CoreML export failure: unexpected number of inputs for node x.2 (_convolution): 13

[Nabyssache]

Additional context

issue occur:
Converting Frontend ==> MIL Ops: 0%| | 0/970 [00:00<?, ? ops/s]Converting op 221 : constant
Adding op '221' of type const
Converting op 222 : constant
Adding op '222' of type const
Converting op 223 : constant
Adding op '223' of type const
Converting op 224 : constant
Adding op '224' of type const
Converting op 225 : constant
Converting op 226 : constant
Adding op '226' of type const
Converting op 227 : constant
Adding op '227' of type const
Converting op 228 : slice
Adding op '228' of type slice_by_index
Adding op '228_begin_0' of type const
Adding op '228_end_0' of type const
Adding op '228_stride_0' of type const
Adding op '228_end_mask_0' of type const
Converting op 229 : slice
Adding op '229' of type slice_by_index
Adding op '229_begin_0' of type const
Adding op '229_end_0' of type const
Adding op '229_stride_0' of type const
Adding op '229_end_mask_0' of type const
Converting op 230 : slice
Adding op '230' of type slice_by_index
Adding op '230_begin_0' of type const
Adding op '230_end_0' of type const
Adding op '230_stride_0' of type const
Adding op '230_end_mask_0' of type const
Converting op 231 : slice
Adding op '231' of type slice_by_index
Adding op '231_begin_0' of type const
Adding op '231_end_0' of type const
Adding op '231_stride_0' of type const
Adding op '231_end_mask_0' of type const
Converting op 232 : slice
Adding op '232' of type slice_by_index
Adding op '232_begin_0' of type const
Adding op '232_end_0' of type const
Adding op '232_stride_0' of type const
Adding op '232_end_mask_0' of type const
Converting op 233 : slice
Adding op '233' of type slice_by_index
Adding op '233_begin_0' of type const
Adding op '233_end_0' of type const
Adding op '233_stride_0' of type const
Adding op '233_end_mask_0' of type const
Converting op 234 : slice
Adding op '234' of type slice_by_index
Adding op '234_begin_0' of type const
Adding op '234_end_0' of type const
Adding op '234_stride_0' of type const
Adding op '234_end_mask_0' of type const
Converting op 235 : slice
Adding op '235' of type slice_by_index
Adding op '235_begin_0' of type const
Adding op '235_end_0' of type const
Adding op '235_stride_0' of type const
Adding op '235_end_mask_0' of type const
Converting op 236 : listconstruct
Converting op input.1 : cat
Adding op 'input.1' of type concat
Adding op 'input.1_interleave_0' of type const
Converting op 238 : listconstruct
Adding op '238' of type const
Converting op 239 : listconstruct
Adding op '239' of type const
Converting op 240 : listconstruct
Adding op '240' of type const
Converting op 241 : listconstruct
Adding op '241' of type const
Converting op x.2 : _convolution
Converting Frontend ==> MIL Ops: 2%|█ | 21/970 [00:00<00:00, 1017.80 ops/s]
CoreML export failure: unexpected number of inputs for node x.2 (_convolution): 13

Export complete (11.10s). Visualize with https://github.com/lutzroeder/netron

when I use command: python models/export.py --weights "yolov5l.pt" --img 640 --batch 1
I see #1667
my torch = 1.7.1 and torchvision= 0.8.2 torchaudio=0.7.2 coremltools=4.0

what wrong happen?

[github-actions]

👋 Hello @Nabyssache, 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://www.ultralytics.com or email Glenn Jocher at glenn.jocher@ultralytics.com.

Requirements

Python 3.8 or later with all requirements.txt dependencies installed, including torch>=1.7. To install run:

$ pip install -r requirements.txt

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 Notebook with free GPU:
• Kaggle Notebook with free GPU: https://www.kaggle.com/models/ultralytics/yolov5
• Google Cloud Deep Learning VM. See GCP Quickstart Guide
• Docker Image https://hub.docker.com/r/ultralytics/yolov5. 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), testing (test.py), inference (detect.py) and export (export.py) on MacOS, Windows, and Ubuntu every 24 hours and on every commit.

[Nabyssache]

Package Version

---

absl-py 0.11.0
attr 0.3.1
attrs 20.3.0
cachetools 4.2.0
certifi 2020.12.5
chardet 4.0.0
coremltools 4.0
cycler 0.10.0
Cython 0.29.21
google-auth 1.24.0
google-auth-oauthlib 0.4.2
grpcio 1.34.1
idna 2.10
joblib 1.0.0
kiwisolver 1.3.1
Markdown 3.3.3
matplotlib 3.3.3
mpmath 1.1.0
numpy 1.19.5
oauthlib 3.1.0
onnx 1.8.0
opencv-python 4.5.1.48
packaging 20.8
pandas 1.2.0
Pillow 8.1.0
pip 20.3.3
protobuf 3.14.0
pyasn1 0.4.8
pyasn1-modules 0.2.8
pycocotools 2.0.2
pyparsing 2.4.7
python-dateutil 2.8.1
pytz 2020.5
PyYAML 5.3.1
requests 2.25.1
requests-oauthlib 1.3.0
rsa 4.7
scikit-learn 0.24.0
scipy 1.6.0
seaborn 0.11.1
setuptools 51.1.2.post20210112
six 1.15.0
sympy 1.7.1
tensorboard 2.4.1
tensorboard-plugin-wit 1.7.0
thop 0.0.31.post2005241907
threadpoolctl 2.1.0
torch 1.7.1
torchaudio 0.7.2
torchvision 0.8.2
tqdm 4.56.0
typing-extensions 3.7.4.3
urllib3 1.26.2
Werkzeug 1.0.1
wheel 0.36.2

[glenn-jocher]

@Nabyssache coremltools is incompatible with recent versions of PyTorch. You should raise your issue directly on the coremltools repository.

[mzkaramat]

Head branch from coremltool repo which is compatible with PyTorch 1.7

pip install -Uqq git+https://github.com/apple/coremltools.git@master

[glenn-jocher]

@mzkaramat thanks for the notice! That's good to know. We don't integrate master branch branches in requirements.txt (for stability), so I will wait for a release and then update requirements.txt on the next one. If anyone is working on CoreML export though I would recommend installing as @mzkaramat recommends for the time being.

[ramondebruyn]

@mzkaramat Thank you! I've been looking for a solution to this for a week and finally came across this!

[github-actions]

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.