ultralytics / yolov5

YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite
https://docs.ultralytics.com
GNU Affero General Public License v3.0
50.55k stars 16.3k forks source link

How does YOLO perform with augmented data? #8504

Closed SanjayGhanagiri closed 2 years ago

SanjayGhanagiri commented 2 years ago

Search before asking

Question

We see a lot of augmented data being used for many machine learning models. Of course model performs well when we provide around 1500 images per class which has realistic possible images in training set.

What happens when we provide augmented images which has black and white, colourised , rotated etc, these variations might not be present in a realistic scenario. Does this help model in accuracy?

In the below example it can be seen that original image of a parrot is far different from augmented versions. Does this help the model?

Screenshot 2022-07-07 at 1 09 40 PM

Additional

No response

github-actions[bot] commented 2 years ago

👋 Hello @SanjayGhanagiri, thank you for your interest in YOLOv5 🚀! Please visit our ⭐️ Tutorials to get started, where you can find quickstart guides for simple tasks like Custom Data Training all the way to advanced concepts like Hyperparameter Evolution.

If this is a 🐛 Bug Report, please provide screenshots and minimum viable code to reproduce your issue, otherwise we can not help you.

If this is a custom training ❓ Question, please provide as much information as possible, including dataset images, training logs, screenshots, and a public link to online W&B logging if available.

For business inquiries or professional support requests please visit https://ultralytics.com or email support@ultralytics.com.

Requirements

Python>=3.7.0 with all requirements.txt installed including PyTorch>=1.7. To get started:

git clone https://github.com/ultralytics/yolov5  # clone
cd yolov5
pip install -r requirements.txt  # install

Environments

YOLOv5 may be run in any of the following up-to-date verified environments (with all dependencies including CUDA/CUDNN, Python and PyTorch preinstalled):

Status

CI CPU testing

If this badge is green, all YOLOv5 GitHub Actions Continuous Integration (CI) tests are currently passing. CI tests verify correct operation of YOLOv5 training (train.py), validation (val.py), inference (detect.py) and export (export.py) on macOS, Windows, and Ubuntu every 24 hours and on every commit.

glenn-jocher commented 2 years ago

@SanjayGhanagiri 👋 Hello! Thanks for asking about image augmentation. YOLOv5 🚀 applies online imagespace and colorspace augmentations in the trainloader (but not the val_loader) 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.

YOLOv5 augmentation

Augmentation Hyperparameters

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-low.yaml

https://github.com/ultralytics/yolov5/blob/b94b59e199047aa8bf2cdd4401ae9f5f42b929e6/data/hyps/hyp.scratch-low.yaml#L6-L34

Augmentation Previews

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:

YOLOv5 Albumentations Integration

YOLOv5 🚀 is now fully integrated with Albumentations, a popular open-source image augmentation package. Now you can train the world's best Vision AI models even better with custom Albumentations 😃!

PR https://github.com/ultralytics/yolov5/pull/3882 implements this integration, which will automatically apply Albumentations transforms during YOLOv5 training if albumentations>=1.0.3 is installed in your environment. See https://github.com/ultralytics/yolov5/pull/3882 for full details.

Example train_batch0.jpg on COCO128 dataset with Blur, MedianBlur and ToGray. See the YOLOv5 Notebooks to reproduce: Open In Colab Open In Kaggle

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

SanjayGhanagiri commented 2 years ago

@glenn-jocher Thank you. Your answer was very informative. I have doubt from the augmented data.

  1. From the albumentations data, will it not confuse the model if we use green parrot and train the model, where in reality the original image of the parrot is red?
  2. YOLOv5 Training considers colour of the image right ?
glenn-jocher commented 2 years ago

@SanjayGhanagiri yes color is used by YOLOv5.

Some augmentation is useful to prevent overfitting and allow training to progress longer, but excess augmentation will hurt performance, it's up to you as the domain expert to put in place an appropriate augmentation strategy.

SanjayGhanagiri commented 2 years ago

@glenn-jocher Thanks. Your comments were very helpful.

glenn-jocher commented 11 months ago

You're welcome, @SanjayGhanagiri! I'm glad I could help. If you have any more questions or need further assistance, feel free to ask. Good luck with your YOLOv5 training! 🚀