def _create_output_metadata(self):
"""Creates the output metadata for a Bert QA model."""
# Creates outputs info.
end_meta = _metadata_fb.TensorMetadataT()
end_meta.name = "end_logits"
end_meta.description = (
"logits over the sequence which indicates the"
" end position of the answer span with closed interval.")
end_meta.content = _metadata_fb.ContentT()
end_meta.content.contentPropertiesType = (
_metadata_fb.ContentProperties.FeatureProperties)
end_meta.content.contentProperties = _metadata_fb.FeaturePropertiesT()
start_meta = _metadata_fb.TensorMetadataT()
start_meta.name = "start_logits"
start_meta.description = (
"logits over the sequence which indicates "
"the start position of the answer span with closed interval.")
start_meta.content = _metadata_fb.ContentT()
start_meta.content.contentPropertiesType = (
_metadata_fb.ContentProperties.FeatureProperties)
start_meta.content.contentProperties = _metadata_fb.FeaturePropertiesT()
# The order of output_metadata should match the order of tensor names in
# OutputTensorNames.
output_metadata = [start_meta, end_meta]
# Order the tensor metadata according to the output tensor order.
ordered_output_names = self._get_output_tensor_names()
return self._order_tensor_metadata_with_names(output_metadata,
self.model_info.output_names,
ordered_output_names)
def convert():
saved_model_path = 'gaze_prediction_model.h5'
gaze_pred_model = tf.keras.models.load_model(saved_model_path)
# some layer names have been renamed to:
"""
Left Eye: placeholder
Right Eye: placeholder_1
Face: face
Face Mask: placeholder_2
"""
# Creates model info.
model_meta = _metadata_fb.ModelMetadataT()
model_meta.name = "EyeTracker Gaze Prediction Model"
model_meta.description = "Predicts the coordinates relative to the camera position of the phone camera"
model_meta.version = "v1"
model_meta.author = "EyeCon"
# Create Input Info.
input_left_eye_meta = _metadata_fb.TensorMetadataT()
input_right_eye_meta = _metadata_fb.TensorMetadataT()
input_face = _metadata_fb.TensorMetadataT()
input_face_mask = _metadata_fb.TensorMetadataT()
converter = tf.lite.TFLiteConverter.from_keras_model(gaze_pred_model)
tflite_model = converter.convert()
# save the model
with open('gaze_predictor_model.tflite', 'wb') as f:
f.write(tflite_model)
def _write_metadata(model_path: str, label_map_path: str, mean: List[float],
std: List[float]):
"""Add normalization option and label map TFLite metadata to the model.
Args:
model_path: The path of the TFLite model
label_map_path: The path of the label map file
mean: The mean value used to normalize input image tensor
std: The standard deviation used to normalize input image tensor
"""
# Creates flatbuffer for model information.
model_meta = _metadata_fb.ModelMetadataT()
# Creates flatbuffer for model input metadata.
# Here we add the input normalization info to input metadata.
input_meta = _metadata_fb.TensorMetadataT()
input_normalization = _metadata_fb.ProcessUnitT()
input_normalization.optionsType = (
_metadata_fb.ProcessUnitOptions.NormalizationOptions)
input_normalization.options = _metadata_fb.NormalizationOptionsT()
input_normalization.options.mean = mean
input_normalization.options.std = std
input_meta.processUnits = [input_normalization]
# Creates flatbuffer for model output metadata.
# Here we add label file to output metadata.
output_meta = _metadata_fb.TensorMetadataT()
label_file = _metadata_fb.AssociatedFileT()
label_file.name = os.path.basename(label_map_path)
label_file.type = _metadata_fb.AssociatedFileType.TENSOR_AXIS_LABELS
output_meta.associatedFiles = [label_file]
# Creates subgraph to contain input and output information,
# and add subgraph to the model information.
subgraph = _metadata_fb.SubGraphMetadataT()
subgraph.inputTensorMetadata = [input_meta]
subgraph.outputTensorMetadata = [output_meta]
model_meta.subgraphMetadata = [subgraph]
# Serialize the model metadata buffer we created above using flatbuffer
# builder.
b = flatbuffers.Builder(0)
b.Finish(model_meta.Pack(b),
_metadata.MetadataPopulator.METADATA_FILE_IDENTIFIER)
metadata_buf = b.Output()
# Populates metadata and label file to the model file.
populator = _metadata.MetadataPopulator.with_model_file(model_path)
populator.load_metadata_buffer(metadata_buf)
populator.load_associated_files([label_map_path])
populator.populate()
def _create_input_metadata(self):
"""Creates the input metadata for a Bert model.
Returns:
A list of the three input tensor metadata in flatbuffer objects.
"""
# Creates inputs info.
ids_meta = _metadata_fb.TensorMetadataT()
ids_meta.name = "ids"
ids_meta.description = ("Tokenized ids of input text.")
ids_meta.content = _metadata_fb.ContentT()
ids_meta.content.contentPropertiesType = (
_metadata_fb.ContentProperties.FeatureProperties)
ids_meta.content.contentProperties = _metadata_fb.FeaturePropertiesT()
mask_meta = _metadata_fb.TensorMetadataT()
mask_meta.name = "mask"
mask_meta.description = (
"Mask with 1 for real tokens and 0 for padding "
"tokens.")
mask_meta.content = _metadata_fb.ContentT()
mask_meta.content.contentPropertiesType = (
_metadata_fb.ContentProperties.FeatureProperties)
mask_meta.content.contentProperties = _metadata_fb.FeaturePropertiesT()
segment_meta = _metadata_fb.TensorMetadataT()
segment_meta.name = "segment_ids"
segment_meta.description = (
"0 for the first sequence, 1 for the second sequence if exists.")
segment_meta.content = _metadata_fb.ContentT()
segment_meta.content.contentPropertiesType = (
_metadata_fb.ContentProperties.FeatureProperties)
segment_meta.content.contentProperties = _metadata_fb.FeaturePropertiesT(
)
# The order of input_metadata should match the order of tensor names in
# InputTensorNames.
input_metadata = [ids_meta, mask_meta, segment_meta]
# Order the tensor metadata according to the input tensor order.
ordered_input_names = self._get_input_tensor_names()
return self._order_tensor_metadata_with_names(
input_metadata, self.model_info.input_names, ordered_input_names)
def create_preprocessor_output_metadata():
output_meta = _metadata_fb.TensorMetadataT()
output_meta.name = "Preprocessed image"
image_size = 224
output_meta.description = f"Preprocessed image, shaped 3 x {image_size} x {image_size}"
output_meta.content = _metadata_fb.ContentT()
output_meta.content.content_properties = _metadata_fb.FeaturePropertiesT()
output_meta.content.contentPropertiesType = (
_metadata_fb.ContentProperties.FeatureProperties)
return output_meta
def create_output_metadata():
output_metadata = _metadata_fb.TensorMetadataT()
output_metadata.name = "face_embeddings"
output_metadata.description = "Embedding vector with 2048 values per face."
