tf.lite.RepresentativeDataset
Stay organized with collections
Save and categorize content based on your preferences.
Representative dataset to evaluate optimizations.
tf.lite.RepresentativeDataset(
input_gen
)
A representative dataset that can be used to evaluate optimizations by the
converter. E.g. converter can use these examples to estimate (min, max) ranges
by calibrating the model on inputs. This can allow converter to quantize a
converted floating point model.
Args |
|---|
input_gen
|
an input generator that can be used to generate input samples
for the model. This must be a callable object that returns an object
that supports the iter() protocol (e.g. a generator function). The
elements generated must have same type and shape as inputs to the model.
|
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.
Last updated 2020-10-01 UTC.
[null,null,["Last updated 2020-10-01 UTC."],[],[],null,["# tf.lite.RepresentativeDataset\n\n\u003cbr /\u003e\n\n|------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------|\n| [TensorFlow 2 version](/api_docs/python/tf/lite/RepresentativeDataset) | [View source on GitHub](https://github.com/tensorflow/tensorflow/blob/v1.15.0/tensorflow/lite/python/lite.py#L112-L130) |\n\nRepresentative dataset to evaluate optimizations.\n\n#### View aliases\n\n\n**Compat aliases for migration**\n\nSee\n[Migration guide](https://www.tensorflow.org/guide/migrate) for\nmore details.\n\n[`tf.compat.v1.lite.RepresentativeDataset`](/api_docs/python/tf/lite/RepresentativeDataset), \\`tf.compat.v2.lite.RepresentativeDataset\\`\n\n\u003cbr /\u003e\n\n tf.lite.RepresentativeDataset(\n input_gen\n )\n\nA representative dataset that can be used to evaluate optimizations by the\nconverter. E.g. converter can use these examples to estimate (min, max) ranges\nby calibrating the model on inputs. This can allow converter to quantize a\nconverted floating point model.\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Args ---- ||\n|-------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| `input_gen` | an input generator that can be used to generate input samples for the model. This must be a callable object that returns an object that supports the `iter()` protocol (e.g. a generator function). The elements generated must have same type and shape as inputs to the model. |\n\n\u003cbr /\u003e"]]
TensorFlow 2 version
View source on GitHub