Giters

experiencor / keras-yolo2

Easy training on custom dataset. Various backends (MobileNet and SqueezeNet) supported. A YOLO demo to detect raccoon run entirely in brower is accessible at https://git.io/vF7vI (not on Windows).

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Default augmentation can translate images but not boxes.

Fafa87 opened this issue · comments

commented

sometimes(iaa.Affine(...)) is used in default augmentation in master which can rotate and translating the image. Boxes stay on the same place with is bad (especially if you have small boxes).

The fix is to use imaug to move bboxes as well. See #107 or Rodrigo fork https://github.com/rodrigo2019/keras_yolo2 (however mind rodrigo2019#20).

commented

Hi! I have noticed this problem as well. Augmentation has been fixed in https://github.com/experiencor/keras-yolo3 or alternatively in my project https://github.com/AIWintermuteAI/aXeleRate which also supports other network types(classifier and segnet). You can check dataset augmentation in colab notebook
https://colab.research.google.com/github/AIWintermuteAI/aXeleRate/blob/master/resources/aXeleRate_test_detector.ipynb
by executing
visualize_dataset(img_folder='aXeleRate/sample_datasets/detector/imgs', ann_folder='aXeleRate/sample_datasets/detector/anns', img_size=None, jitter=True)