tf.quantization.experimental.QuantizationOptions

View source on GitHub

A ProtocolMessage

View aliases

Compat aliases for migration

See Migration guide for more details.

tf.compat.v1.quantization.experimental.QuantizationOptions

Attributes
`calibration_options`	`CalibrationOptions calibration_options`
`debugger_options`	`DebuggerOptions debugger_options`
`enable_legacy_weight_only`	`bool enable_legacy_weight_only`
`enable_per_channel_quantization`	`bool enable_per_channel_quantization`
`enable_two_input_tensors`	`bool enable_two_input_tensors`
`experimental_enable_tpu_model_support`	`bool experimental_enable_tpu_model_support`
`force_graph_mode_calibration`	`bool force_graph_mode_calibration`
`freeze_all_variables`	`bool freeze_all_variables`
`min_num_elements_for_weights`	`int64 min_num_elements_for_weights`
`op_set`	`OpSet op_set`
`quantization_method`	`QuantizationMethod quantization_method`
`representative_datasets`	`repeated RepresentativeDatasetsEntry representative_datasets`
`signature_keys`	`repeated string signature_keys`
`tags`	`repeated string tags`
`unit_wise_quantization_specs`	`repeated UnitWiseQuantizationSpec unit_wise_quantization_specs`

Child Classes

class RepresentativeDatasetsEntry

Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates. Some content is licensed under the numpy license.

Last updated 2024-01-23 UTC.