Bienqq
/
car-detection-bayes
2
1
Fork 0
Code Issues Pull Requests Releases Wiki Activity

updates

This commit is contained in:
Glenn Jocher 2018-09-01 13:41:34 +02:00
parent 45c7d4642b
commit aa346973ae
1 changed files with 10 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
README.md
View File

@ -24,15 +24,17 @@ Run `train.py` to begin training after downloading COCO data with `data/get_coco
## Augmentation ## Augmentation
`datasets.py` applies random 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. Examples pictured below. `datasets.py` applies random 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.
- Translation: +/- 20% X and Y Augmentation | Description
- Rotation: +/- 5 degrees --- | ---
- Skew: +/- 3 degrees Translation | +/- 20% vertical and horizontal
- Scale: +/- 20% Rotation | +/- 5 degrees
- Reflection: 50% probability left-right Skew | +/- 3 degrees
- Saturation: +/- 50% Scale | +/- 20%
- Intensity: +/- 50% Reflection | 50% probability left-right
Saturation | +/- 50%
Intensity | +/- 50%
![Alt](https://github.com/ultralytics/yolov3/blob/master/data/coco_augmentation_examples.jpg "coco image augmentation") ![Alt](https://github.com/ultralytics/yolov3/blob/master/data/coco_augmentation_examples.jpg "coco image augmentation")