Unable to load CoreML.framework. Cannot make predictions. #372

pokidyshev · 2019-06-10T21:06:04Z

I've got the latest coremltools installed from source.

I can't run model.predict because it gives exception:

Exception                                 Traceback (most recent call last)
<ipython-input-32-c70d9e92a144> in <module>
     54 
     55 
---> 56 coreml_model.predict({"input": np.zeros((1, 10, 4, 1, 1))})
     57 

~/.local/share/virtualenvs/FaceBoxes.PyTorch-kg-NzRFz/src/coremltools/coremltools/models/model.py in predict(self, data, useCPUOnly, **kwargs)
    339 
    340             if not _MLModelProxy:
--> 341                 raise Exception('Unable to load CoreML.framework. Cannot make predictions.')
    342             elif _MLModelProxy.maximum_supported_specification_version() < self._spec.specificationVersion:
    343                 engineVersion = _MLModelProxy.maximum_supported_specification_version()

Exception: Unable to load CoreML.framework. Cannot make predictions.

Here is my snippet:

import onnx
import torch
import numpy as np

from torch import nn
from onnx import onnx_pb
from onnx_coreml import convert


class Dummy(nn.Module):
    def __init__(self):
        super().__init__()
        self.priors = torch.randn(10, 4)
        self.variances = [1, 1]
    
    def forward(self, loc):
        boxes = torch.cat([
            self.priors[:, :2] + loc[:, :2] * self.variances[0] * self.priors[:, 2:],
            self.priors[:, 2:] * torch.exp(loc[:, 2:] * self.variances[1])], 1)
        boxes = torch.cat([boxes[:, :2] - boxes[:, 2:] / 2, boxes[:, 2:]], 1)
        boxes = torch.cat([boxes[:, :2], boxes[:, 2:] + boxes[:, :2]], 1)
        return boxes

model = Dummy()

dummy_input = torch.randn(10, 4)

model_name = 'dummy'
input_names = ['input']
output_names = ['out']
torch.onnx.export(model, dummy_input, f"{model_name}.onnx", verbose=False,
                  input_names=input_names, output_names=output_names)

model_in = f"{model_name}.onnx"
model_out = f"{model_name}.mlmodel"

model_file = open(model_in, 'rb')
model_proto = onnx_pb.ModelProto()
model_proto.ParseFromString(model_file.read())

coreml_model = convert(model_proto)
coreml_model.save(model_out)

# this line gives Exception
coreml_model.predict({"input": np.zeros((1, 10, 4, 1, 1))})

The text was updated successfully, but these errors were encountered:

TobyRoseman · 2019-06-10T22:54:20Z

@pokidyshev - What version of Python are you using? Also are you using the 3.0b1 version of coremltools?

pokidyshev · 2019-06-11T09:46:40Z

@TobyRoseman
I’m using python 3.6 and coremltools 3.0b1
The same thing with 2.1.0

TobyRoseman · 2019-06-11T19:19:36Z

I'm seeing a similar issue. I'm on macOS 10.14.6.

I downloaded the MNIST classifier from the Core ML Model page. The following code works fine with coremltools version 2.1.0, for all version of Python support by 2.1.0 (i.e. 2.7, 3.5, 3.6):

import coremltools
from PIL import Image
import numpy as np

data = np.empty((28,28), dtype=np.uint8)
input_image = Image.fromarray(data)

model = coremltools.models.MLModel('./Downloads/MNISTClassifier.mlmodel')
print(model.predict({'image': input_image}))

Using the same code with coremltools version 3.0b1, it only works for Python 2.7.

For Python 3.6, I get the following error when I try to load the model:

Fatal Python error: PyThreadState_Get: no current thread

Abort trap: 6

For Python 3.5 and 3.7 I get the following error when I try to call predict on the model:

Traceback (most recent call last):
  File "/Users/tobyroseman/backup/cmt_issues.py", line 9, in <module>
    print(model.predict({'image': input_image}))
  File "/Users/tobyroseman/anaconda3/envs/env_name/lib/python3.7/site-packages/coremltools/models/model.py", line 341, in predict
    raise Exception('Unable to load CoreML.framework. Cannot make predictions.')
Exception: Unable to load CoreML.framework. Cannot make predictions.