output_metadata.content = _metadata_fb.ContentT()
output_metadata.content.content_properties = _metadata_fb.FeaturePropertiesT(
)
output_metadata.content.contentPropertiesType = (
_metadata_fb.ContentProperties.FeatureProperties)
output_stats = _metadata_fb.StatsT()
# output_stats.max = [1.0]
# output_stats.min = [0.0]
output_metadata.stats = output_stats
return output_metadata
def create_preprocessor_input_metadata():
input_meta = _metadata_fb.TensorMetadataT()
input_meta.name = "image preprocessing"
input_meta.description = (
"Input image to be preprocessed. The input image can be of any size.")
input_meta.content = _metadata_fb.ContentT()
input_meta.content.contentProperties = _metadata_fb.ImagePropertiesT()
input_meta.content.contentProperties.colorSpace = _metadata_fb.ColorSpaceType.RGB
input_meta.content.contentPropertiesType = _metadata_fb.ContentProperties.ImageProperties
input_meta.processUnits = []
input_stats = _metadata_fb.StatsT()
input_stats.max = [255]
input_stats.min = [0]
input_meta.stats = input_stats
return input_meta
def _create_output_metadata(self):
"""Creates the output metadata for a Bert text classifier model."""
# Create output info.
output_meta = _metadata_fb.TensorMetadataT()
output_meta.name = "probability"
output_meta.description = "Probabilities of labels respectively."
output_meta.content = _metadata_fb.ContentT()
output_meta.content.contentProperties = _metadata_fb.FeaturePropertiesT(
)
output_meta.content.contentPropertiesType = (
_metadata_fb.ContentProperties.FeatureProperties)
label_file = _metadata_fb.AssociatedFileT()
label_file.name = os.path.basename(self.model_info.label_file)
label_file.description = ("Labels for classification categories.")
label_file.type = _metadata_fb.AssociatedFileType.TENSOR_AXIS_LABELS
output_meta.associatedFiles = [label_file]
return [output_meta]
def create_input_metadata():
input_metadata = _metadata_fb.TensorMetadataT()
input_metadata.name = "image"
input_metadata.description = VggFaceMetadata.Layers.ANDROID_INPUT
input_metadata.content = _metadata_fb.ContentT()
input_metadata.content.contentProperties = _metadata_fb.ImagePropertiesT()
input_metadata.content.contentProperties.colorSpace = _metadata_fb.ColorSpaceType.RGB
input_metadata.content.contentPropertiesType = _metadata_fb.ContentProperties.ImageProperties
# Normalization
input_normalization = _metadata_fb.ProcessUnitT()
input_normalization.optionsType = _metadata_fb.ProcessUnitOptions.NormalizationOptions
input_normalization.options = _metadata_fb.NormalizationOptionsT()
input_normalization.options.mean = [91.4953, 103.8827, 131.0912]
input_normalization.options.std = [1, 1, 1]
input_metadata.processUnits = [input_normalization]
# Input stats
input_stats = _metadata_fb.StatsT()
input_metadata.stats = input_stats
return input_metadata
from tflite_support import metadata as _metadata
from tflite_support import metadata_schema_py_generated as _metadata_fb
import flatbuffers
import os
model_meta = _metadata_fb.ModelMetadataT()
model_meta.name = "MobilenNetV2 SSD 300x300 Object Detector"
model_meta.description = ("Localize the most prominent object in the"
"image from a set of N categories such as"
"Crosswalk, Green/Red signal, Car")
model_meta.version = 'V1'
model_meta.author = "Phoenix"
model_meta.license = ('Apache License. Version 2.0 '
'http://www.apache.org/licenses/LICENSE-2.0. ')
input_meta = _metadata_fb.TensorMetadataT()
input_meta.name = 'Image'
input_meta.description = (
"Input image to be classified. The expected image is {0} x {1}, with "
"three channels (red, blue, green) per pixel. Each value in the "
"tensor is a single byte between 0 and 255. ".format(640, 640))
input_meta.content = _metadata_fb.ContentT()
input_meta.content.contentProperties = _metadata_fb.ImagePropertiesT()
input_meta.content.contentProperties.colorSpace = _metadata_fb.ColorSpaceType.RGB
input_meta.content.contentPropertiesType = _metadata_fb.ContentProperties.ImageProperties
input_normalization = _metadata_fb.ProcessUnitT()
input_normalization.optionsType = _metadata_fb.ProcessUnitOptions.NormalizationOptions
input_normalization.options = _metadata_fb.NormalizationOptionsT()
input_normalization.options.mean = [127.5]
input_normalization.options.std = [127.5]
from tflite_support import metadata as _metadata
from tflite_support import metadata_schema_py_generated as _metadata_fb
""" ... """
"""Creates the metadata for an image classifier."""
# Creates model info.
model_meta = _metadata_fb.ModelMetadataT()
model_meta.name = "MobileNetV1 PNU building Detection"
model_meta.description = ("Identify which building in PNU")
model_meta.version = "v1"
model_meta.author = "BEOKS"
model_meta.license = ("Apache License. Version 2.0 "
"http://www.apache.org/licenses/LICENSE-2.0.")
