The "fitness" function in train.py.

[snop222]

In the train.py, line 29, as folowing:

from utils.general import labels_to_class_weights, increment_path, labels_to_image_weights, init_seeds, \
fitness, strip_optimizer, get_latest_run, check_dataset, check_file, check_git_status, check_img_size, \
check_requirements, print_mutation, set_logging, one_cycle, colorstr

The "fitness" actually is a function defined in "utils/metrics.py".
Why it is imported "from" by "utils.general" ?
But, the train.py could be running with no error report ?

[github-actions]

👋 Hello @snop222, 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.

[glenn-jocher]

@snop222 fitness() defines a model fitness based on a weighted combination of metrics. We use fitness for hyperparameter evolution and to decide when to save a new best.pt checkpoint.

yolov5/utils/metrics.py

Lines 12 to 16 in efa4946

	def fitness(x):
	# Model fitness as a weighted combination of metrics
	w = [0.0, 0.0, 0.1, 0.9] # weights for [P, R, mAP@0.5, mAP@0.5:0.95]
	return (x[:, :4] * w).sum(1)

The function itself is in metrics.py as you noted. In train.py it could be imported directly from metrics.py, it is imported from general.py since it is already available there due to a previous import:

yolov5/utils/general.py

Line 21 in efa4946

from utils.metrics import fitness

[snop222]

Thank you vrey much.

[github-actions]

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.

[patel-zeel]

@glenn-jocher Is there any option to manually set the weights for the fitness function or define our own fitness function? We are working on a project with a constraint like "Maximize recall where precision is at least 50%". If you think this can be useful to a broader community, I'd be happy to contribute to the ultralytics library to make this possible.