Difference metrics result on validation set

[n-patricia]

Search before asking

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

Question

Hi,

I have finished my training after 200 epochs and the validation set performed quite nice

However when I only run val.py once, the result drops significantly

How to get similar results for validation set on val.py without going through training process?

Best,
Novi

Additional

No response

[UltralyticsAssistant]

👋 Hello @n-patricia, thank you for your interest in YOLOv5 🚀! This is an automated response to help you get support faster. An Ultralytics engineer will follow up here shortly.

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 a minimum reproducible example to help us debug it (exact commands, dataset snippet or public sample, environment details, and full logs).

If this is a custom training ❓ Question, please provide as much information as possible, including dataset image examples and training/validation logs, and verify you are following our Tips for Best Training Results. Screenshots of metrics are helpful too 📊

Requirements

Python>=3.8.0 with all requirements.txt installed including PyTorch>=1.8. 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):

• 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, validation, inference, export and benchmarks on macOS, Windows, and Ubuntu every 24 hours and on every commit.

[Bovey0809]

@n-patricia What's the command you are using for the first screenshot?

[n-patricia]

@Bovey0809
First one just call python train.py --data data.yaml --weights ... and that is the val results from last epoch
Second one call python val.py --data data.yaml --weights ...