# Creates input info.
input_meta = _metadata_fb.TensorMetadataT()
input_meta.name = "image"
input_meta.content = _metadata_fb.ContentT()
input_meta.content.contentProperties = _metadata_fb.ImagePropertiesT()
input_meta.content.contentProperties.colorSpace = (
_metadata_fb.ColorSpaceType.RGB)
input_meta.content.contentPropertiesType = (
_metadata_fb.ContentProperties.ImageProperties)
input_normalization = _metadata_fb.ProcessUnitT()
input_normalization.optionsType = (
_metadata_fb.ProcessUnitOptions.NormalizationOptions)
input_normalization.options = _metadata_fb.NormalizationOptionsT()
input_normalization.options.mean = [127.5]
input_normalization.options.std = [127.5]
input_meta.processUnits = [input_normalization]
input_stats = _metadata_fb.StatsT()
def build_metadata(name: str,
version: str,
labels: List[LabelDescription],
output_types: List[OutputTensorType],
output_interpretation: str = "",
task: Optional[str] = None,
author: str = "",
task_params: str = "") -> bytearray:
"""
Args:
name:
version:
labels:
output_types:
output_interpretation:
task:
author:
task_params:
Returns:
"""
if task is None or task == "":
# Auto infer detection or localization from targets
types = set(output_types)
if types == {
OutputTensorType.BOX_SHAPE,
OutputTensorType.OBJECTNESS,
OutputTensorType.CLASSES,
}:
task = TaskType.OBJECT_DETECTION.value
elif types == {
OutputTensorType.BOX_SHAPE, OutputTensorType.OBJECTNESS
}:
task = TaskType.OBJECT_LOCALIZATION.value
else:
raise ValueError(
f"Cannot infer task_type from output_types: {output_types}")
metadata = ModelMetadata(
name=name,
version=version,
task=task,
output_interpretation=output_interpretation,
labels=labels,
task_params=task_params,
)
model_meta = _metadata_fb.ModelMetadataT()
model_meta.name = name
model_meta.description = json.dumps(metadata.asdict)
model_meta.version = version
model_meta.author = author
input_meta = _metadata_fb.TensorMetadataT()
input_meta.name = "image"
output_metas = []
for t in output_types:
output_meta = _metadata_fb.TensorMetadataT()
output_meta.name = t.value
output_metas.append(output_meta)
subgraph = _metadata_fb.SubGraphMetadataT()
subgraph.inputTensorMetadata = [input_meta]
subgraph.outputTensorMetadata = output_metas
model_meta.subgraphMetadata = [subgraph]
b = flatbuffers.Builder(0)
b.Finish(model_meta.Pack(b),
_metadata.MetadataPopulator.METADATA_FILE_IDENTIFIER)
metadata_buf = b.Output()
return metadata_buf
labelmap_file = args.base + "/" + args.labelmap
export_model_path = args.base + "/" + args.model
# Creates model info.
model_meta = _metadata_fb.ModelMetadataT()
model_meta.name = "MobileNetV2 SSD OID TF1 300x300 Object Detector"
model_meta.description = ("Localize the most prominent object in the "
"image from a set of N categories such as "
"trees, animals, food, vehicles, person etc.")
model_meta.version = "v1"
model_meta.author = "AA"
model_meta.license = ("Apache License. Version 2.0 "
"http://www.apache.org/licenses/LICENSE-2.0.")
# Creates input info.
input_meta = _metadata_fb.TensorMetadataT()
# Creates output info.
output_meta = _metadata_fb.TensorMetadataT()
input_meta.name = "image"
input_meta.description = (
"Input image to be classified. The expected image is {0} x {1}, with "
"three channels (red, blue, and green) per pixel. Each value in the "
"tensor is a single byte between 0 and 255.".format(300, 300))
input_meta.content = _metadata_fb.ContentT()
input_meta.content.contentProperties = _metadata_fb.ImagePropertiesT()
input_meta.content.contentProperties.colorSpace = (
_metadata_fb.ColorSpaceType.RGB)
input_meta.content.contentPropertiesType = (
_metadata_fb.ContentProperties.ImageProperties)
def _create_metadata(self):
"""Creates the metadata for an image classifier."""
# Creates model info.
model_meta = _metadata_fb.ModelMetadataT()
model_meta.name = self.model_info.name
model_meta.description = ("Equipment.")
model_meta.version = self.model_info.version
model_meta.author = "TensorFlow"
model_meta.license = ("Apache License. Version 2.0 "
"http://www.apache.org/licenses/LICENSE-2.0.")
# Creates input info.
input_meta = _metadata_fb.TensorMetadataT()
input_meta.name = "image"
input_meta.description = (
"The expected image is 300 x 300, with three channels "
"(re, blue, and green) per pixel. Each value in the tensor is between"
" 0 and 1.")
input_meta.content = _metadata_fb.ContentT()
input_meta.content.contentProperties = _metadata_fb.ImagePropertiesT()
input_meta.content.contentProperties.colorSpace = (
_metadata_fb.ColorSpaceType.RGB)
input_meta.content.contentPropertiesType = (
_metadata_fb.ContentProperties.ImageProperties)
input_normalization = _metadata_fb.ProcessUnitT()
input_normalization.optionsType = (
_metadata_fb.ProcessUnitOptions.NormalizationOptions)
input_normalization.options = _metadata_fb.NormalizationOptionsT()
input_normalization.options.mean = self.model_info.mean
input_normalization.options.std = self.model_info.std
input_meta.processUnits = [input_normalization]
input_stats = _metadata_fb.StatsT()
input_stats.max = [self.model_info.image_max]
input_stats.min = [self.model_info.image_min]
input_meta.stats = input_stats
# Creates output info.
output_location_meta = _metadata_fb.TensorMetadataT()
output_location_meta.name = "location"
output_location_meta.description = "The locations of the detected boxes."
output_location_meta.content = _metadata_fb.ContentT()
output_location_meta.content.contentPropertiesType = (
_metadata_fb.ContentProperties.BoundingBoxProperties)
output_location_meta.content.contentProperties = (
_metadata_fb.BoundingBoxPropertiesT())
output_location_meta.content.contentProperties.index = [1, 0, 3, 2]
output_location_meta.content.contentProperties.type = (
_metadata_fb.BoundingBoxType.BOUNDARIES)
output_location_meta.content.contentProperties.coordinateType = (
_metadata_fb.CoordinateType.RATIO)
output_location_meta.content.range = _metadata_fb.ValueRangeT()
output_location_meta.content.range.min = 2
output_location_meta.content.range.max = 2
output_class_meta = _metadata_fb.TensorMetadataT()
output_class_meta.name = "category"
output_class_meta.description = "The categories of the detected boxes."
output_class_meta.content = _metadata_fb.ContentT()
output_class_meta.content.contentPropertiesType = (
_metadata_fb.ContentProperties.FeatureProperties)
output_class_meta.content.contentProperties = (
_metadata_fb.FeaturePropertiesT())
output_class_meta.content.range = _metadata_fb.ValueRangeT()
output_class_meta.content.range.min = 2
output_class_meta.content.range.max = 2
label_file = _metadata_fb.AssociatedFileT()
label_file.name = os.path.basename(self.label_file_path)
label_file.description = "Label of objects that this model can recognize."
label_file.type = _metadata_fb.AssociatedFileType.TENSOR_VALUE_LABELS
output_class_meta.associatedFiles = [label_file]
output_score_meta = _metadata_fb.TensorMetadataT()
output_score_meta.name = "score"
output_score_meta.description = "The scores of the detected boxes."
output_score_meta.content = _metadata_fb.ContentT()
output_score_meta.content.contentPropertiesType = (
_metadata_fb.ContentProperties.FeatureProperties)
output_score_meta.content.contentProperties = (
_metadata_fb.FeaturePropertiesT())
output_score_meta.content.range = _metadata_fb.ValueRangeT()
output_score_meta.content.range.min = 2
output_score_meta.content.range.max = 2
output_number_meta = _metadata_fb.TensorMetadataT()
output_number_meta.name = "number of detections"
output_number_meta.description = "The number of the detected boxes."
