github.com-ultralytics-yolov3_-_2019-11-28_09-36-07

github.com-ultralytics-yolov3_-_2019-11-28_09-36-07

Posted by

Download
ITEM TILE – File Size: 6.4K

YOLOv3 in PyTorch > ONNX > CoreML > iOS

61591130-f7beea00-abc2-11e9-9dc0-d6abcf4 logoname1000.png 61591093-2b4d4480-abc2-11e9-8b46-d88eb1d 50044365-9b22ac00-0082-11e9-862f-e77aee7 61591100-55066b80-abc2-11e9-9647-52c0e04

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

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.

63258271-fe9d5300-c27b-11e9-9a15-95038da

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 degreesShear | +/- 2 degrees (vertical and horizontal)Scale | +/- 10%Reflection | 50% probability (horizontal-only)HSV Saturation | +/- 50%HSV Intensity | +/- 50%

66699231-27beea80-ece5-11e9-9cad-bdf9d82

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)

GPUs | batch_size | images/sec | epoch time | epoch cost— |—| — | — | — K80 | 64 (32×2) | 11 | 175 min | $0.58T4 | 64 (32×2) | 40 | 49 min | $0.29T4 x2 | 64 (64×1) | 61 | 32 min | $0.36V100 | 64 (32×2) | 115 | 17 min | $0.24V100 x2 | 64 (64×1) | 150 | 13 min | $0.362080Ti | 64 (32×2) | 81 | 24 min | – 2080Ti x2 | 64 (64×1) | 140 | 14 min | –

Inference

detect.py runs inference on any sources:

bashpython3 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 weights/yolov3.weights64067835-51d5b500-cc2f-11e9-982e-843f7f9

YOLOv3-tiny: python3 detect.py --cfg cfg/yolov3-tiny.cfg --weights weights/yolov3-tiny.weights64067834-51d5b500-cc2f-11e9-9357-c485b15

YOLOv3-SPP: python3 detect.py --cfg cfg/yolov3-spp.cfg --weights weights/yolov3-spp.weights64067833-51d5b500-cc2f-11e9-8208-6fe1978

Pretrained Weights

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

Darknet Conversion

“`bash$ 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 0.65.
  • YOLOv3-SPP ultralytics is ultralytics68.pt with yolov3-spp.cfg.
  • Darknet results published in https://arxiv.org/abs/1804.02767.

|img-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
35.2 |29.0
51.5
52.3
53.9YOLOv3-tiny
YOLOv3
YOLOv3-SPP
YOLOv3-SPP ultralytics |416 |16.0
31.1
33.9
38.8 |32.9
55.3
56.8
58.7YOLOv3-tiny
YOLOv3
YOLOv3-SPP
YOLOv3-SPP ultralytics |608 |16.6
33.0
37.0
40.6 |35.5
57.9
60.6
60.7

“`bash$ python3 test.py –save-json –img-size 608 –nms-thres 0.65 –weights ultralytics68.ptNamespace(batchsize=16, cfg=’cfg/yolov3-spp.cfg’, confthres=0.001, data=’data/coco.data’, device=”, imgsize=608, iouthres=0.5, nmsthres=0.65, savejson=True, weights=’ultralytics68.pt’)Using CUDA device0 CudaDeviceProperties(name=’Tesla T4′, totalmemory=15079MB)

           Class    Images   Targets         P         R   mAP@0.5        F1: 100% 313/313 [06:52<00:00,  1.24it/s]             all     5e+03  3.58e+04     0.107     0.779      0.59     0.182

Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.404 <— Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.597 <— Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.438 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.241 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.444 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.511 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.326 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.533 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.570 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.393 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.614 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.691“`

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.

To restore the repository download the bundle

wget https://archive.org/download/github.com-ultralytics-yolov3_-_2019-11-28_09-36-07/ultralytics-yolov3_-_2019-11-28_09-36-07.bundle

and run:

 git clone ultralytics-yolov3_-_2019-11-28_09-36-07.bundle 

Source: https://github.com/ultralytics/yolov3
Uploader: ultralytics
Upload date: 2019-11-28