question about export tflite

[June1124]

Search before asking

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

Question

PyTorch: starting from runs\train-cls\exp\weights\best.pt with output shape (1, 2) (2.4 MB)

TensorFlow SavedModel: starting export with tensorflow 2.8.0...

TensorFlow SavedModel: export failure: 'ClassificationModel' object has no attribute 'yaml'

TensorFlow Lite: starting export with tensorflow 2.8.0...

TensorFlow Lite: export failure: 'NoneType' object has no attribute 'call'

The above is the error reported after I trained the classification model and exported the tflite format, before I trained the detection model I could successfully export the onnx format, is there any solution?

Additional

No response

[github-actions]

👋 Hello @June1124, 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]

@June1124 thanks for the bug report! Unfortunately ClassificationModel types are not exportable to TF formats currently. We are working on adding this functionality in the future though.

[glenn-jocher]

@June1124 I've added an assert to inform users that ClassificationModel TF export is not yet supported in #9226. We will add this feature when we can in the future.