If I modify the install code to remove this line from a try/except block, I get the following error:

    334 
    335             #try:
--> 336             from ..libcoremlpython import _MLModelProxy
    337             #except:
    338             #    _MLModelProxy = None

ImportError: dlopen(/Users/tobyroseman/Documents/turicreate-py37/deps/env/lib/python3.7/site-packages/coremltools/libcoremlpython.so, 2): Library not loaded: /Library/Frameworks/Python.framework/Versions/3.7/Python
  Referenced from: /Users/tobyroseman/Documents/turicreate-py37/deps/env/lib/python3.7/site-packages/coremltools/libcoremlpython.so
  Reason: image not found

pokidyshev · 2019-06-11T20:17:19Z

On my setup it also happens on 2.1.0 because of slice operation (x[:,:,:2]), when I change indexing with torch.split the error disappears.

staubda · 2019-06-13T01:09:14Z

Also getting the
'Unable to load CoreML.framework. Cannot make predictions.'
error running Python 3.6 and coremltools 3.01b.

Getting further using Python 2.7, although hitting a different error (maybe my fault):
The model expects input feature Preprocessor__sub__0 to be an image, but the input is of type 5.

EDIT:
Got things working by switching to Python 2.7 and feeding in an Image rather than a numpy array.

Necross · 2019-07-02T21:21:18Z

Are you hitting the same issue with coremltools3.0b2?

TobyRoseman · 2019-07-02T23:49:22Z

@Necross - this is still broken with the 3.0b2 wheel. The code I shared previously in this issues fails if you're using Anaconda Python. It does however work if you are using Python downloaded from python.org.

bhushan23 · 2019-07-06T00:03:38Z

Problem is missing libcoremlpython.so from

< PYTHON SITE PACKAGE PATH >/coremltools/

In my case PYTHON SITE PACKAGE PATH = /Users/bhushansonawane/miniconda3/envs/py36/lib/python3.6/site-packages/coremltools-3.0b2-py3.6.egg/coremltools

Following worked for me-

1. Build from source - provide correct env path
2. Use setup.py in build directory to copy generated libcoremlpython.so

build from source as follow

1. cd to root of coremltools
2. mkdir build && cd build
3. cmake \
  -DPYTHON_EXECUTABLE:FILEPATH=/Users/bhushansonawane/miniconda3/envs/py35/bin/python \
  -DPYTHON_INCLUDE_DIR=/Users/bhushansonawane/miniconda3/envs/py35/include/python3.5m/ \
  -DPYTHON_LIBRARY=/Users/bhushansonawane/miniconda3/envs/py35/lib/python3.5/ \
../
4. make install
4. cp ../setup.py ./
5. python setup.py install

python setup.py install copies coremltools directly to the package directory and hence misses libcoremlpython library
Not using DPYTHON_LIBRARY during cmake leads to

Fatal Python error: PyThreadState_Get: no current thread

which I am not sure of why yet

I have tested this on python3.5, python3.6 works fine for me.

@TobyRoseman could you please give it a try?

TobyRoseman · 2019-07-08T20:15:14Z

@bhushan23 - that works for me too. Thank you so much for your help!

I was trying something very similar but was missing the -DPYTHON_LIBRARY= parameter. I've created a pull request (#394) to add that to the instructions.

TobyRoseman · 2019-08-07T00:02:42Z

This has been fixed in the most recent release. Please install the fourth beta (pip install coremltools==3.0b4).

motasay · 2019-08-07T17:35:03Z

I have 3.0b4 and am facing the same issue when trying to predict with the model. Python 3.6.9 and macOS 10.14.6.

> import coremltools

> feature_names = list(map(lambda x: str(x), X_train.columns.values))
> output_names = "card_index"
> coreml_model = coremltools.converters.sklearn.convert(clf, input_features=feature_names,
                                                  output_feature_names=output_names)

> dummy_inputs = {x:0 for x in feature_names}
> coreml_model.predict(dummy_inputs)

exception loading model proxy: dlopen(/Users/motasim/.pyenv/versions/3.6.9/envs/BalootAI-py369/lib/python3.6/site-packages/coremltools/libcoremlpython.so, 2): Symbol not found: _objc_opt_class
  Referenced from: /Users/xxxx/.pyenv/versions/3.6.9/envs/AI-py369/lib/python3.6/site-packages/coremltools/libcoremlpython.so (which was built for Mac OS X 10.15)
  Expected in: /usr/lib/libobjc.A.dylib
 in /Users/xxxx/.pyenv/versions/3.6.9/envs/AI-py369/lib/python3.6/site-packages/coremltools/libcoremlpython.so

