def caffe_model(caffe_model_file_path, caffe_prototxt_file_path):
# Sometimes, critical information in the Caffe converter is missing from the .caffemodel file.
#This information is present in the deploy.prototxt file.
#You can provide us with both files in the conversion process.
if caffe_model_file_path == True and caffe_prototxt_file_path == True:
#caffe to coreml
caffe_to_coreml = caffe.convert(caffe_input, caffe_prototxt)
caffe_to_coreml = caffe_to_coreml.save('./path/to/save/caffe_to_coreml.mlmodel')
elif caffe_model == True and caffe_prototxt == False:
caffe_to_coreml = caffe.convert(caffe_input)
caffe_to_coreml = caffe_to_coreml.save('./path/to/save/caffe_to_coreml.mlmodel')
return caffe_to_coreml
def conversion_to_mlmodel(net_name, proto_name, layer_type, input_layer):
filename = '{}nets/{}/mlkitmodels/{}.mlmodel'.format(
nets_path, layer_type, net_name)
caffe_model_path = '{}nets/{}/caffemodels/{}.caffemodel'.format(
nets_path, layer_type, net_name),
proto_path = '{}nets/{}/prototxt/{}.prototxt'.format(
nets_path, layer_type, proto_name)
model_path = caffe_model_path[0]
if isinstance(input_layer, str):
input_layer = [input_layer]
try:
model = caffe_converter.convert((model_path, proto_path), )
model.save(filename)
except RuntimeError as e:
print(e)
return False
return True
def _evaluate_and_test_model_meanpreprocessing(self, n):
failed_tests_load = []
failed_tests_conversion = []
failed_tests_evaluation = []
extract_tarfile('{}nets/{}.gz'.format(nets_path, FOLDER_NAME),
'{}nets/'.format(nets_path))
path_prototxt = '{}nets/{}/{}/image{}.prototxt'.format(
nets_path, FOLDER_NAME, str(n), str(n))
path_caffemodel = '{}nets/{}/{}/image{}.caffemodel'.format(
nets_path, FOLDER_NAME, str(n), str(n))
path_mlmodel = '{}nets/{}/{}/image{}.mlmodel'.format(
nets_path, FOLDER_NAME, str(n), str(n))
if n == 1:
path_binaryproto = '{}nets/{}/1/mean_binary_proto1.binaryproto'.format(
nets_path, FOLDER_NAME)
else:
path_binaryproto = dict()
for i in range(n):
path_binaryproto["data{}".format(
str(i + 1)
)] = '{}nets/{}/{}/mean_binary_proto{}.binaryproto'.format(
nets_path, FOLDER_NAME, str(n), str(i + 1))
image_input_names = []
for i in range(n):
image_input_names.append("data{}".format(str(i + 1)))
#convert it
try:
model = caffe_converter.convert(
(path_caffemodel, path_prototxt, path_binaryproto),
image_input_names=image_input_names)
model.save(path_mlmodel)
except RuntimeError as e:
print(e)
failed_tests_conversion.append(
'image mean preprocessing: conversion failure')
#load it (compile it)
load_result = load_mlmodel(path_mlmodel)
if load_result is False:
failed_tests_load.append('image mean preprocessing: load failure')
#load Caffe's input and output
with open('{}nets/{}/{}/input.json'.format(nets_path, FOLDER_NAME,
str(n))) as data_file:
input_data_dict = json.load(data_file)
with open('{}nets/{}/{}/output.json'.format(nets_path, FOLDER_NAME,
str(n))) as data_file:
output_data_dict = json.load(data_file)
output_data = np.array(output_data_dict["output_data"])
coreml_input_dict = dict()
for i in range(n):
input_data = np.array(input_data_dict["input_data{}".format(
str(i + 1))]).astype(np.uint8)
img = PIL.Image.fromarray(
np.transpose(input_data[0, :, :, :], [1, 2, 0]))
coreml_input_dict["data{}".format(str(i + 1))] = img
#load and evaluate mlmodel
mlmodel = coremltools.models.MLModel(path_mlmodel)
coreml_out = mlmodel.predict(coreml_input_dict)['output']
caffe_preds = output_data.flatten()
coreml_preds = coreml_out.flatten()
if len(caffe_preds) != len(coreml_preds):
failed_tests_evaluation.append(
'single image mean preprocessing: evaluation failure')
max_relative_error = compare_models(output_data.flatten(),
coreml_out.flatten())
if max_relative_error > 0.001:
failed_tests_evaluation.append(
'single image mean preprocessing: evaluation failure')
self.assertEqual(failed_tests_conversion, [])
self.assertEqual(failed_tests_load, [])
self.assertEqual(failed_tests_evaluation, [])
shutil.rmtree('{}nets/{}'.format(nets_path, FOLDER_NAME))