Data-Augmentation-for-Object-Detection

Data Augmentation For Object Detection using Pytorch and PIL (image from VOC dataset)

• [x] Adjust Contrast
• [x] Adjust Brightness
• [x] Adjust saturation
• [x] Lighting Noise
• [x] Flip
• [x] Rotate
• [x] Random crop
• [x] Zoom out (expand image)
• [x] Rotate only bouding box (optional)
• [x] Cutout
• [x] Mixup

I wrote a repo: Implementation of Single Shot MultiBox Detector (SSD) using some data augmentation strategies. Check it out!