Val Loss smaller than Train Loss

[st162053]

Search before asking

• [X] I have searched the YOLOv5 issues and discussions and found no similar questions.

Question

Hi, as seen in the graph my val losses are constantly lower than my train losses. Why is that and is val>train a sign for overfitting? Or does it only occur with the increase of the val losses? Thanks

Additional

No response

[glenn-jocher]

@st162053 this is normal. Train images are augmented (harder) and the val images are not (easier).

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.

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:

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

[st162053]

Great. Thank you! Would you recommend using an annotated test dataset after train and validation for evaluation of the model?

[glenn-jocher]

@st162053 main purpose of a test set is competition holdout with no public labels.