how to train a detector with input images of a rectangular shape 192x32?

[JVision]

Thank you for the great implementation of the algorithm. I found it is a lot more friendly than the original one.

❔Question

I need to run the yolo model inside a rectangular object (license number plate) to detect defect printed letters. The license number plate is of a fixed size 192x32. The letters could be printed with large positional variations and with large font variations.

how to set the input image size of the detector 192x32. I've tried to set --img-size to 192 and discovered in the opt.yaml file that the input image size is 192x192. isn't it a bit of waste on running the detection on a vertically enlarged image?

Additional context

I've searched rectangular input training in this issue list and found the answers are outdated.

[github-actions]

👋 Hello @JVision, thank you for your interest in 🚀 YOLOv3! 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

YOLOv3 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/yolov3
• Google Cloud Deep Learning VM. See GCP Quickstart Guide
• Docker Image https://hub.docker.com/r/ultralytics/yolov3. See Docker Quickstart Guide

Status

If this badge is green, all YOLOv3 GitHub Actions Continuous Integration (CI) tests are currently passing. CI tests verify correct operation of YOLOv3 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.

[JVision]

I found an answer here.

#332

Problem solved. thanks.

[glenn-jocher]

@JVision try python train.py --img 192 --rect

[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.