output_number_meta.content = _metadata_fb.ContentT()
output_number_meta.content.contentPropertiesType = (
_metadata_fb.ContentProperties.FeatureProperties)
output_number_meta.content.contentProperties = (
_metadata_fb.FeaturePropertiesT())
# Creates subgraph info.
group = _metadata_fb.TensorGroupT()
group.name = "detection result"
group.tensorNames = [
output_location_meta.name, output_class_meta.name,
output_score_meta.name
]
subgraph = _metadata_fb.SubGraphMetadataT()
subgraph.inputTensorMetadata = [input_meta]
subgraph.outputTensorMetadata = [
output_location_meta, output_class_meta, output_score_meta,
output_number_meta
]
subgraph.outputTensorGroups = [group]
model_meta.subgraphMetadata = [subgraph]
b = flatbuffers.Builder(0)
b.Finish(model_meta.Pack(b),
_metadata.MetadataPopulator.METADATA_FILE_IDENTIFIER)
self.metadata_buf = b.Output()
def _create_metadata(self):
"""Creates the metadata for the selfie2anime model."""
# Creates model info.
model_meta = _metadata_fb.ModelMetadataT()
model_meta.name = "Selfie2Anime"
model_meta.description = ("Convert selfie to anime.")
model_meta.version = "v1"
model_meta.author = "TensorFlow"
model_meta.license = ("Apache License. Version 2.0 "
"http://www.apache.org/licenses/LICENSE-2.0.")
# Creates info for the input, selfie image.
input_image_meta = _metadata_fb.TensorMetadataT()
input_image_meta.name = "selfie_image"
input_image_meta.description = (
"The expected image is 256 x 256, with three channels "
"(red, blue, and green) per pixel. Each value in the tensor is between"
" 0 and 1.")
input_image_meta.content = _metadata_fb.ContentT()
input_image_meta.content.contentProperties = (
_metadata_fb.ImagePropertiesT())
input_image_meta.content.contentProperties.colorSpace = (
_metadata_fb.ColorSpaceType.RGB)
input_image_meta.content.contentPropertiesType = (
_metadata_fb.ContentProperties.ImageProperties)
input_image_normalization = _metadata_fb.ProcessUnitT()
input_image_normalization.optionsType = (
_metadata_fb.ProcessUnitOptions.NormalizationOptions)
input_image_normalization.options = _metadata_fb.NormalizationOptionsT(
)
input_image_normalization.options.mean = [0.0]
input_image_normalization.options.std = [255]
input_image_meta.processUnits = [input_image_normalization]
input_image_stats = _metadata_fb.StatsT()
input_image_stats.max = [1.0]
input_image_stats.min = [0.0]
input_image_meta.stats = input_image_stats
# Creates output info, anime image
output_image_meta = _metadata_fb.TensorMetadataT()
output_image_meta.name = "anime_image"
output_image_meta.description = "Image styled."
output_image_meta.content = _metadata_fb.ContentT()
output_image_meta.content.contentProperties = _metadata_fb.ImagePropertiesT(
)
output_image_meta.content.contentProperties.colorSpace = (
_metadata_fb.ColorSpaceType.RGB)
output_image_meta.content.contentPropertiesType = (
_metadata_fb.ContentProperties.ImageProperties)
output_image_normalization = _metadata_fb.ProcessUnitT()
output_image_normalization.optionsType = (
_metadata_fb.ProcessUnitOptions.NormalizationOptions)
output_image_normalization.options = _metadata_fb.NormalizationOptionsT(
)
output_image_normalization.options.mean = [0.0]
output_image_normalization.options.std = [0.003921568627] # 1/255
output_image_meta.processUnits = [output_image_normalization]
output_image_stats = _metadata_fb.StatsT()
output_image_stats.max = [1.0]
output_image_stats.min = [0.0]
output_image_meta.stats = output_image_stats
# Creates subgraph info.
subgraph = _metadata_fb.SubGraphMetadataT()
subgraph.inputTensorMetadata = [input_image_meta
] # Updated by Margaret
subgraph.outputTensorMetadata = [output_image_meta
] # Updated by Margaret
model_meta.subgraphMetadata = [subgraph]
b = flatbuffers.Builder(0)
b.Finish(model_meta.Pack(b),
_metadata.MetadataPopulator.METADATA_FILE_IDENTIFIER)
self.metadata_buf = b.Output()
def _create_metadata(self):
"""Creates the metadata for a text classifier."""
# Creates model info.
model_meta = _metadata_fb.ModelMetadataT()
model_meta.name = self.model_info.name
model_meta.description = self.model_info.description
model_meta.version = self.model_info.version
model_meta.author = "TensorFlow"
model_meta.license = ("Apache License. Version 2.0 "
"http://www.apache.org/licenses/LICENSE-2.0.")
# Creates input info.
input_meta = _metadata_fb.TensorMetadataT()
input_meta.name = "input_text"
input_meta.description = (
"Embedding vectors representing the input text to be classified. The "
"input need to be converted from raw text to embedding vectors using "
"the attached dictionary file.")
# Create the vocab file.
vocab_file = _metadata_fb.AssociatedFileT()
vocab_file.name = os.path.basename(self.associated_files[1])
vocab_file.description = ("Vocabulary file to convert natural language "
"words to embedding vectors.")
vocab_file.type = _metadata_fb.AssociatedFileType.VOCABULARY
# Create the RegexTokenizer.
tokenizer = _metadata_fb.ProcessUnitT()
tokenizer.optionsType = (
_metadata_fb.ProcessUnitOptions.RegexTokenizerOptions)
tokenizer.options = _metadata_fb.RegexTokenizerOptionsT()
tokenizer.options.delimRegexPattern = self.model_info.delim_regex_pattern
tokenizer.options.vocabFile = [vocab_file]
input_meta.content = _metadata_fb.ContentT()
input_meta.content.contentPropertiesType = (
_metadata_fb.ContentProperties.FeatureProperties)
input_meta.content.contentProperties = _metadata_fb.FeaturePropertiesT()
input_meta.processUnits = [tokenizer]
# Creates output info.
output_meta = _metadata_fb.TensorMetadataT()
output_meta.name = "probability"
output_meta.description = "Probabilities of the labels respectively."
output_meta.content = _metadata_fb.ContentT()
output_meta.content.contentProperties = _metadata_fb.FeaturePropertiesT()
output_meta.content.contentPropertiesType = (
_metadata_fb.ContentProperties.FeatureProperties)
output_stats = _metadata_fb.StatsT()
output_stats.max = [1.0]
output_stats.min = [0.0]
output_meta.stats = output_stats
label_file = _metadata_fb.AssociatedFileT()
label_file.name = os.path.basename(self.associated_files[0])
label_file.description = ("Labels for the categories that the model can "
"classify.")
