def convert_flexible_coremodel(model_path, input_name, output_name):
spec = coremltools.utils.load_spec(model_path)
img_size_ranges = flexible_shape_utils.NeuralNetworkImageSizeRange()
img_size_ranges.add_height_range((100, 1920))
img_size_ranges.add_width_range((100, 1920))
flexible_shape_utils.update_image_size_range(spec,
feature_name=input_name,
size_range=img_size_ranges)
flexible_shape_utils.update_image_size_range(spec,
feature_name=output_name,
size_range=img_size_ranges)
coremltools.utils.save_spec(spec, model_path)
model_spec = coremltools.utils.load_spec(model_path)
model_fp16_spec = coremltools.utils.convert_neural_network_spec_weights_to_fp16(
model_spec)
coremltools.utils.save_spec(model_fp16_spec, model_path)
def _set_user_inputs(proto, inputs):
for input_type in inputs:
shape = input_type.shape
if isinstance(shape, EnumeratedShapes):
if isinstance(input_type, ImageType):
default_height, default_width = 0, 0
for inp in proto.description.input:
if inp.name == input_type.name:
default_height = inp.type.imageType.height
default_width = inp.type.imageType.width
break
image_sizes = []
if input_type.channel_first:
for s in shape.shapes:
if s.shape[-2] == default_height and s.shape[
-1] == default_width:
continue
image_sizes.append(
flexible_shape_utils.NeuralNetworkImageSize(
height=s.shape[-2], width=s.shape[-1]))
else:
for s in shape.shapes:
if s.shape[-3] == default_height and s.shape[
-2] == default_width:
continue
image_sizes.append(
flexible_shape_utils.NeuralNetworkImageSize(
height=s.shape[-3], width=s.shape[-2]))
add_enumerated_image_sizes(proto,
input_type.name,
sizes=image_sizes)
else:
add_multiarray_ndshape_enumeration(
proto, input_type.name,
[tuple(s.shape) for s in shape.shapes])
elif isinstance(shape, Shape):
shape = shape.shape # This is shape in Shape
if all([
not isinstance(s, RangeDim) and not is_symbolic(s)
and s > 0 for s in shape
]):
continue
if isinstance(input_type, ImageType):
img_range = flexible_shape_utils.NeuralNetworkImageSizeRange()
if input_type.channel_first:
H = shape[-2]
W = shape[-1]
else:
H = shape[-3]
W = shape[-2]
if isinstance(H, RangeDim):
img_range.add_height_range((H.lower_bound, H.upper_bound))
elif is_symbolic(H):
img_range.add_height_range((1, -1))
else:
img_range.add_height_range((H, H))
if isinstance(W, RangeDim):
img_range.add_width_range((W.lower_bound, W.upper_bound))
elif is_symbolic(W):
img_range.add_width_range((1, -1))
else:
img_range.add_width_range((W, W))
flexible_shape_utils.update_image_size_range(
proto, input_type.name, img_range)
else:
lb = []
ub = []
for s in shape:
if isinstance(s, RangeDim):
lb.append(s.lower_bound)
ub.append(s.upper_bound)
elif is_symbolic(s):
lb.append(1)
ub.append(-1)
else:
lb.append(s)
ub.append(s)
set_multiarray_ndshape_range(proto,
input_type.name,
lower_bounds=lb,
upper_bounds=ub)
model_file = open(model_in, 'rb')
model_proto = onnx_pb.ModelProto()
model_proto.ParseFromString(model_file.read())
print("prepare to convert...")
coreml_model = convert(model_proto,
preprocessing_args={
'image_scale': (1.0 / 255.0 / 58.50182),
'blue_bias': (-109.496254 / 255.0 / 58.50182),
'green_bias': (-118.698456 / 255.0 / 58.50182),
'red_bias': (-124.68751 / 255.0 / 58.50182),
'is_bgr': True
},
image_input_names=['gemfield'
]) #, image_output_names=['745'])
#coreml_model = convert(model_proto, preprocessing_args= {'image_scale' : (1.0/255), 'is_bgr':True}, image_input_names=['gemfield'],image_output_names=['745'])
coreml_model.save(model_out)
####
import coremltools
from coremltools.models.neural_network import flexible_shape_utils
spec = coremltools.utils.load_spec(model_out)
img_size_ranges = flexible_shape_utils.NeuralNetworkImageSizeRange()
img_size_ranges.add_height_range((384, 640))
img_size_ranges.add_width_range((384, 640))
flexible_shape_utils.update_image_size_range(spec,
feature_name='gemfield',
size_range=img_size_ranges)
#flexible_shape_utils.update_image_size_range(spec, feature_name='745', size_range=img_size_ranges)
coremltools.utils.save_spec(spec, 'flex_{}'.format(model_out))
######
