Error in convert model from pt to tflite

[qiujianchen]

Search before asking

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

Question

I use YOLOv5n.pt to train my own datasets and want to convert pytorch model to .tflite with INT8 quantization. However, I failed. So I want to ask solutions. Thank you!
(By the way, if without INT8 quantization, I can convert it successfully.)

Command:
python export.py --data data/my_datasets_4.yaml --weights runs/train/exp/weights/best.pt --imgsz 256 320 --simplify --include tflite --batch-size 1 --int8

Error:
TensorFlow Lite: export failure: module 'tensorflow.lite.python.schema_py_generated' has no attribute 'Model'

Environment:
Tensorflow==2.4.0
Pytorch==1.7.1(gpu)
python==3.8

Additional

No response

[github-actions]

👋 Hello @qiujianchen, 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 Glenn Jocher at glenn.jocher@ultralytics.com.

Requirements

Python>=3.6.0 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]

@qiujianchen I don't recognize this error, but just FYI --simplify does not apply to TFLite exports, and a recent bug with --int8 was resolved today in #6216

[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 ⭐!

[HunarAA]

@qiujianchen have you found any solution for your problem? I have used your way for converting best.pt to tflite but still not working in my flutter app

[zldrobit]

@HunarAA You could check your converted TFLite model with python detect.py --weights {the tflite model}.tflite --data {your image directory}. What's the version of YOLOv5 you used to export the model? Plz use the latest v6.1 version for exporting.

[HunarAA]

I have checked it with my webcam and it works fine. But with the flutter app it closes the app directly while the app works with YOLOv2 tflite.

Have you the command for converting YOLOv5 to tflite using v6.1?

[zldrobit]

Yes, plz see #1127 (comment).

[HunarAA]

error in "--cfg". I have my own models/dataset.yaml because I trained my own yolov5m.

the error: export.py: error: unrecognized arguments: --cfg models/dataset.yaml

[zldrobit]

Sorry for not updating #1127 (comment). There is no need for a --cfg option, and the config yaml is stored in a model weight now. Plz just ignore that argument and try again.

[glenn-jocher]

@zldrobit Apologies for the confusion. The recent changes eliminate the need for a --cfg argument. The config yaml is now stored within the model weight. Please disregard the --cfg option and reattempt the conversion. Let me know how it goes!