label_file.type = _metadata_fb.AssociatedFileType.TENSOR_AXIS_LABELS
output_meta.associatedFiles = [label_file]
# Creates subgraph info.
subgraph = _metadata_fb.SubGraphMetadataT()
subgraph.inputTensorMetadata = [input_meta]
subgraph.outputTensorMetadata = [output_meta]
model_meta.subgraphMetadata = [subgraph]
b = flatbuffers.Builder(0)
b.Finish(
model_meta.Pack(b),
_metadata.MetadataPopulator.METADATA_FILE_IDENTIFIER)
self.metadata_buf = b.Output()
def _create_metadata(self):
"""Creates the metadata for an object detector."""
model_meta = _metadata_fb.ModelMetadataT()
model_meta.name = self.model_info.name
model_meta.description = (
"Identify which of a known set of objects might be present and provide "
"information about their positions within the given image or a video "
"stream.")
model_meta.version = self.model_info.version
model_meta.author = "TensorFlow Lite Model Maker"
model_meta.license = ("Apache License. Version 2.0 "
"http://www.apache.org/licenses/LICENSE-2.0.")
# Creates input info.
input_meta = _metadata_fb.TensorMetadataT()
input_meta.name = "image"
input_meta.description = (
"Input image to be detected. The expected image is {0} x {1}, with "
"three channels (red, blue, and green) per pixel. Each value in the "
"tensor is a single byte between 0 and 255.".format(
self.model_info.image_width, self.model_info.image_height))
input_meta.content = _metadata_fb.ContentT()
input_meta.content.contentProperties = _metadata_fb.ImagePropertiesT()
input_meta.content.contentProperties.colorSpace = (
_metadata_fb.ColorSpaceType.RGB)
input_meta.content.contentPropertiesType = (
_metadata_fb.ContentProperties.ImageProperties)
input_normalization = _metadata_fb.ProcessUnitT()
input_normalization.optionsType = (
_metadata_fb.ProcessUnitOptions.NormalizationOptions)
input_normalization.options = _metadata_fb.NormalizationOptionsT()
input_normalization.options.mean = self.model_info.mean
input_normalization.options.std = self.model_info.std
input_meta.processUnits = [input_normalization]
input_stats = _metadata_fb.StatsT()
input_stats.max = [self.model_info.image_max]
input_stats.min = [self.model_info.image_min]
input_meta.stats = input_stats
# Creates outputs info.
output_location_meta = _metadata_fb.TensorMetadataT()
output_location_meta.name = "location"
output_location_meta.description = "The locations of the detected boxes."
output_location_meta.content = _metadata_fb.ContentT()
output_location_meta.content.contentPropertiesType = (
_metadata_fb.ContentProperties.BoundingBoxProperties)
output_location_meta.content.contentProperties = (
_metadata_fb.BoundingBoxPropertiesT())
output_location_meta.content.contentProperties.index = [1, 0, 3, 2]
output_location_meta.content.contentProperties.type = (
_metadata_fb.BoundingBoxType.BOUNDARIES)
output_location_meta.content.contentProperties.coordinateType = (
_metadata_fb.CoordinateType.RATIO)
output_location_meta.content.range = _metadata_fb.ValueRangeT()
output_location_meta.content.range.min = 2
output_location_meta.content.range.max = 2
output_class_meta = _metadata_fb.TensorMetadataT()
output_class_meta.name = "category"
output_class_meta.description = "The categories of the detected boxes."
output_class_meta.content = _metadata_fb.ContentT()
output_class_meta.content.contentPropertiesType = (
_metadata_fb.ContentProperties.FeatureProperties)
output_class_meta.content.contentProperties = (
_metadata_fb.FeaturePropertiesT())
output_class_meta.content.range = _metadata_fb.ValueRangeT()
output_class_meta.content.range.min = 2
output_class_meta.content.range.max = 2
label_file = _metadata_fb.AssociatedFileT()
label_file.name = os.path.basename(self.associated_files[0])
label_file.description = "Label of objects that this model can recognize."
label_file.type = _metadata_fb.AssociatedFileType.TENSOR_VALUE_LABELS
output_class_meta.associatedFiles = [label_file]
output_score_meta = _metadata_fb.TensorMetadataT()
output_score_meta.name = "score"
output_score_meta.description = "The scores of the detected boxes."
output_score_meta.content = _metadata_fb.ContentT()
output_score_meta.content.contentPropertiesType = (
_metadata_fb.ContentProperties.FeatureProperties)
output_score_meta.content.contentProperties = (
_metadata_fb.FeaturePropertiesT())
output_score_meta.content.range = _metadata_fb.ValueRangeT()
output_score_meta.content.range.min = 2
output_score_meta.content.range.max = 2
output_number_meta = _metadata_fb.TensorMetadataT()
output_number_meta.name = "number of detections"
output_number_meta.description = "The number of the detected boxes."
output_number_meta.content = _metadata_fb.ContentT()
output_number_meta.content.contentPropertiesType = (
_metadata_fb.ContentProperties.FeatureProperties)
output_number_meta.content.contentProperties = (
_metadata_fb.FeaturePropertiesT())
# Creates subgraph info.
group = _metadata_fb.TensorGroupT()
group.name = "detection result"
group.tensorNames = [
output_location_meta.name, output_class_meta.name,
output_score_meta.name
]
subgraph = _metadata_fb.SubGraphMetadataT()
subgraph.inputTensorMetadata = [input_meta]
subgraph.outputTensorMetadata = [
output_location_meta, output_class_meta, output_score_meta,
output_number_meta
]
subgraph.outputTensorGroups = [group]
model_meta.subgraphMetadata = [subgraph]
b = flatbuffers.Builder(0)
b.Finish(model_meta.Pack(b),
_metadata.MetadataPopulator.METADATA_FILE_IDENTIFIER)
self.metadata_buf = b.Output()
def create_metadata(model_file_name, label_map_file_name, num_labels):
from tflite_support import flatbuffers
from tflite_support import metadata as _metadata
from tflite_support import metadata_schema_py_generated as _metadata_fb
""" ... """
"""Creates the metadata for an image classifier."""
# Creates model info.
model_meta = _metadata_fb.ModelMetadataT()
model_meta.name = 'MobileNetV1 image classifier'
model_meta.description = ('Identify the most prominent object in the '
'image from a set of 1,001 categories such as '
'trees, animals, food, vehicles, person etc.')
model_meta.version = 'v1'
model_meta.author = 'TensorFlow'
model_meta.license = ('Apache License. Version 2.0 '
'http://www.apache.org/licenses/LICENSE-2.0.')