---------------------------------------------------------------------------
Exception                                 Traceback (most recent call last)
<ipython-input-20-b61708773172> in <module>
      5 
      6 dummy_inputs = {x:0 for x in feature_names}
----> 7 model.predict(dummy_inputs)

~/.pyenv/versions/3.6.9/envs/AI-py369/lib/python3.6/site-packages/coremltools/models/model.py in predict(self, data, useCPUOnly, **kwargs)
    343 
    344             if not _MLModelProxy:
--> 345                 raise Exception('Unable to load CoreML.framework. Cannot make predictions.')
    346             elif _MLModelProxy.maximum_supported_specification_version() < self._spec.specificationVersion:
    347                 engineVersion = _MLModelProxy.maximum_supported_specification_version()

Exception: Unable to load CoreML.framework. Cannot make predictions.

TobyRoseman · 2019-08-07T18:11:38Z

@motasay - I just tried with Python 3.6 and 3.0b4. You're right it's not working. I'm reopening this issue.

Looks like we've had a regression. This issue is fixed in 3.0b3.

josephsieh · 2019-08-23T05:53:07Z

python 3.7.4 with coremltools 3.0b5 has the same issue :

exception loading model proxy: dlopen(aanaconda3/envs/coreml/lib/python3.7/site-packages/coremltools/libcoremlpython.so, 2): 
Library not loaded: /Library/Frameworks/Python.framework/Versions/3.7/Python
Referenced from: /aanaconda3/envs/coreml/lib/python3.7/site-packages/coremltools/libcoremlpython.so

python 3.7.4 with coremltools 3.0b3 works properly though.

Necross · 2019-08-23T18:18:02Z

@josephsieh which operating system are you using?

josephsieh · 2019-08-23T18:54:45Z

@Necross macOS Mojave 10.14.6

zhao15 · 2019-09-14T06:06:38Z

macOS 10.15 (19A558d), python3.7 , coremltools 3.0b5
same issue.

aseemw · 2019-09-14T16:27:03Z

@zhao15 3.0b6 wheels have been released as well, which should fix the issue. Can you try that as well?

josephsieh · 2019-09-18T22:54:15Z

Now it's working again. Tested on python 2.7.16 and python 3.7.4

1duo · 2019-09-18T23:00:38Z

macOS 10.15 (19A558d), python3.7 , coremltools 3.0b5
same issue.

Can you verify with coremltools==3.0b6? Thanks.

1duo · 2019-09-18T23:00:45Z

Now it's working again. Tested on python 2.7.16 and python 3.7.4

Thanks for verifying!

yaysummeriscoming · 2020-01-31T13:16:37Z

I'm getting the same issue. Running 10.14.6, tried both python 3.6 and 3.7. Also tried coremltools 3.0, 3.1 and 3.2 and building from source as per bhushan23's instructions. Any ideas?

AryanGold · 2020-03-16T18:58:21Z

I'm getting the same issue. Running 10.14.6, tried both python 3.6 and 3.7. Also tried coremltools 3.0, 3.1 and 3.2 and building from source as per bhushan23's instructions. Any ideas?

You should try manually copy builded library 'libcoremlpython.so' to 'site-packages/..../coremltools' folder.

I builded Coremltools from source as mentioned bhushan23 in folder: "/Users/admin/temp/coremltools/" and then copy library.
sample:
cp /Users/admin/temp/coremltools/coremltools/libcoremlpython.so /Users/admin/Library/Python/3.7/lib/python/site-packages/coremltools-3.3-py3.7.egg/coremltools/
and all works

wmpauli · 2020-07-28T20:05:12Z

I'm having the same issue, with coremltools==4.0b2 (also tried down to 3.3).

the library file seems to be in the right place. /lib/python3.7/site-packages/coremltools/libcoremlpython.so

with python=3.7.7 torchvision=0.6.1 and torch=1.5.1

I'm getting this error message:
exception loading model proxy: dlopen(/Users/[...]/miniconda3/envs/[..]/lib/python3.7/site-packages/coremltools/libcoremlpython.so, 2): Symbol not found: OBJC_CLASS$_MLModelConfiguration
Referenced from: /Users/[..]/miniconda3/envs/[..]/lib/python3.7/site-packages/coremltools/libcoremlpython.so (which was built for Mac OS X 10.16)
Expected in: /System/Library/Frameworks/CoreML.framework/Versions/A/CoreML
in /Users/[..]/miniconda3/envs/[..]/lib/python3.7/site-packages/coremltools/libcoremlpython.so

