Convert from yolov5 to Tflite

[TehKonnos]

❔Question

How can I change the shape of input from [batch,rgb,width,height] to [batch,width,height,rgb]
I tried to change the line 53 and 101 but in the final export of tflite the imput shape has the wrong order.

Additional context

The conversion from onnx to tflite is here: https://colab.research.google.com/drive/1tCtXEJ-E6_CoveneunwGXbgy62M_dwKb?usp=sharing
But I think my problem starts in the early stages of conversion.
Thank you for your time

[github-actions]

👋 Hello @TehKonnos, 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.

[PraveenGit3]

Did u succeed in conversion to tf lite ?

[TehKonnos]

No. As I understand there are 4 options to use your pt model.

1. Run Add export and detection for TensorFlow saved_model, graph_def and TFLite #959 solution and check the custom android application he recommends.
2. Add Metadata to your file, converted from ONNX to Saved_Model to TFLITE and use android studio's ML Binding method
3. Run your .pt file on android using pytorch's method as shown here: https://github.com/pytorch/android-demo-app/tree/master/ObjectDetection
4. Train your model again with Transfer Learning from MobileNet SSD so the outputs fit Tensorflow's application.

[PraveenGit3]

I'm planning to run these yolov5 .pt on raspberry pi 4. If I convert to onxx to tf lite does it work ?

[TehKonnos]

I dont think you need any conversion. Just use detect.py there.

[zldrobit]

You could also refer to #1127 and use https://github.com/zldrobit/yolov5 for TFLite model export.

[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
• 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 ⭐!