Visualization using TorchView

mert-kurttutan commented 1 year ago

Search before asking

[X] I have searched the YOLOv5 issues and found no similar feature requests.

Description

Extra improved python only visualization tool with torchview.

Hi, I have been experimenting on visualizing models of yolov5 family. It provides customizable visualization of pytorch models. Features include showing nested modules with dashed lines, or depth limit, and it is very close to plot_model of keras.

One example of yolovl6 is at the additional section.

You can see, for instance, dashed lines representing nested modules,

I saw in other issues that you promoted other visualization tools, e.g. netron. But, these might not be favorable when

you want python only tool with customization option.

The customization option becomes really useful too manage network that are too large to view.

I guess if you are convinced by the tool, either you can

promote it as another tool in addition to the existing ones
integrate as an optional visualization feature. This might be too much to ask :)

Use case

It would be really beneficial when debugging yolov5 related codes using different customization options provided in torchview.

Additional

model gv (3)

Are you willing to submit a PR?

[X] Yes I'd like to help by submitting a PR!

github-actions[bot] commented 1 year ago

👋 Hello @mert-kurttutan, 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://ultralytics.com or email support@ultralytics.com.

Requirements

Python>=3.7.0 with all requirements.txt installed including PyTorch>=1.7. 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.

github-actions[bot] commented 1 year ago

👋 Hello, this issue has been automatically marked as stale because it has not had recent activity. Please note it will be closed if no further activity occurs.

Access additional YOLOv5 🚀 resources:

Wiki – https://docs.ultralytics.com/yolov5
Tutorials – https://docs.ultralytics.com/yolov5
Docs – https://docs.ultralytics.com

Access additional Ultralytics ⚡ resources:

Ultralytics HUB – https://ultralytics.com/hub
Vision API – https://ultralytics.com/yolov5
About Us – https://ultralytics.com/about
Join Our Team – https://ultralytics.com/work
Contact Us – https://ultralytics.com/contact

Feel free to inform us of any other issues you discover or feature requests that come to mind in the future. Pull Requests (PRs) are also always welcomed!

Thank you for your contributions to YOLOv5 🚀 and Vision AI ⭐!

glenn-jocher commented 12 months ago

@mert-kurttutan hi there, thanks for sharing this visualization tool! It's great to see the community experimenting with new ways to visualize YOLOv5 models. Your example with the customizable features looks promising.

We're always open to exploring new tools and features that can benefit the YOLO community. I'll review the torchview tool and see how it can complement our existing visualization options.

If you have specific suggestions or examples of how torchview can enhance YOLOv5 model visualization, feel free to share them. Your contribution will definitely help us improve the YOLOv5 experience.

Thanks again for your support and willingness to submit a PR! Your efforts are truly appreciated.

ultralytics / yolov5