Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

CoreML export failure: For an ML Program, extension must be .mlpackage (not .mlmodel). #1918

Open
matt-d opened this issue Nov 14, 2023 · 1 comment · May be fixed by #1919
Open

CoreML export failure: For an ML Program, extension must be .mlpackage (not .mlmodel). #1918

matt-d opened this issue Nov 14, 2023 · 1 comment · May be fixed by #1919

Comments

@matt-d
Copy link

matt-d commented Nov 14, 2023 •
edited
Loading

When trying to convert tiny via:

python export.py --weights tiny.pt --img-size 640 640

Running MIL backend_mlprogram pipeline: 100%|██████████| 12/12 [00:00<00:00, 553.37 passes/s] CoreML export failure: For an ML Program, extension must be .mlpackage (not .mlmodel). Please see https://coremltools.readme.io/docs/unified-conversion-api#target-conversion-formats to see the difference between neuralnetwork and mlprogram model types.

torchlite and onnx exports successfully.

Starting TorchScript-Lite export with torch 1.10.0a0+3fd9dcf... TorchScript-Lite export success, saved as /train/runs/train/yolov7/weights/tiny.torchscript.ptl

Starting ONNX export with onnx 1.8.204... ONNX export success, saved as /train/runs/train/yolov7/weights/tiny.onnx
@matt-d matt-d linked a pull request Nov 14, 2023 that will close this issue
Open
@N3XT14
Copy link

N3XT14 commented Mar 12, 2024

Hi, Do you know how to interpret the result of the CoreML exported mlpackage predictions?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging a pull request may close this issue.

use .mlpackage format matt-d/yolov7
2 participants
@matt-d @N3XT14