car-detection-bayes/README.md

36 lines
1.9 KiB
Markdown
Raw Normal View History

2018-08-26 08:51:39 +00:00
<img src="https://storage.googleapis.com/ultralytics/UltralyticsLogoName1000×676.png" width="200">
# Introduction
This directory contains software developed by Ultralytics LLC. For more information on Ultralytics projects please visit:
http://www.ultralytics.com  
# Description
2018-08-26 09:06:01 +00:00
The https://github.com/ultralytics/yolov3 repo contains code to train YOLOv3 on the COCO dataset: https://cocodataset.org/#home. **Credit to Joseph Redmon for YOLO** (https://pjreddie.com/darknet/yolo/) and to **Erik Lindernoren for the pytorch implementation** this work is based on (https://github.com/eriklindernoren/PyTorch-YOLOv3).
2018-08-26 08:51:39 +00:00
# Requirements
Python 3.6 or later with the following `pip3 install -U -r requirements.txt` packages:
- `numpy`
- `torch`
- `opencv-python`
2018-08-26 09:05:13 +00:00
# Training
2018-08-26 08:51:39 +00:00
2018-08-26 09:12:10 +00:00
Run `train.py` to begin training after downloading COCO data with `data/get_coco_dataset.sh`. Each epoch trains on 120,000 images from the train and validate COCO sets, and tests on 5000 images from the COCO validate set. An Nvidia GTX 1080 Ti will process ~16 epochs per day. Loss plots for the bounding boxes, objectness and class confidence should appear similar to results shown here (coming soon)
2018-08-26 08:57:06 +00:00
![Alt](https://github.com/ultralytics/yolov3/blob/master/data/coco_training_loss.png "training loss")
2018-08-26 08:51:39 +00:00
2018-08-26 09:05:13 +00:00
# Inference
2018-08-26 08:51:39 +00:00
Checkpoints will be saved in `/checkpoints` directory. Run `detect.py` to apply trained weights to an image, such as `zidane.jpg` from the `data/samples` folder, shown here.
![Alt](https://github.com/ultralytics/yolov3/blob/master/data/zidane_result.jpg "example")
2018-08-26 09:05:13 +00:00
# Testing
2018-08-26 08:51:39 +00:00
Run `test.py` to test the latest checkpoint on the 5000 validation images. Joseph Redmon's official YOLOv3 weights produce a mAP of .581 using this method, compared to .579 in his paper.
# Contact
For questions or comments please contact Glenn Jocher at glenn.jocher@ultralytics.com or visit us at http://www.ultralytics.com/contact