December 13, 2019

910 words 5 mins read

ultralytics/yolov3

ultralytics/yolov3

YOLOv3 in PyTorch > ONNX > CoreML > iOS

repo name ultralytics/yolov3
repo link https://github.com/ultralytics/yolov3
homepage https://www.ultralytics.com
language Jupyter Notebook
size (curr.) 6884 kB
stars (curr.) 3705
created 2018-08-26
license GNU General Public License v3.0

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 all of the pip install -U -r requirements.txt packages including:

  • torch >= 1.4
  • opencv-python
  • Pillow

All dependencies are included in the associated docker images. Docker requirements are:

  • Nvidia Driver >= 440.44
  • Docker Engine - CE >= 19.03

Tutorials

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: preemptible n1-standard-16 (16 vCPUs, 60 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: 1 TB SSD
Dataset: COCO train 2014 (117,263 images)
Model: yolov3-spp.cfg
Command: python3 train.py --img 416 --batch 32 --accum 2

GPU n --batch --accum img/s epochtime epochcost
K80 1 32 x 2 11 175 min $0.58
T4 12 32 x 264 x 1 4161 48 min32 min $0.28$0.36
V100 12 32 x 264 x 1 122178 16 min11 min $0.23$0.31
2080Ti 12 32 x 264 x 1 81140 24 min14 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

$ python3 test.py --cfg yolov3-spp.cfg --weights yolov3-spp-ultralytics.pt
Size COCO mAP@0.5…0.95 COCO mAP@0.5
YOLOv3-tinyYOLOv3YOLOv3-SPPYOLOv3-SPP-ultralytics 320 14.028.730.536.6 29.151.852.356.0
YOLOv3-tinyYOLOv3YOLOv3-SPPYOLOv3-SPP-ultralytics 416 16.031.233.940.4 33.055.456.960.2
YOLOv3-tinyYOLOv3YOLOv3-SPPYOLOv3-SPP-ultralytics 512 16.632.735.641.6 34.957.759.561.7
YOLOv3-tinyYOLOv3YOLOv3-SPPYOLOv3-SPP-ultralytics 608 16.633.137.042.1 35.458.260.761.7
$ python3 test.py --cfg yolov3-spp.cfg --weights yolov3-spp-ultralytics.pt --img 608

Namespace(batch_size=32, cfg='yolov3-spp.cfg', conf_thres=0.001, data='data/coco2014.data', device='', img_size=608, iou_thres=0.6, save_json=True, single_cls=False, task='test', weights='weights/yolov3-spp-ultralytics.pt')
Using CUDA device0 _CudaDeviceProperties(name='Tesla V100-SXM2-16GB', total_memory=16130MB)

              Class    Images   Targets         P         R   mAP@0.5        F1: 100%|█████| 157/157 [02:46<00:00,  1.06s/it]
                 all     5e+03  3.51e+04      0.51     0.667     0.611     0.574

 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.419
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.618
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.448
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.247
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.462
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.534
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.341
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.557
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.606
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.440
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.649
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.735

Speed: 6.6/1.5/8.1 ms inference/NMS/total per 608x608 image at batch-size 32

Reproduce Our Results

This command trains yolov3-spp.cfg from scratch to our mAP above. Training takes about one week on a 2080Ti.

$ python3 train.py --weights '' --cfg yolov3-spp.cfg --epochs 273 --batch 16 --accum 4 --multi

Reproduce Our Environment

To access an up-to-date working environment (with all dependencies including CUDA/CUDNN, Python and PyTorch preinstalled), consider a:

Citation

DOI

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.

comments powered by Disqus