neural_compressor.tensorflow.utils.utility

Module Contents

Classes

CpuInfo	Get CPU Info.
Statistics	The statistics printer.
CaptureOutputToFile	Not displayed in API Docs.
LazyImport	Lazy import python module till use.

Functions

version1_lt_version2(version1, version2)	Check whether version1 is less than version2.
version1_gt_version2(version1, version2)	Check whether version1 is greater than version2.
version1_eq_version2(version1, version2)	Check whether version1 is equal to version2.
version1_gte_version2(version1, version2)	Check whether version1 is greater than version2 or is equal to it.
version1_lte_version2(version1, version2)	Check whether version1 is less than version2 or is equal to it.
register_algo(name)	Decorator function to register algorithms in the algos_mapping dictionary.
deep_get(dictionary, keys[, default])	Get the dot key's item in nested dict
itex_installed()	Check if the Intel® Extension for TensorFlow has been installed.
dump_elapsed_time([customized_msg])	Get the elapsed time for decorated functions.
combine_histogram(old_hist, arr)	Collect layer histogram for arr and combine it with old histogram.
get_all_fp32_data(data)	Get all the fp32 data.
get_tensor_histogram(tensor_data[, bins])	Get the histogram of the tensor data.
Dequantize(data, scale_info)	Dequantize the data with the scale_info.
dequantize_weight(weight_tensor, min_filter_tensor, ...)	Dequantize the weight with min-max filter tensors.
dump_data_to_local(data, path, filename)	Dump data to local as pkl file.
load_data_from_pkl(path, filename)	Load data from local pkl file.
singleton(cls)	Not displayed in API Docs.
disable_random([seed])	A Decorator to disable tf random seed.
valid_keras_format(model)	Check if the input model is Sequential or Functional model.

neural_compressor.tensorflow.utils.utility.version1_lt_version2(version1, version2)

Check whether version1 is less than version2.

neural_compressor.tensorflow.utils.utility.version1_gt_version2(version1, version2)

Check whether version1 is greater than version2.

neural_compressor.tensorflow.utils.utility.version1_eq_version2(version1, version2)

Check whether version1 is equal to version2.

neural_compressor.tensorflow.utils.utility.version1_gte_version2(version1, version2)

Check whether version1 is greater than version2 or is equal to it.

neural_compressor.tensorflow.utils.utility.version1_lte_version2(version1, version2)

Check whether version1 is less than version2 or is equal to it.

neural_compressor.tensorflow.utils.utility.register_algo(name)

Decorator function to register algorithms in the algos_mapping dictionary.

Usage example:

@register_algo(name=example_algo) def example_algo(model: tf.keras.Model, quant_config: StaticQuantConfig) -> tf.keras.Model:

…

Parameters:

name (str) – The name under which the algorithm function will be registered.

Returns:

The decorator function to be used with algorithm functions.

Return type:

decorator

neural_compressor.tensorflow.utils.utility.deep_get(dictionary, keys, default=None)

Get the dot key’s item in nested dict

eg person = {‘person’:{‘name’:{‘first’:’John’}}} deep_get(person, “person.name.first”) will output ‘John’.

Parameters:

• dictionary (dict) – The dict object to get keys

• keys (dict) – The deep keys

• default (object) – The return item if key not exists

Returns:

the item of the deep dot keys

Return type:

item

neural_compressor.tensorflow.utils.utility.itex_installed()

Check if the Intel® Extension for TensorFlow has been installed.

neural_compressor.tensorflow.utils.utility.dump_elapsed_time(customized_msg='')

Get the elapsed time for decorated functions.

Parameters:

customized_msg (string, optional) – The parameter passed to decorator. Defaults to None.

neural_compressor.tensorflow.utils.utility.combine_histogram(old_hist, arr)

Collect layer histogram for arr and combine it with old histogram.

neural_compressor.tensorflow.utils.utility.get_all_fp32_data(data)

Get all the fp32 data.

neural_compressor.tensorflow.utils.utility.get_tensor_histogram(tensor_data, bins=2048)

Get the histogram of the tensor data.

neural_compressor.tensorflow.utils.utility.Dequantize(data, scale_info)

Dequantize the data with the scale_info.

neural_compressor.tensorflow.utils.utility.dequantize_weight(weight_tensor, min_filter_tensor, max_filter_tensor)

Dequantize the weight with min-max filter tensors.

neural_compressor.tensorflow.utils.utility.dump_data_to_local(data, path, filename)

Dump data to local as pkl file.

Parameters:

• data – Data used to dump

• path – The directory to save data

• filename – The filename to dump

Returns:

loaded data

neural_compressor.tensorflow.utils.utility.load_data_from_pkl(path, filename)

Load data from local pkl file.

Parameters:

• path – The directory to load data

• filename – The filename to load

neural_compressor.tensorflow.utils.utility.singleton(cls)

Not displayed in API Docs.

Singleton decorator.

neural_compressor.tensorflow.utils.utility.disable_random(seed=1)

A Decorator to disable tf random seed.

neural_compressor.tensorflow.utils.utility.valid_keras_format(model)

Check if the input model is Sequential or Functional model.

class neural_compressor.tensorflow.utils.utility.CpuInfo

Get CPU Info.

class neural_compressor.tensorflow.utils.utility.Statistics(data, header, field_names, output_handle=logger.info)

The statistics printer.

class neural_compressor.tensorflow.utils.utility.CaptureOutputToFile(tmp_file_path, stream=sys.stderr)

Not displayed in API Docs.

Capture the output to file.

class neural_compressor.tensorflow.utils.utility.LazyImport(module_name)

Lazy import python module till use.