I have used the already trained caffemodel through coremltools to convert to mlmodel failed!
My conversion code:
import coremltools
# Convert a caffe model to a classifier in Core ML
caffe_model = ('TextBoxes_icdar13.caffemodel', 'deploy.prototxt')
coreml_model = coremltools.converters.caffe.convert(
caffe_model,
image_input_names='data'
)
# Now save the model
coreml_model.save('TextBoxes_icdar13.mlmodel')
The error is as follows:
MAMBAXIE-MC0:TextBoxes mambaxie$ python convert.py
/Users/mambaxie/anaconda2/lib/python2.7/site-packages/coremltools/proto
[libprotobuf ERROR /git/coreml/deps/protobuf/src/google/protobuf/text_format.cc:298] Error parsing text-format caffe.NetParameter: 758:14: Message type "caffe.LayerParameter" has no field named "norm_param".
Traceback (most recent call last):
File "convert.py", line 8, in <module>
image_input_names='data'
File "/Users/mambaxie/anaconda2/lib/python2.7/site-packages/coremltools/converters/caffe/_caffe_converter.py", line 142, in convert
predicted_feature_name)
File "/Users/mambaxie/anaconda2/lib/python2.7/site-packages/coremltools/converters/caffe/_caffe_converter.py", line 187, in _export
predicted_feature_name
RuntimeError: Unable to load caffe network Prototxt file: deploy.prototxt
How can I fix it?
