My val class loss increase

[pakcheera]

❔Question

Hello I do the insect detection in yolov5. I have 90 pictures ( 2 classes ). I use Roboflow to prepare the picture(3 augmentations per picture). then I run the model yolov5s. but I get the graph in following. I don't know why my val class increase. Can anyone help me.

Additional context

[github-actions[bot]]

👋 Hello @pakcheera, 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://www.ultralytics.com or email Glenn Jocher at glenn.jocher@ultralytics.com.

Requirements

Python 3.8 or later with all requirements.txt dependencies installed, including torch>=1.7. To install run:

$ pip install -r requirements.txt

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):

• Google Colab Notebook with free GPU:
• Kaggle Notebook with free GPU: https://www.kaggle.com/ultralytics/yolov5
• Google Cloud Deep Learning VM. See GCP Quickstart Guide
• Docker Image https://hub.docker.com/r/ultralytics/yolov5. See Docker Quickstart Guide

Status

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), testing (test.py), inference (detect.py) and export (export.py) on MacOS, Windows, and Ubuntu every 24 hours and on every commit.

[glenn-jocher]

@pakcheera overfitting is a desired training trait, if you don't see it this is a good indicator that you have not trained long enough. Ideally however all of your loss components would begin to overfit in a synchronized way. If classification loss is overfitting early, you should take steps to reduce it's gain, increase augmentation, or of course increase your dataset, as with 90 images nothing great will be achievable (think 1 or 2 orders of magnitude larger at a minimum, i.e. 1000 to 10k images).

[github-actions[bot]]

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.