CoreML export failure: Unable to load CoreML.framework. Cannot make predictions.

mac os version: 10.13.6

I can't even get it to work on the example from the coremltools documentation:

import coremltools as ct
import torch
import torchvision

model = torchvision.models.mobilenet_v2()
model.eval()
example_input = torch.rand(1, 3, 256, 256)
traced_model = torch.jit.trace(model, example_input)

input = ct.TensorType(name='input_name', shape=(1, 3, 256, 256))
mlmodel = ct.convert(traced_model, inputs=[input], minimum_deployment_target=ct.target.macOS15)
results = mlmodel.predict({"input": example_input.numpy()})
print(results['1651']) # 1651 is the node name given by PyTorch's JIT

Vozf · 2020-08-19T11:21:53Z

It still reproduces with 4.0b3

bhushan23 · 2020-08-19T18:33:07Z

@Vozf @wmpauli could you please try installing coremltools from following wheels?(https://github.com/apple/coremltools/releases/tag/4.0b3) in following order?

py3 wheels for your Mac version
py3 any wheels

Vozf · 2020-08-19T18:35:40Z

Recreated the whole env and this error is gone for me. Although previous env was with python3.8, so this may have been an issue

wmpauli · 2020-08-19T19:00:20Z

@bhushan23 , I was also able by downgrading the python version. I don't have my mac with me right now, but i think both 3.6 and 3.7 worked.

TobyRoseman · 2020-08-19T22:24:09Z

Yes, this is broken again, at least in Python 3.8. It was working properly in 4.0b2. Reopening.

TobyRoseman · 2020-08-21T03:17:18Z

It seems I spoke too soon when I said that it was working properly in 4.0b2. Some of the wheels for that version also do not seem to work correctly. For example coremltools-4.0b2-cp27-none-macosx_10_13_intel.whl does not work. I get the following error when trying to load the CoreML framework:

/venv/lib/python2.7/site-packages/coremltools/libcoremlpython.so, 2): Symbol not found: _OBJC_CLASS_$_MLModelConfiguration
  Referenced from: /venv/lib/python2.7/site-packages/coremltools/libcoremlpython.so (which was built for Mac OS X 10.16)
  Expected in: /System/Library/Frameworks/CoreML.framework/Versions/A/CoreML

TobyRoseman · 2020-08-21T03:40:37Z

I have not checked all of the wheels for 4.0b2 but I'm seeing the same issue for other combinations for macOS/Python-Version: 10.14/2.7, 10.14/3.5, 10.14/3.6, 10.14/3.7 and 10.14/3.8.

glenn-jocher · 2020-08-23T01:30:35Z

Receive this error with coremltools 4.0b3. and Python 3.8 in MacOS. Downgrading to a Python 3.7 environment solved the problem for me.

GodsonDsilva · 2020-09-04T14:54:00Z

I am facing the same issue with coremltools 4.0b3, even with Python 3.7 ... I am having MacOS 10.14.7.

TobyRoseman · 2020-10-03T00:43:05Z

According to my tests this is now fixed in coremltools 4.0b4.

vade · 2020-12-31T21:50:42Z

This appears to be an issue with latest CoreML Tools with Miniconda / M1 Mac. I am using the following method to install CoreMLtools 4.0 on macOS 11 on an M1 Mac mini:

#1011 (comment)

andrewk1 · 2021-01-04T01:46:32Z

This appears to be an issue with latest CoreML Tools with Miniconda / M1 Mac. I am using the following method to install CoreMLtools 4.0 on macOS 11 on an M1 Mac mini:

#1011 (comment)

I was having the same issue as well, but was able to fix it by compiling and installing coremltools from source (on M1 Macbook Air)

pokidyshev · 2021-05-18T18:38:43Z

LMAO: was googling to find a solution to a similar bug and stumbled upon this thread. 2 years passed since I've opened this issue and the bug is still present 😂

exception loading model proxy: No module named 'coremltools.libcoremlpython'

Traceback (most recent call last):
  File "/Users/sandpiturtle/Developer/tavour/yolov5/detect_coreml.py", line 193, in <module>
    detect(opt=opt)
  File "/Users/sandpiturtle/Developer/tavour/yolov5/detect_coreml.py", line 75, in detect
    pred = mlmodel.predict({'image': img})
  File "/Users/sandpiturtle/opt/miniconda3/envs/yolov5/lib/python3.9/site-packages/coremltools/models/model.py", line 345, in predict
    raise Exception(
Exception: Unable to load CoreML.framework. Cannot make predictions.

