Scale	+/- 10%
Reflection	50% probability (horizontal-only)
HSV Saturation	+/- 50%
HSV Intensity	+/- 50%

Speed

https://cloud.google.com/deep-learning-vm/
Machine type: n1-standard-8 (8 vCPUs, 30 GB memory)
CPU platform: Intel Skylake
GPUs: K80 ($0.20/hr), T4 ($0.35/hr), V100 ($0.83/hr) CUDA with Nvidia Apex FP16/32
HDD: 100 GB SSD
Dataset: COCO train 2014 (117,263 images)
Model: yolov3-spp.cfg

GPUs	batch_size	images/sec	epoch time	epoch cost
K80	64 (32x2)	11	175 min	$0.58
T4	64 (32x2)	40	49 min	$0.29
T4 x2	64 (64x1)	61	32 min	$0.36
V100	64 (32x2)	115	17 min	$0.24
V100 x2	64 (64x1)	150	13 min	$0.36
2080Ti	64 (32x2)	81	24 min	-
2080Ti x2	64 (64x1)	140	14 min	-

Inference

detect.py runs inference on any sources:

python3 detect.py --source ...

• Image: --source file.jpg
• Video: --source file.mp4
• Directory: --source dir/
• Webcam: --source 0
• RTSP stream: --source rtsp://170.93.143.139/rtplive/470011e600ef003a004ee33696235daa
• HTTP stream: --source http://wmccpinetop.axiscam.net/mjpg/video.mjpg

To run a specific models:

YOLOv3: python3 detect.py --cfg cfg/yolov3.cfg --weights yolov3.weights

YOLOv3-tiny: python3 detect.py --cfg cfg/yolov3-tiny.cfg --weights yolov3-tiny.weights

YOLOv3-SPP: python3 detect.py --cfg cfg/yolov3-spp.cfg --weights yolov3-spp.weights

Pretrained Weights

Download from: https://drive.google.com/open?id=1LezFG5g3BCW6iYaV89B2i64cqEUZD7e0

Darknet Conversion

$ git clone https://github.com/ultralytics/yolov3 && cd yolov3

# convert darknet cfg/weights to pytorch model
$ python3  -c "from models import *; convert('cfg/yolov3-spp.cfg', 'weights/yolov3-spp.weights')"
Success: converted 'weights/yolov3-spp.weights' to 'converted.pt'

# convert cfg/pytorch model to darknet weights
$ python3  -c "from models import *; convert('cfg/yolov3-spp.cfg', 'weights/yolov3-spp.pt')"
Success: converted 'weights/yolov3-spp.pt' to 'converted.weights'

mAP

• test.py --weights weights/yolov3.weights tests official YOLOv3 weights.
• test.py --weights weights/last.pt tests latest checkpoint.
• mAPs on COCO2014 using pycocotools.
• mAP@0.5 run at --nms-thres 0.5, mAP@0.5...0.95 run at --nms-thres 0.7.
• YOLOv3-SPP ultralytics is ultralytics68.pt with yolov3-spp.cfg.
• Darknet results published in https://arxiv.org/abs/1804.02767.

	Size	COCO mAP @0.5...0.95	COCO mAP @0.5
YOLOv3-tiny YOLOv3 YOLOv3-SPP YOLOv3-SPP ultralytics	320	14.0 28.7 30.5 35.4	29.1 51.8 52.3 54.3
YOLOv3-tiny YOLOv3 YOLOv3-SPP YOLOv3-SPP ultralytics	416	16.0 31.2 33.9 39.0	33.0 55.4 56.9 59.2
YOLOv3-tiny YOLOv3 YOLOv3-SPP YOLOv3-SPP ultralytics	512	16.6 32.7 35.6 40.3	34.9 57.7 59.5 60.6
YOLOv3-tiny YOLOv3 YOLOv3-SPP YOLOv3-SPP ultralytics	608	16.6 33.1 37.0 40.9	35.4 58.2 60.7 60.9

$ python3 test.py --save-json --img-size 608 --nms-thres 0.7 --weights ultralytics68.pt
Namespace(batch_size=16, cfg='cfg/yolov3-spp.cfg', conf_thres=0.001, data='data/coco.data', device='1', img_size=608, iou_thres=0.5, nms_thres=0.7, save_json=True, weights='ultralytics68.pt')
Using CUDA device0 _CudaDeviceProperties(name='GeForce RTX 2080 Ti', total_memory=11019MB)

               Class    Images   Targets         P         R   mAP@0.5        F1: 100%|███████████████████████████████████████████████████████████████████████████████████| 313/313 [09:46<00:00,  1.09it/s]
                 all     5e+03  3.58e+04    0.0481     0.829     0.589    0.0894

 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.40882
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.60026
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.44551
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.24343
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.45024
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.51362
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.32644
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.53629
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.59343
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.42207
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.63985
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.70688

Citation

Contact

Issues should be raised directly in the repository. For additional questions or comments please email Glenn Jocher at glenn.jocher@ultralytics.com or visit us at https://contact.ultralytics.com.