Skip to main content

Questions tagged [coreml]

Apple's Core ML framework and tools for making predictions using machine learning. Supports a variety of regression and classification models, as well as general-purpose neural networks.

coreml
0 votes
1 answer
31 views

Error converting Tensorflow model to CoreML model

NotImplementedError Traceback (most recent call last) Cell In[19], line 1 ----> 1 mlmodel = ct.convert(model, convert_to="mlmodel", source="tensorflow") ...
Aakash Kothari's user avatar
0 votes
0 answers
31 views

Error while exporting Tensorflow model to CoreML

'Sequential' object has no attribute '_get_save_spec' import tensorflow as tf import coremltools as ct print(tf.__version__) # Load your existing Keras model model_path = "/Users/name/Desktop/...
Aakash Kothari's user avatar
0 votes
0 answers
26 views

Image recognition CoreMl + SwiftUi.... Issue with view

I'm experiencing an issue with my SwiftUI project that uses Firebase and a CoreML model for image recognition. Despite adding various debug print statements, the process doesn't proceed beyond the ...
user102623's user avatar
0 votes
0 answers
34 views

Exporting a Bert-based PyTorch model to CoreML. How can I make the CoreML model work for any input?

I use the code below to export a Bert-based PyTorch model to CoreML. Since I used dummy_input = tokenizer("A French fan", return_tensors="pt") the CoreML model only works with ...
Franck Dernoncourt's user avatar
0 votes
0 answers
39 views

How can one convert a .mlpackage Core ML model to a .mlmodel Core ML model?

How can one convert a .mlpackage model to a .mlmodel model? Example of a .mlpackage Core ML model created on Ubuntu 20.04 (tested with Python 3.10 and torch 2.3.1) with Hugging Face's Exporters lib: ...
Franck Dernoncourt's user avatar
-3 votes
1 answer
46 views

How can one run a Core ML model on macOS 10.12?

https://developer.apple.com/documentation/coreml mentions macOS 10.13+: How can one run a Core ML model on macOS 10.12? Example of a Core ML model created on Ubuntu 20.04 (tested with Python 3.10 ...
Franck Dernoncourt's user avatar
0 votes
1 answer
71 views

"RuntimeError: BlobWriter not loaded" error when exporting a PyTorch model to CoreML. How to fix it?

I get a "RuntimeError: BlobWriter not loaded" error when exporting a PyTorch model to CoreML. How to fix it? Same issue with Python 3.11 and Python 3.10. Same issue with torch 2.3.1 and 2.2....
Franck Dernoncourt's user avatar
0 votes
0 answers
107 views

"Failed to load _MLModelProxy: No module named 'coremltools.libcoremlpython'"when converting an ONNX model to CoreML with onnx-coreml lib. How to fix?

I try to use the onnx-coreml lib to convert an ONNX model to CoreML: import onnx from onnx_coreml import convert onnx_model = onnx.load('model.onnx') coreml_model = convert(onnx_model) coreml_model....
Franck Dernoncourt's user avatar
0 votes
0 answers
52 views

How can I export a tokenizer from Huggingface transformers to CoreML?

I load a tokenizer and a Bert model from Huggingface transformers, and export the Bert model to CoreML: from transformers import AutoTokenizer, AutoModelForTokenClassification import torch # Load the ...
Franck Dernoncourt's user avatar
1 vote
2 answers
99 views

Japanese Vertical text recognition with VNRecognizeTextRequest not working

I'm using the Apple OCR capabilities provided by the Vision Framework to recognize text in images. While I've had great success with horizontal text in Japanese, Korean, and Chinese, I'm encountering ...
Basel's user avatar
  • 630
0 votes
0 answers
33 views

CoreML object detection works in Xcode model preview but not in code with VNCoreMLRequest

I've been working on an object detection project for several weeks now. I've finally got the model detecting my objects accurately, with a near 90% confidence interval for most objects. When I pull ...
Warblr's user avatar
  • 1,188
0 votes
0 answers
29 views

The Coreml Model I Converted Using YOLOV is Performing Very Poorly in The iOS Application

I converted my custom model trained with YOLOv8m to a CoreML model: from ultralytics import YOLO model_path="{best.pt model}" model=YOLO(model_path) model.export(format='coreml', nms=True, ...
aka.betta's user avatar
0 votes
1 answer
21 views

Troubleshooting onnxruntime inference - X num_dims does not match W num_dims

Using the nnhash.py script found here: https://github.com/AsuharietYgvar/AppleNeuralHash2ONNX # Copyright 2021 Asuhariet Ygvar # # Licensed under the Apache License, Version 2.0 (the "License&...
Joshua Terrill's user avatar
0 votes
0 answers
30 views

Race Conditions and Queue Usage in Swift Project Using CoreMotion, CoreML, and WatchConnectivity

I am working on a Swift project involving CoreMotion, CoreML, and WatchConnectivity. The setup involves a Watch app sending CoreMotion data to a phone app at a rate of 0.1 seconds. The phone app ...
Megool's user avatar
  • 989
1 vote
0 answers
36 views

If a PyTorch model can be converted to onnx, can it always be converted to CoreML?

If a PyTorch model can be converted to ONNX, can it always be converted to CoreML?
Franck Dernoncourt's user avatar

15 30 50 per page
1
2 3 4 5
63