TobyRoseman · 2021-05-18T21:10:52Z

@pokidyshev - This issue should be fixed now. It looks like you're using Python 3.9. Coremltools doesn't support Python 3.9 yet.

I think this is an installation issue. I think you must have installed coremltools using an egg rather than a wheel. Building libcoremlpython must have failed during installation. Did you receive an error message during installation?

I suggest just using Python 3.8 for now.

poormag · 2021-09-19T15:14:09Z

coremltools5 beta is ok for python3.9+

TobyRoseman mentioned this issue Jun 21, 2019

Python 3.7 macOS Support apple/turicreate#2079

Merged

Mahanotrahul mentioned this issue Jun 24, 2019

Product of input blob dimensions C,H,W (96,3448,1) must be equal to the parameter 'inputChannels' (96) #389

Closed

Necross added the repro needed label Jul 2, 2019

TobyRoseman removed the repro needed label Jul 3, 2019

TobyRoseman mentioned this issue Jul 16, 2019

Unable to call predict #400

Closed

TobyRoseman closed this as completed Aug 7, 2019

TobyRoseman reopened this Aug 7, 2019

aseemw closed this as completed Sep 18, 2019

TobyRoseman reopened this Aug 19, 2020

TobyRoseman closed this as completed Oct 3, 2020

TobyRoseman mentioned this issue Oct 3, 2020

Use new coremltools beta apple/turicreate#3346

Merged

Unable to load CoreML.framework. Cannot make predictions. #372

Unable to load CoreML.framework. Cannot make predictions. #372

Comments

pokidyshev commented Jun 10, 2019

TobyRoseman commented Jun 10, 2019

pokidyshev commented Jun 11, 2019 • edited

TobyRoseman commented Jun 11, 2019

pokidyshev commented Jun 11, 2019

staubda commented Jun 13, 2019 • edited

Necross commented Jul 2, 2019

TobyRoseman commented Jul 2, 2019

bhushan23 commented Jul 6, 2019 • edited

TobyRoseman commented Jul 8, 2019

TobyRoseman commented Aug 7, 2019

motasay commented Aug 7, 2019 • edited

TobyRoseman commented Aug 7, 2019

josephsieh commented Aug 23, 2019 • edited

Necross commented Aug 23, 2019

josephsieh commented Aug 23, 2019

zhao15 commented Sep 14, 2019

aseemw commented Sep 14, 2019

josephsieh commented Sep 18, 2019

1duo commented Sep 18, 2019

1duo commented Sep 18, 2019

yaysummeriscoming commented Jan 31, 2020

AryanGold commented Mar 16, 2020

wmpauli commented Jul 28, 2020 • edited

Vozf commented Aug 19, 2020

bhushan23 commented Aug 19, 2020

Vozf commented Aug 19, 2020

wmpauli commented Aug 19, 2020

TobyRoseman commented Aug 19, 2020

TobyRoseman commented Aug 21, 2020

TobyRoseman commented Aug 21, 2020

glenn-jocher commented Aug 23, 2020

GodsonDsilva commented Sep 4, 2020

TobyRoseman commented Oct 3, 2020

vade commented Dec 31, 2020

andrewk1 commented Jan 4, 2021 • edited

pokidyshev commented May 18, 2021

TobyRoseman commented May 18, 2021

poormag commented Sep 19, 2021

pokidyshev commented Jun 11, 2019 •

edited

staubda commented Jun 13, 2019 •

edited

bhushan23 commented Jul 6, 2019 •

edited

motasay commented Aug 7, 2019 •

edited

josephsieh commented Aug 23, 2019 •

edited

wmpauli commented Jul 28, 2020 •

edited

andrewk1 commented Jan 4, 2021 •

edited