def get_shape(inp: dict):
if 'shape' not in inp:
raise ValueError("shape key not found")
shape = inp['shape']
default_shape = inp.get('default_shape')
if not isinstance(shape, list):
raise ValueError("shape should be list, found {}, type {}".format(
shape, type(shape)))
list_items = 0
for s in shape:
if isinstance(s, list):
list_items += 1
is_enum_shapes = list_items == len(shape)
# All or None shapes element shoud be list
# Regular shape [1,20,20,3]
# Enumerated Shapes [[1,20,20,3], [1,40,40,3]]
user_assert(list_items == 0 or is_enum_shapes,
"Can not parse shape {}".format(shape))
if is_enum_shapes:
enum_shapes = [transform_shape(s) for s in shape]
print("enum_shapes:", enum_shapes)
return ct.EnumeratedShapes(shapes=enum_shapes, default=default_shape)
# Replace string elements such as "1..50" with RangeDim(1, 50)
tx_shape = transform_shape(shape)
print("tx_shape:", tx_shape)
return ct.Shape(shape=tx_shape, default=default_shape)
def test_image_input_rangedim(self, convert_to):
example_input = torch.rand(1, 3, 50, 50) * 255
traced_model = torch.jit.trace(TestConvModule().eval(), example_input)
input_shape = ct.Shape(shape=(1, 3, ct.RangeDim(25, 100, default=45),
ct.RangeDim(25, 100, default=45)))
model = ct.convert(traced_model,
inputs=[ct.ImageType(shape=input_shape)],
convert_to=convert_to)
spec = model.get_spec()
assert spec.description.input[0].type.imageType.width == 45
assert spec.description.input[0].type.imageType.height == 45
assert spec.description.input[
0].type.imageType.imageSizeRange.widthRange.lowerBound == 25
assert spec.description.input[
0].type.imageType.imageSizeRange.widthRange.upperBound == 100
_assert_torch_coreml_output_shapes(model,
spec,
traced_model,
example_input,
is_image_input=True)
def test_multiarray_input_rangedim(self, convert_to):
if convert_to == "mlprogram" and ct.utils._macos_version() < (12, 0):
return
example_input = torch.rand(1, 3, 50, 50) * 100
traced_model = torch.jit.trace(TestConvModule().eval(), example_input)
input_shape = ct.Shape(shape=(1, 3, ct.RangeDim(25, 100, default=45),
ct.RangeDim(25, 100, default=45)))
model = ct.convert(traced_model,
inputs=[ct.TensorType(shape=input_shape)],
convert_to=convert_to)
spec = model.get_spec()
assert list(spec.description.input[0].type.multiArrayType.shape) == [
1, 3, 45, 45
]
assert spec.description.input[
0].type.multiArrayType.shapeRange.sizeRanges[2].lowerBound == 25
assert spec.description.input[
0].type.multiArrayType.shapeRange.sizeRanges[2].upperBound == 100
_assert_torch_coreml_output_shapes(model, spec, traced_model,
example_input)
from coremltools.converters.onnx import convert
bfModel = BlazeFace()
bfModel.load_weights("./blazeface.pth")
bfModel.load_anchors("./anchors.npy")
bfs = BlazeFaceScaled(bfModel)
bfs.eval()
traced_model = torch.jit.trace(bfs,
torch.rand(1, 3, 128, 128),
check_trace=True)
# print(traced_model)
mlmodel = ct.convert(traced_model,
inputs=[
ct.ImageType(name="image",
shape=ct.Shape(shape=(
1,
3,
128,
128,
)),
bias=[-1, -1, -1],
scale=1 / 127.5)
])
mlmodel.save('../App/BlazeFace CoreML/BlazeFaceScaled.mlmodel')
print(mlmodel)
# Save converted CoreML model
# result = mlmodel.predict({"betas_pose_trans": x, "v_personal": y}, usesCPUOnly=True)
# Convert to Core ML
model = ct.convert([tf_model], source='tensorflow')
x = np.random.rand(1, 256, 256, 3)
tf_out = model.predict([x])
# convert functions
predict_model = tf.saved_model.load('./models/magenta_colab/predict_incepv3')
transfer_model = tf.saved_model.load('./models/magenta_colab/transfer_incepv3')
concrete_func = predict_model.signatures[
tf.saved_model.DEFAULT_SERVING_SIGNATURE_DEF_KEY]
print(concrete_func.inputs)
concrete_func.inputs[0].set_shape([1, 256, 256, 3])
# Range for the sequence dimension is "arbitary"
input_shape = ct.Shape(shape=(1, ct.RangeDim(), ct.RangeDim(), 3))
model_input = ct.TensorType(shape=input_shape)
# Convert the model
predict_mlmodel = ct.convert(model=[concrete_func],
source='tensorflow',
inputs=[model_input])
predict_model = tf.saved_model.load('./models/magenta_colab/predict_incepv3')
predict_model.summary()
model = ct.convert(predict_model, source='tensorflow')
#
def convert_coreml_model_dynamic(saved_model_path,
# model(data)
# transforms.ToPILImage()(image[0]).show(command='fim')
# to_visualize = ['gray', 'hint', 'hint_ab', 'fake_entr',
# 'real', 'fake_reg', 'real_ab', 'fake_ab_reg', ]
# visuals = util.get_subset_dict(
# model.model.get_current_visuals(), to_visualize)
# for key, value in visuals.items():
# print(key)
# transforms.ToPILImage()(value[0]).show(command='fim')
output = model(img, hint)
output = util.lab2rgb(output, opt=opt)
transforms.ToPILImage()(output[0]).show(command='fim')
traced_model = torch.jit.trace(model, (img, hint), check_trace=False)
mlmodel = ct.convert(
model=traced_model,
inputs=[
ct.TensorType(name="image",
shape=ct.Shape(shape=(1, 3, ct.RangeDim(1, 4096),
ct.RangeDim(1, 4096)))),
ct.TensorType(name="hint",
shape=ct.Shape(shape=(1, 3, ct.RangeDim(1, 4096),
ct.RangeDim(1, 4096)))),
])
mlmodel.save("~/color.mlmodel")