# Creates input info.
input_meta = _metadata_fb.TensorMetadataT()
input_meta.name = 'image'
input_meta.description = (
'Input image to be classified. The expected image is {0} x {1}, with '
'three channels (red, blue, and green) per pixel. Each value in the '
'tensor is a single byte between 0 and 255.'.format(416, 416))
input_meta.content = _metadata_fb.ContentT()
input_meta.content.contentProperties = _metadata_fb.ImagePropertiesT()
input_meta.content.contentProperties.colorSpace = (
_metadata_fb.ColorSpaceType.RGB)
input_meta.content.contentPropertiesType = (
_metadata_fb.ContentProperties.ImageProperties)
input_normalization = _metadata_fb.ProcessUnitT()
input_normalization.optionsType = (
_metadata_fb.ProcessUnitOptions.NormalizationOptions)
input_normalization.options = _metadata_fb.NormalizationOptionsT()
input_normalization.options.mean = [127.5]
input_normalization.options.std = [127.5]
input_meta.processUnits = [input_normalization]
input_stats = _metadata_fb.StatsT()
input_stats.max = [255]
input_stats.min = [0]
input_meta.stats = input_stats
# Creates output info.
bbox_meta = _metadata_fb.TensorMetadataT()
bbox_meta.name = 'bbox'
bbox_meta.description = '.'
bbox_meta.content = _metadata_fb.ContentT()
bbox_meta.content.content_properties = _metadata_fb.FeaturePropertiesT()
bbox_meta.content.contentPropertiesType = (
_metadata_fb.ContentProperties.FeatureProperties)
bbox_stats = _metadata_fb.StatsT()
bbox_stats.max = [416.0]
bbox_stats.min = [0.0]
bbox_meta.stats = bbox_stats
classes_meta = _metadata_fb.TensorMetadataT()
classes_meta.name = 'classes'
classes_meta.description = '.'
classes_meta.content = _metadata_fb.ContentT()
classes_meta.content.content_properties = _metadata_fb.FeaturePropertiesT()
classes_meta.content.contentPropertiesType = (
_metadata_fb.ContentProperties.FeatureProperties)
classes_stats = _metadata_fb.StatsT()
classes_stats.max = [num_labels]
classes_stats.min = [0]
classes_meta.stats = classes_stats
label_file = _metadata_fb.AssociatedFileT()
label_file.name = os.path.basename(label_map_file_name)
label_file.description = 'Labels for objects that the model can recognize.'
label_file.type = _metadata_fb.AssociatedFileType.TENSOR_AXIS_LABELS
classes_meta.associatedFiles = [label_file]
confidence_meta = _metadata_fb.TensorMetadataT()
confidence_meta.name = 'confidence'
confidence_meta.description = '.'
confidence_meta.content = _metadata_fb.ContentT()
confidence_meta.content.content_properties = _metadata_fb.FeaturePropertiesT(
)
confidence_meta.content.contentPropertiesType = (
_metadata_fb.ContentProperties.FeatureProperties)
confidence_stats = _metadata_fb.StatsT()
confidence_stats.max = [1.0]
confidence_stats.min = [0.0]
confidence_meta.stats = confidence_stats
num_dets_meta = _metadata_fb.TensorMetadataT()
num_dets_meta.name = 'num_dets'
num_dets_meta.description = '.'
num_dets_meta.content = _metadata_fb.ContentT()
num_dets_meta.content.content_properties = _metadata_fb.FeaturePropertiesT(
)
num_dets_meta.content.contentPropertiesType = (
_metadata_fb.ContentProperties.FeatureProperties)
num_dets_stats = _metadata_fb.StatsT()
num_dets_stats.max = [200]
num_dets_stats.min = [0]
num_dets_meta.stats = num_dets_stats
raw_output_meta = _metadata_fb.TensorMetadataT()
raw_output_meta.name = 'raw_output'
raw_output_meta.description = '.'
raw_output_meta.content = _metadata_fb.ContentT()
raw_output_meta.content.content_properties = _metadata_fb.FeaturePropertiesT(
)
raw_output_meta.content.contentPropertiesType = (
_metadata_fb.ContentProperties.FeatureProperties)
subgraph = _metadata_fb.SubGraphMetadataT()
subgraph.inputTensorMetadata = [input_meta]
subgraph.outputTensorMetadata = [
bbox_meta, classes_meta, confidence_meta, num_dets_stats
] # raw_output_meta
model_meta.subgraphMetadata = [subgraph]
b = flatbuffers.Builder(0)
b.Finish(model_meta.Pack(b),
_metadata.MetadataPopulator.METADATA_FILE_IDENTIFIER)
metadata_buf = b.Output()
populator = _metadata.MetadataPopulator.with_model_file(model_file_name)
populator.load_metadata_buffer(metadata_buf)
populator.load_associated_files([label_map_file_name])
populator.populate()
def _create_metadata(self):
"""Creates the metadata for an image classifier."""
# Creates model info.
model_meta = _metadata_fb.ModelMetadataT()
model_meta.name = self.model_info.name
model_meta.description = ("Identify the most prominent object in the "
"image from a set of %d categories." %
self.model_info.num_classes)
model_meta.version = self.model_info.version
model_meta.author = "TensorFlow"
model_meta.license = ("Apache License. Version 2.0 "
"http://www.apache.org/licenses/LICENSE-2.0.")
# Creates input info.
input_meta = _metadata_fb.TensorMetadataT()
input_meta.name = "image"
input_meta.description = (
"Input image to be classified. The expected image is {0} x {1}, with "
"three channels (red, blue, and green) per pixel. Each value in the "
"tensor is a single byte between {2} and {3}.".format(
self.model_info.image_width, self.model_info.image_height,
self.model_info.image_min, self.model_info.image_max))
input_meta.content = _metadata_fb.ContentT()
input_meta.content.contentProperties = _metadata_fb.ImagePropertiesT()
input_meta.content.contentProperties.colorSpace = (
_metadata_fb.ColorSpaceType.RGB)
input_meta.content.contentPropertiesType = (
_metadata_fb.ContentProperties.ImageProperties)
input_normalization = _metadata_fb.ProcessUnitT()
input_normalization.optionsType = (
_metadata_fb.ProcessUnitOptions.NormalizationOptions)
input_normalization.options = _metadata_fb.NormalizationOptionsT()
input_normalization.options.mean = self.model_info.mean
input_normalization.options.std = self.model_info.std
input_meta.processUnits = [input_normalization]
input_stats = _metadata_fb.StatsT()
input_stats.max = [self.model_info.image_max]
input_stats.min = [self.model_info.image_min]
input_meta.stats = input_stats
# Creates output info.
output_location_meta = _metadata_fb.TensorMetadataT()
output_location_meta.name = "location"
output_location_meta.description = "The locations of the detected boxes."
