Converting .pt or .onnx to .pb and .tflite

[wiky231]

Search before asking

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

Question

I trained a YOLOv5s on a custom dataset on Google Colab. Now I'm trying to convert the trained weights from .pt and .onnx format to .pb and .tflite format as I want to make an Android app for my model. Does anyone know the solution? Thanks

Additional

No response

[github-actions]

👋 Hello @axlecky, 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):

• 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), validation (val.py), inference (detect.py) and export (export.py) on macOS, Windows, and Ubuntu every 24 hours and on every commit.

[glenn-jocher]

@axlecky see TFLite, ONNX, CoreML, TensorRT Export tutorial.

YOLOv5 Tutorials

• Train Custom Data  🚀 RECOMMENDED
• Tips for Best Training Results  ☘️ RECOMMENDED
• Weights & Biases Logging  🌟 NEW
• Roboflow for Datasets, Labeling, and Active Learning  🌟 NEW
• Multi-GPU Training
• PyTorch Hub  ⭐ NEW
• TFLite, ONNX, CoreML, TensorRT Export 🚀
• Test-Time Augmentation (TTA)
• Model Ensembling
• Model Pruning/Sparsity
• Hyperparameter Evolution
• Transfer Learning with Frozen Layers  ⭐ NEW
• Architecture Summary  ⭐ NEW

Good luck 🍀 and let us know if you have any other questions!

[Shashi42]

Hi @axlecky , I'm trying to do the exact same thing that you are doing. I have already trained a yolov5m model. I wish to see realtime detection in an Android app.

I'm currently using this repo for realtime object detection. App. Maybe if by chance you too are using this repo for reference, we could help each other

I have already followed the export tutorial to generate .tflite weights from .pt weights but I'm facing an issue when loading the .tflite model.

[wiky231]

Hi @Shashi42, I managed to build a simple app using this repo: https://github.com/zldrobit/tfjs-yolov5-example.git.
However, I'm trying to add more functions such as inference for gallery images etc. I will also try the repo that you mentioned in the next few days.
Do you mind leaving your email/discord for easier communication?

[Shashi42]

Sure. This is my discord username Shashi#2907.

[github-actions]

👋 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://github.com/ultralytics/yolov5/wiki
• 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]

Hey @Shashi42, glad to hear you've made progress with the Android app! When it comes to adding more functions like gallery image inference, the YOLOv5 repo at https://github.com/ultralytics/yolov5 has extensive documentation on model export and integration for different platforms, including Android.

For loading the .tflite model, could you provide more details on the specific issue you're encountering? This can help us troubleshoot the problem and find a solution.

Thanks and keep up the great work!