Questions about images that are augmentation during Train

[LEEGILJUN]

Dear Developers,

I have a few questions while studying yolo v5.

I known what the hyperparameters for image augmentation are from the link below https://github.com/ultralytics/yolov5/issues/607 https://github.com/ultralytics/yolov5/issues/4342

I'm asking because I don't understand the code about augmentation working

1. How many images are created when I use the augmentation method when Train? If all 9 parameters are operated, it will be x9 times the original image when am I training?

2. For example, when all augmentation methods are applied to images, Is it possible to control how many times the total amount of training image data is compared to the original image?

3. Is only one augmentation method applied to one image? Or can multiple augmentation methods be applied to one image?

4. Does augmentation only work when I am Train or Test? and is the augmentation image was included when test or validation?

5. Is there a function to save the multiplied image augmentation?

6. last year, yolov5 is included test.py and detect.py but now only val.py. what is different between test.py and val.py

[glenn-jocher]

@LEEGILJUN 👋 Hello! Thanks for asking about image augmentation. YOLOv5 🚀 applies online imagespace and colorspace augmentations in the trainloader (but not the testloader) to present a new and unique augmented Mosaic (original image + 3 random images) each time an image is loaded for training. Images are never presented twice in the same way.

The hyperparameters used to define these augmentations are in your hyperparameter file (default data/hyp.scratch.yaml) defined when training:

python train.py --hyp hyp.scratch.yaml

https://github.com/ultralytics/yolov5/blob/90b7895d652c3bd3d361b2d6e9aee900fd67f5f7/data/hyp.scratch.yaml#L1-L33

You can view the effect of your augmentation policy in your train_batch*.jpg images once training starts. These images will be in your train logging directory, typically yolov5/runs/train/exp:

train_batch0.jpg shows train batch 0 mosaics and labels:

Good luck and let us know if you have any other questions!

[LEEGILJUN]

Hello Thank you for answer. Since the question is not resolved, I will ask again.

1. If the number of original training images is 1000, how many images are there in total after augmentation??
2. I understood your answer as follows. The original image and 9 augmentation methods are used to create a mosaic with 1+3 combined. So is the augmentation applied to the original images randomly to make a mosaic? When I use all 12 hyper-parameters??
3. How many mosaic images were finally created?? Can I instead of saving this as a batch image, save it in a separate folder

Thank you

[glenn-jocher]

@LEEGILJUN YOLOv5 🚀 applies online imagespace and colorspace augmentations in the trainloader (but not the testloader) to present a new and unique augmented Mosaic (original image + 3 random images) each time an image is loaded for training. Images are never presented twice in the same way.

[github-actions[bot]]

👋 Hello, this issue has been automatically marked as stale because it has not had recent activity. Please note it will be closed if no further activity occurs.

Access additional YOLOv5 🚀 resources:

• Wiki – https://github.com/ultralytics/yolov5/wiki
• Tutorials – https://docs.ultralytics.com/yolov5
• Docs – https://docs.ultralytics.com

Access additional Ultralytics ⚡ resources:

• Ultralytics HUB – https://ultralytics.com/hub
• Vision API – https://ultralytics.com/yolov5
• About Us – https://ultralytics.com/about
• Join Our Team – https://ultralytics.com/work
• Contact Us – https://ultralytics.com/contact

Feel free to inform us of any other issues you discover or feature requests that come to mind in the future. Pull Requests (PRs) are also always welcomed!

Thank you for your contributions to YOLOv5 🚀 and Vision AI ⭐!