output_location_meta.content = _metadata_fb.ContentT()
output_location_meta.content.contentPropertiesType = (
_metadata_fb.ContentProperties.BoundingBoxProperties)
output_location_meta.content.contentProperties = (
_metadata_fb.BoundingBoxPropertiesT())
output_location_meta.content.contentProperties.index = [1, 0, 3, 2]
output_location_meta.content.contentProperties.type = (
_metadata_fb.BoundingBoxType.BOUNDARIES)
output_location_meta.content.contentProperties.coordinateType = (
_metadata_fb.CoordinateType.RATIO)
output_location_meta.content.range = _metadata_fb.ValueRangeT()
output_location_meta.content.range.min = 0
output_location_meta.content.range.max = 255
output_confidence_meta = _metadata_fb.TensorMetadataT()
output_confidence_meta.name = "confidence"
output_confidence_meta.description = "The confidences of the detected boxes."
output_confidence_meta.content = _metadata_fb.ContentT()
output_confidence_meta.content.contentPropertiesType = (
_metadata_fb.ContentProperties.FeatureProperties)
output_confidence_meta.content.contentProperties = (
_metadata_fb.FeaturePropertiesT())
output_confidence_meta.content.range = _metadata_fb.ValueRangeT()
output_confidence_meta.content.range.min = 0
output_confidence_meta.content.range.max = 255
# label_file = _metadata_fb.AssociatedFileT()
# label_file.name = os.path.basename("labelmap.txt")
# label_file.description = "Label of objects that this model can recognize."
# label_file.type = _metadata_fb.AssociatedFileType.TENSOR_VALUE_LABELS
# output_confidence_meta.associatedFiles = [label_file]
output_landmark_meta = _metadata_fb.TensorMetadataT()
output_landmark_meta.name = "landmark"
output_landmark_meta.description = "The landmark of the detected boxes."
output_landmark_meta.content = _metadata_fb.ContentT()
output_landmark_meta.content.contentPropertiesType = (
_metadata_fb.ContentProperties.FeatureProperties)
output_landmark_meta.content.contentProperties = (
_metadata_fb.FeaturePropertiesT())
output_landmark_meta.content.range = _metadata_fb.ValueRangeT()
output_landmark_meta.content.range.min = 0
output_landmark_meta.content.range.max = 255
# Creates subgraph info.
subgraph = _metadata_fb.SubGraphMetadataT()
subgraph.inputTensorMetadata = [input_meta]
subgraph.outputTensorMetadata = [
output_location_meta, output_confidence_meta, output_landmark_meta
]
model_meta.subgraphMetadata = [subgraph]
b = flatbuffers.Builder(0)
b.Finish(model_meta.Pack(b),
_metadata.MetadataPopulator.METADATA_FILE_IDENTIFIER)
self.metadata_buf = b.Output()
def build_metadata(
model_file_path: str,
#model_name: str,
#model_description: str,
#model_author: str,
#model_license: str,
vocab_file_path: str=None,
sentencepiece_model_path: str=None):
model_meta = _metadata_fb.ModelMetadataT()
model_meta.name = 'distilbert news'
model_meta.description = 'some model description'
model_meta.version = 'v1'
model_meta.author = 'Unknown'
model_meta.license = 'Apache License. Version 2.0'
model_meta.minParserVersion = '1.1.0'
# Creates input info.
ids = _metadata_fb.TensorMetadataT()
segment_ids = _metadata_fb.TensorMetadataT()
mask = _metadata_fb.TensorMetadataT()
ids.name = "ids"
ids.description = "Tokenized ids of input text."
ids.content = _metadata_fb.ContentT()
ids.content.contentProperties = _metadata_fb.FeaturePropertiesT()
ids.content.contentPropertiesType = (
_metadata_fb.ContentProperties.FeatureProperties)
segment_ids.name = "segment_ids"
segment_ids.description = "0 for the first sequence, 1 for the second sequence if exits."
segment_ids.content = _metadata_fb.ContentT()
segment_ids.content.contentProperties = _metadata_fb.FeaturePropertiesT()
segment_ids.content.contentPropertiesType = (
_metadata_fb.ContentProperties.FeatureProperties)
mask.name = "mask"
mask.description = "Mask with 1 for real tokens and 0 for padding tokens."
mask.content = _metadata_fb.ContentT()
mask.content.contentProperties = _metadata_fb.FeaturePropertiesT()
mask.content.contentPropertiesType = (
_metadata_fb.ContentProperties.FeatureProperties)
# Creates output info.
output_meta = _metadata_fb.TensorMetadataT()
output_meta.name = "output"
output_meta.description = "the id of the output class"
output_meta.content = _metadata_fb.ContentT()
output_meta.content.contentProperties = _metadata_fb.FeaturePropertiesT()
output_meta.content.contentPropertiesType = (
_metadata_fb.ContentProperties.FeatureProperties)
"""
label_file = _metadata_fb.AssociatedFileT()
label_file.name = os.path.basename(label_file_path)
label_file.description = "Labels for the categories to be predicted."
label_file.type = _metadata_fb.AssociatedFileType.TENSOR_AXIS_LABELS
output_meta.associatedFiles = [label_file]
"""
input_process_units = []
if sentencepiece_model_path is not None:
#Add sentencepiece specific process unit
sentencepiece_process_unit = _metadata_fb.ProcessUnitT()
sentencepiece_process_unit.optionsType = (
_metadata_fb.ProcessUnitOptions.SentencePieceTokenizerOptions)
sentencepiece_process_unit.options = _metadata_fb.SentencePieceTokenizerOptionsT()
sentencepiece_model = AssociatedFileT()
sentencepiece_model.name="30k-clean-model",
sentencepiece_model.description="The sentence piece model file."
sentencepiece_process_unit.options.sentencePieceModel = [sentencepiece_model]
input_process_units.append(sentencepiece_process_unit)
if vocab_file_path is not None:
model_process_unit = _metadata_fb.ProcessUnitT()
model_process_unit.optionsType = (
_metadata_fb.ProcessUnitOptions.BertTokenizerOptions)
model_process_unit.options = _metadata_fb.BertTokenizerOptionsT()
vocab_file = AssociatedFileT()
vocab_file.name="jp word piece vocab",
vocab_file.description="Japanese Vocabulary file for the BERT tokenizer.",
vocab_file.type=_metadata_fb.AssociatedFileType.VOCABULARY
model_process_unit.options.vocabFile = [vocab_file]
input_process_units.append(model_process_unit)
#Put metadata together
subgraph = _metadata_fb.SubGraphMetadataT()
subgraph.inputTensorMetadata = [ids, mask, segment_ids]
subgraph.outputTensorMetadata = [output_meta]
subgraph.inputProcessUnits = input_process_units
model_meta.subgraphMetadata = [subgraph]
#create flat buffers for metadata
b = flatbuffers.Builder(0)
b.Finish(
model_meta.Pack(b),
_metadata.MetadataPopulator.METADATA_FILE_IDENTIFIER)
metadata_buf = b.Output()
#associate files to metadata
populator = _metadata.MetadataPopulator.with_model_file(model_file_path)
populator.load_metadata_buffer(metadata_buf)
if vocab_file_path is not None:
files = [vocab_file_path]
else:
files = [sentencepiece_model_path]
populator.load_associated_files(files)
populator.populate()
def _create_metadata(self):
"""Creates the metadata for an image classifier."""
