tf_agents.distributions.utils.DistributionSpecV2
Stay organized with collections
Save and categorize content based on your preferences.
Describes a tfp.distribution.Distribution using nested parameters.
tf_agents.distributions.utils.DistributionSpecV2(
event_shape: tf.TensorShape,
dtype: tf.DType,
parameters: tf_agents.distributions.utils.Params
)
Args |
event_shape
|
The distribution's event_shape . This is the shape that
distribution.sample() returns. distribution.sample(sample_shape)
returns tensors of shape sample_shape + event_shape .
|
dtype
|
The distribution's dtype .
|
parameters
|
The recursive parameters of the distribution, with tensors
having directly been converted to tf.TypeSpec objects.
|
Attributes |
dtype
|
|
event_shape
|
|
event_spec
|
|
parameters
|
|
Methods
__eq__
View source
__eq__(
other
)
Return self==value.
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 2024-04-26 UTC.
[null,null,["Last updated 2024-04-26 UTC."],[],[],null,["# tf_agents.distributions.utils.DistributionSpecV2\n\n\u003cbr /\u003e\n\n|-----------------------------------------------------------------------------------------------------------------------|\n| [View source on GitHub](https://github.com/tensorflow/agents/blob/v0.19.0/tf_agents/distributions/utils.py#L571-L631) |\n\nDescribes a tfp.distribution.Distribution using nested parameters. \n\n tf_agents.distributions.utils.DistributionSpecV2(\n event_shape: tf.TensorShape,\n dtype: tf.DType,\n parameters: ../../../tf_agents/distributions/utils/Params\n )\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Args ---- ||\n|---------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| `event_shape` | The distribution's `event_shape`. This is the shape that `distribution.sample()` returns. `distribution.sample(sample_shape)` returns tensors of shape `sample_shape + event_shape`. |\n| `dtype` | The distribution's `dtype`. |\n| `parameters` | The recursive parameters of the distribution, with tensors having directly been converted to [`tf.TypeSpec`](https://www.tensorflow.org/api_docs/python/tf/TypeSpec) objects. |\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Raises ------ ||\n|-------------|---------------------------------------------------------------------------------------------------------------------|\n| `TypeError` | If for any entry `x` in `parameters`: [`tf.is_tensor(x)`](https://www.tensorflow.org/api_docs/python/tf/is_tensor). |\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Attributes ---------- ||\n|---------------|---------------|\n| `dtype` | \u003cbr /\u003e \u003cbr /\u003e |\n| `event_shape` | \u003cbr /\u003e \u003cbr /\u003e |\n| `event_spec` | \u003cbr /\u003e \u003cbr /\u003e |\n| `parameters` | \u003cbr /\u003e \u003cbr /\u003e |\n\n\u003cbr /\u003e\n\nMethods\n-------\n\n### `__eq__`\n\n[View source](https://github.com/tensorflow/agents/blob/v0.19.0/tf_agents/distributions/utils.py#L615-L621) \n\n __eq__(\n other\n )\n\nReturn self==value."]]