Module: tfl.conditional_cdf
Stay organized with collections
Save and categorize content based on your preferences.
Implements CDF transformation with derived parameters (kernels).
cdf_fn is similar to tfl.layers.CDF, which is an additive / multiplicative
average of a few shifted and scaled sigmoid or relu6 basis functions,
with the difference that the functions are parametrized by the provided
parameters instead of learnable weights belonging to a tfl.layers.CDF layer.
These parameters can be one of:
- constants,
- trainable variables,
- outputs from other TF modules.
For inputs of shape (batch_size, input_dim), two sets of free-form
parameters are used to configure the CDF function:
location_parameters for where to place the sigmoid / relu6 transformation
basis,scaling_parameters (optional) for the horizontal scaling before applying
the transformation basis.
Functions
cdf_fn(...): Maps inputs through a CDF function specified by keypoint parameters.
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 2024-08-02 UTC.
[null,null,["Last updated 2024-08-02 UTC."],[],[],null,["# Module: tfl.conditional_cdf\n\n\u003cbr /\u003e\n\n|-------------------------------------------------------------------------------------------------------------------------|\n| [View source on GitHub](https://github.com/tensorflow/lattice/blob/v2.1.1/tensorflow_lattice/python/conditional_cdf.py) |\n\nImplements CDF transformation with derived parameters (kernels).\n\n`cdf_fn` is similar to [`tfl.layers.CDF`](../tfl/layers/CDF), which is an additive / multiplicative\naverage of a few shifted and scaled `sigmoid` or `relu6` basis functions,\nwith the difference that the functions are parametrized by the provided\nparameters instead of learnable weights belonging to a [`tfl.layers.CDF`](../tfl/layers/CDF) layer.\n\nThese parameters can be one of:\n\n- constants,\n- trainable variables,\n- outputs from other TF modules.\n\nFor inputs of shape `(batch_size, input_dim)`, two sets of free-form\nparameters are used to configure the CDF function:\n\n- `location_parameters` for where to place the sigmoid / relu6 transformation basis,\n- `scaling_parameters` (optional) for the horizontal scaling before applying the transformation basis.\n\nFunctions\n---------\n\n[`cdf_fn(...)`](../tfl/conditional_cdf/cdf_fn): Maps `inputs` through a CDF function specified by keypoint parameters."]]
View source on GitHub