# Creates model info.
model_meta = _metadata_fb.ModelMetadataT()
model_meta.name = self.model_info.name
model_meta.description = ("Identify the most prominent breed of a dog in the "
"image from a set of %d breeds." %
self.model_info.num_classes)
model_meta.version = self.model_info.version
model_meta.author = "https://github.com/puntogris/"
model_meta.license = ("Apache License. Version 2.0 "
"http://www.apache.org/licenses/LICENSE-2.0.")
# Creates input info.
input_meta = _metadata_fb.TensorMetadataT()
input_meta.name = "image"
input_meta.description = (
"Input image to be classified. The expected image is {0} x {1}, with "
"three channels (red, blue, and green) per pixel. Each value in the "
"tensor is a single byte between {2} and {3}.".format(
self.model_info.image_width, self.model_info.image_height,
self.model_info.image_min, self.model_info.image_max))
input_meta.content = _metadata_fb.ContentT()
input_meta.content.contentProperties = _metadata_fb.ImagePropertiesT()
input_meta.content.contentProperties.colorSpace = (
_metadata_fb.ColorSpaceType.RGB)
input_meta.content.contentPropertiesType = (
_metadata_fb.ContentProperties.ImageProperties)
input_normalization = _metadata_fb.ProcessUnitT()
input_normalization.optionsType = (
_metadata_fb.ProcessUnitOptions.NormalizationOptions)
input_normalization.options = _metadata_fb.NormalizationOptionsT()
input_normalization.options.mean = self.model_info.mean
input_normalization.options.std = self.model_info.std
input_meta.processUnits = [input_normalization]
input_stats = _metadata_fb.StatsT()
input_stats.max = [self.model_info.image_max]
input_stats.min = [self.model_info.image_min]
input_meta.stats = input_stats
# Creates output info.
output_meta = _metadata_fb.TensorMetadataT()
output_meta.name = "probability"
output_meta.description = "Probabilities of the %d labels respectively." % self.model_info.num_classes
output_meta.content = _metadata_fb.ContentT()
output_meta.content.content_properties = _metadata_fb.FeaturePropertiesT()
output_meta.content.contentPropertiesType = (
_metadata_fb.ContentProperties.FeatureProperties)
output_stats = _metadata_fb.StatsT()
output_stats.max = [1.0]
output_stats.min = [0.0]
output_meta.stats = output_stats
label_file = _metadata_fb.AssociatedFileT()
label_file.name = os.path.basename(self.label_file_path)
label_file.description = "Labels for objects that the model can recognize."
label_file.type = _metadata_fb.AssociatedFileType.TENSOR_AXIS_LABELS
output_meta.associatedFiles = [label_file]
# Creates subgraph info.
subgraph = _metadata_fb.SubGraphMetadataT()
subgraph.inputTensorMetadata = [input_meta]
subgraph.outputTensorMetadata = [output_meta]
model_meta.subgraphMetadata = [subgraph]
b = flatbuffers.Builder(0)
b.Finish(
model_meta.Pack(b),
_metadata.MetadataPopulator.METADATA_FILE_IDENTIFIER)
self.metadata_buf = b.Output()
def _create_metadata(self):
"""Creates the metadata for an image classifier."""
# Creates model info.
model_meta = _metadata_fb.ModelMetadataT()
model_meta.name = self.model_info.name
model_meta.description = "Letter Recognition Model for handwrite letter recognition"
model_meta.version = self.model_info.version
model_meta.author = "Sebastainj1w"
model_meta.license = ("Apache License. Version 2.0 "
"http://www.apache.org/licenses/LICENSE-2.0.")
# Creates input info.
input_meta = _metadata_fb.TensorMetadataT()
input_meta.name = "sensor_data"
input_meta.description = "Input sensor data to be recognition. The expected data is 252 x 9, with one " \
"channels per pixel. Each value in the tensor is a float32. "
input_meta.content = _metadata_fb.ContentT()
input_meta.content.contentProperties = _metadata_fb.ImagePropertiesT()
input_meta.content.contentProperties.colorSpace = (
_metadata_fb.ColorSpaceType.GRAYSCALE)
input_meta.content.contentPropertiesType = (
_metadata_fb.ContentProperties.ImageProperties)
input_normalization = _metadata_fb.ProcessUnitT()
input_normalization.optionsType = (
_metadata_fb.ProcessUnitOptions.NormalizationOptions)
# input_normalization.options = _metadata_fb.NormalizationOptionsT()
# input_normalization.options.mean = self.model_info.mean
# input_normalization.options.std = self.model_info.std
# input_meta.processUnits = [input_normalization]
input_stats = _metadata_fb.StatsT()
input_stats.max = [self.model_info.image_max]
input_stats.min = [self.model_info.image_min]
input_meta.stats = input_stats
# Creates output info.
output_meta = _metadata_fb.TensorMetadataT()
output_meta.name = "probability"
output_meta.description = "Probabilities of the %d labels respectively." % self.model_info.num_classes
output_meta.content = _metadata_fb.ContentT()
output_meta.content.content_properties = _metadata_fb.FeaturePropertiesT()
output_meta.content.contentPropertiesType = (
_metadata_fb.ContentProperties.FeatureProperties)
output_stats = _metadata_fb.StatsT()
output_stats.max = [1.0]
output_stats.min = [0.0]
output_meta.stats = output_stats
label_file = _metadata_fb.AssociatedFileT()
label_file.name = os.path.basename(self.label_file_path)
label_file.description = "Labels for objects that the model can recognize."
label_file.type = _metadata_fb.AssociatedFileType.TENSOR_AXIS_LABELS
output_meta.associatedFiles = [label_file]
# Creates subgraph info.
subgraph = _metadata_fb.SubGraphMetadataT()
subgraph.inputTensorMetadata = [input_meta]
subgraph.outputTensorMetadata = [output_meta]
model_meta.subgraphMetadata = [subgraph]
b = flatbuffers.Builder(0)
b.Finish(
model_meta.Pack(b),
_metadata.MetadataPopulator.METADATA_FILE_IDENTIFIER)
self.metadata_buf = b.Output()
