python - Error using CoreML model to classify an image -


i'm trying use coreml tools convert keras model coreml , i'm having error in prediction. first converted model:

coreml_model = coremltools.converters.keras.convert(       model,       input_names='stampimage',    # inform coreml input name       image_input_names = 'stampimage', # inform coreml input images       output_names='prediction',       class_labels = class_labels, # labels_dict       predicted_feature_name='predicted_feature_name',       is_bgr=true)  coreml_model.save('./trained_models_data/stamps' + version + '.mlmodel')  

the conversion runs fine. loaded model:

model =  coremltools.models.mlmodel('./trained_models_data/stamps' + version + '.mlmodel')   

and image:

from pil import image   image = image.open('c1243_lnd_899fa3f6-b703-4724-9701-f11dad7cedfe.jpg')  

but when tried predict:

model.predict({'stampimage': image})   

i received error:

error: value type not convertible:   <pil.jpegimageplugin.jpegimagefile image mode=rgb size=714x714 @ 0x1127425a8>   ---------------------------------------------------------------------------   runtimeerror                              traceback (most recent call last)   <ipython-input-21-82fd85392a7f> in <module>()   ----> 1 model.predict({'stampimage': image})     /anaconda/envs/coremltools_py2/lib/python2.7/site-packages/coremltools/models/model.pyc in predict(self, data, **kwargs)       236         """       237         if self.__proxy__:   --> 238             return self.__proxy__.predict(data)       239         else:       240             if _sys.platform != 'darwin' or float('.'.join(_platform.mac_ver()[0].split('.')[:2])) < 10.13:     runtimeerror: value type not convertible   

i tried follow steps "core ml in depth" session in wwdc... know wrong?

you should load converted model coreml on ios side. python use model before conversion.


Comments

Popular posts from this blog

php - Vagrant up error - Uncaught Reflection Exception: Class DOMDocument does not exist -

vue.js - Create hooks for automated testing -

Add new key value to json node in java -