Is YOLO predicting on the validation set?

[tuh00621]

❔Question

I was looking at the test_batch_labels and test_batch_pred images that it gives me after training a model, and the images in the train set have prediction boxes while the images in the validation set do not. Is it making predictions on the validation set despite this?

Additional context

[github-actions[bot]]

👋 Hello @tuh00621, 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 and Kaggle notebooks with free GPU:
• Google Cloud Deep Learning VM. See GCP Quickstart Guide
• Amazon Deep Learning AMI. See AWS Quickstart Guide
• Docker Image. 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.

[AyushExel]

If I got the question right, I think you're asking if the predictions are made on the validation set during the training process. Yes, the model is evaluated on the validation set after every training epoch.

[tuh00621]

@AyushExel When viewing test_batch_labels and test_batch_pred image files in /runs/train/[name], the images in the train set have prediction boxes, while the images in the validation set do not. I'm not sure why this happens. I assume it's still making predictions on the validation set after every epoch but I wanted to make sure this was happening since it's not showing me the boxes in the validation set like it does for the train set.

[AyushExel]

I guess those mosaics are a sample of training images with their labels. But yes, the validation is done validation set for every epoch.

[tuh00621]

Okay, I thought it was still doing it but wanted to make sure. It's still weird how it shows the boxes for only the train set but not the val set.

[glenn-jocher]

@tuh00621 train.jpg mosaics are produced only during epoch 0. test.jpg images are produced only during first and last epoch.

Metrics are evaluated on val set every epoch.

[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.