CoreML: export failure: PyTorch convert function for op 'tensor_split' not implemented.

[jaehyunshinML]

Hi I tried to convert the custom model to cormel with

python export.py --weights yolov5s.pt --include coreml

and

got this error message.

CoreML: export failure: PyTorch convert function for op 'tensor_split' not implemented.

I installed all the package with requirements.txt in a new virtual condo environment.

but still has the same errors.

do you may know possible solution for this? Thanks..

[github-actions]

👋 Hello @jaehyunshinML, 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.

[dmitriy-kalashnikov]

Hello, I have the same issue

python3 export.py --weights yolov5l6.pt --include engine --device 0

`export: data=data/coco128.yaml, weights=['yolov5l6.pt'], imgsz=[640, 640], batch_size=1, device=0, half=False, inplace=False, train=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=['engine']
YOLOv5 🚀 v6.1-51-g9cd89b7 torch 1.11.0+cu113 CUDA:0 (NVIDIA GeForce RTX 3090, 24265MiB)

Fusing layers...
Model Summary: 476 layers, 76726332 parameters, 0 gradients

PyTorch: starting from yolov5l6.pt with output shape (1, 25500, 85) (147.4 MB)

ONNX: starting export with onnx 1.11.0...
WARNING: The shape inference of prim::Constant type is missing, so it may result in wrong shape inference for the exported graph. Please consider adding it in symbolic function.
WARNING: The shape inference of prim::Constant type is missing, so it may result in wrong shape inference for the exported graph. Please consider adding it in symbolic function.
WARNING: The shape inference of prim::Constant type is missing, so it may result in wrong shape inference for the exported graph. Please consider adding it in symbolic function.
ONNX: export failure: Exporting the operator tensor_split to ONNX opset version 13 is not supported. Please feel free to request support or submit a pull request on PyTorch GitHub.

TensorRT: starting export with TensorRT 8.4.0.6...

TensorRT: export failure: failed to export ONNX file: yolov5l6.onnx
`

[glenn-jocher]

@dmitriy-kalashnikov @jaehyunshinML good news 😃! Your original issue may now be fixed ✅ in PR #7074. To receive this update:

• Git – git pull from within your yolov5/ directory or git clone https://github.com/ultralytics/yolov5 again
• PyTorch Hub – Force-reload model = torch.hub.load('ultralytics/yolov5', 'yolov5s', force_reload=True)
• Notebooks – View updated notebooks
• Docker – sudo docker pull ultralytics/yolov5:latest to update your image

Thank you for spotting this issue and informing us of the problem. Please let us know if this update resolves the issue for you, and feel free to inform us of any other issues you discover or feature requests that come to mind. Happy trainings with YOLOv5 🚀!

[dmitriy-kalashnikov]

Thanks, it's currently fixed.