Skip to content
This repository has been archived by the owner on Dec 21, 2023. It is now read-only.

Mac M2 model.export_coreml('.mlmodel') Unable to export model #3461

Open
69Big opened this issue Oct 21, 2022 · 1 comment
Open

Mac M2 model.export_coreml('.mlmodel') Unable to export model #3461

69Big opened this issue Oct 21, 2022 · 1 comment

Comments

@69Big
Copy link

69Big commented Oct 21, 2022

This is my code:
import turicreate as tc
image_folder = 'image1/训练集'
data = tc.image_analysis.load_images(image_folder, with_path=True)
data['label'] = data['path'].apply (lambda path: 'D_4015' if 'D_4015' in path else 'DB_013')
data.save('diller.sframe')
train_data, test_data = data.random_split(0.8, seed=2)
model = tc.image_classifier.create(train_data, target='label')
predictions = model.predict(test_data)
metrics = model.evaluate(test_data)
model.export_coreml('diller.mlmodel')
But an error occurred while exporting the model
Error code:
WARNING:root:scikit-learn version 1.1.2 is not supported. Minimum required version: 0.17. Maximum required version: 0.19.2. Disabling scikit-learn conversion API.
zsh: illegal hardware instruction /opt/anaconda3/envs/diller/bin/python
How can I solve this problem? Apple computers do not support Apple modules, which surprised me.

@69Big
Copy link
Author

69Big commented Oct 21, 2022

M2 cannot return scikit born version 0.19.2; I tried many methods in the evening and asked a great god to help me solve this problem. I'm new

Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant