I was download the ultralytics PyTorch pt and using export.py with nms (CoreML coming up split_with_sizes expects split_sizes to sum exactly to 8500 (input tensor's size at dimension 1), but got split_sizes=[4, 1, 10] error)

[gambobill]

Search before asking

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

Question

python3 export.py --weights model-5.pt --include coreml --nms
export: data=data/coco128.yaml, weights=['model-5.pt'], imgsz=[640, 640], batch_size=1, device=cpu, half=False, inplace=False, keras=False, optimize=False, int8=False, dynamic=False, simplify=False, opset=17, verbose=False, workspace=4, nms=True, agnostic_nms=False, topk_per_class=100, topk_all=100, iou_thres=0.45, conf_thres=0.25, include=['coreml']
YOLOv5 🚀 v7.0-162-gc3e4e94 Python-3.8.0 torch-2.0.0 CPU

[W NNPACK.cpp:64] Could not initialize NNPACK! Reason: Unsupported hardware.
YOLOv5s6u summary (fused): 253 layers, 15257560 parameters, 0 gradients, 24.2 GFLOPs

PyTorch: starting from model-5.pt with output shape (1, 14, 8500) (29.5 MB)
Torch version 2.0.0 has not been tested with coremltools. You may run into unexpected errors. Torch 1.13.1 is the most recent version that has been tested.

CoreML: starting export with coremltools 6.2...
CoreML: export failure ❌ 1.3s: split_with_sizes expects split_sizes to sum exactly to 8500 (input tensor's size at dimension 1), but got split_sizes=[4, 1, 10]
CoreML Pipeline: starting pipeline with coremltools 6.2...
Traceback (most recent call last):
File "export.py", line 818, in
main(opt)
File "export.py", line 813, in main
run(**vars(opt))
File "/Library/Frameworks/Python.framework/Versions/3.8/lib/python3.8/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "export.py", line 733, in run
pipeline_coreml(ct_model, im, file, model.names, y)
File "export.py", line 540, in pipeline_coreml
spec = model.get_spec()
AttributeError: 'NoneType' object has no attribute 'get_spec'

Additional

No response

[github-actions]

👋 Hello @gambobill, 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 a minimum reproducible example to help us debug it.

If this is a custom training ❓ Question, please provide as much information as possible, including dataset image examples and training logs, and verify you are following our Tips for Best Training Results.

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):

• 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, validation, inference, export and benchmarks on macOS, Windows, and Ubuntu every 24 hours and on every commit.

Introducing YOLOv8 🚀

We're excited to announce the launch of our latest state-of-the-art (SOTA) object detection model for 2023 - YOLOv8 🚀!

Designed to be fast, accurate, and easy to use, YOLOv8 is an ideal choice for a wide range of object detection, image segmentation and image classification tasks. With YOLOv8, you'll be able to quickly and accurately detect objects in real-time, streamline your workflows, and achieve new levels of accuracy in your projects.

Check out our YOLOv8 Docs for details and get started with:

pip install ultralytics

[glenn-jocher]

@gambobill hi there,

It looks like you're encountering an issue with exporting the YOLOv5 model to CoreML. The error message indicates that "split_with_sizes expects split_sizes to sum exactly to 8500", which suggests that the number of output classes may not be correct.

One possible solution is to adjust the nc parameter in your data/coco128.yaml file to match the number of classes in your dataset. This could help ensure that the output tensor has the correct shape.

In addition, it seems that you're using Torch version 2.0.0, which hasn't been tested with coremltools. You may want to try downgrading to Torch 1.13.1, which is a version that has been tested with coremltools.

I hope this helps! Let us know if you have any further questions or concerns.

[github-actions]

👋 Hello there! We wanted to give you a friendly reminder that this issue has not had any recent activity and may be closed soon, but don't worry - you can always reopen it if needed. If you still have any questions or concerns, please feel free to let us know how we can help.

For additional resources and information, please see the links below:

• Docs: https://docs.ultralytics.com
• HUB: https://hub.ultralytics.com
• Community: https://community.ultralytics.com

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 YOLO 🚀 and Vision AI ⭐