Export .pt to .onnx with half precision failure.

[1chimaruGin]

Search before asking

• I have searched the YOLOv5 issues and found no similar bug report.

YOLOv5 Component

No response

Bug

Command used to export:
python export.py --weights yolov5s.pt --include openvino --half

Error

export: data=data/coco128.yaml, weights=['yolov5s.pt'], imgsz=[640, 640], batch_size=1, device=cpu, half=True, inplace=False, train=False, keras=False, optimize=False, int8=False, dynamic=False, simplify=False, opset=12, verbose=False, workspace=4, nms=False, agnostic_nms=False, topk_per_class=100, topk_all=100, iou_thres=0.45, conf_thres=0.25, include=['openvino']
YOLOv5 🚀 v6.1-287-g63ba0cb Python-3.9.12 torch-1.10.0 CPU

Fusing layers... 
YOLOv5s summary: 213 layers, 7225885 parameters, 0 gradients, 16.5 GFLOPs

PyTorch: starting from yolov5s.pt with output shape (1, 25200, 85) (14.1 MB)

ONNX: starting export with onnx 1.11.0...
ONNX: export failure: "unfolded2d_copy" not implemented for 'Half'

OpenVINO: starting export with openvino 2022.1.0-7019-cdb9bec7210-releases/2022/1...
[ ERROR ]  The "yolov5s.onnx" is not existing file or directory

OpenVINO: export failure: Command '['mo', '--input_model', 'yolov5s.onnx', '--output_dir', 'yolov5s_openvino_model/', '--data_type', 'FP16']' returned non-zero exit status 1.

Environment

OS: ubuntu 20.04
Python: 3.9
Pytorch: 1.10

Minimal Reproducible Example

No response

Additional

No response

Are you willing to submit a PR?

• Yes I'd like to help by submitting a PR!

[github-actions]

👋 Hello @1chimaruGin, 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]

@1chimaruGin --half exports usually require a GPU, i.e. --half --device 0:

!python export.py --weights yolov5s.pt --include openvino --half --device 0

But be aware that OpenVINO inference is only supported on CPU currently, and I'm not sure if --half inference will work there. Let me know what happens!

[glenn-jocher]

@1chimaruGin I've improved error reporting for this use case in #8522 so users will now get a message to repeat --half exports on a GPU, i.e. with --device 0