Categorical - LostTech.TensorFlow Documentation

Type Categorical

Namespace tensorflow.distributions

Categorical distribution.

The Categorical distribution is parameterized by either probabilities or log-probabilities of a set of `K` classes. It is defined over the integers `{0, 1,..., K}`.

The Categorical distribution is closely related to the `OneHotCategorical` and `Multinomial` distributions. The Categorical distribution can be intuited as generating samples according to `argmax{ OneHotCategorical(probs) }` itself being identical to `argmax{ Multinomial(probs, total_count=1) }`.

#### Mathematical Details

The probability mass function (pmf) is,

```none pmf(k; pi) = prod_j pi_j**[k == j] ```

#### Pitfalls

The number of classes, `K`, must not exceed: - the largest integer representable by `self.dtype`, i.e., `2**(mantissa_bits+1)` (IEEE 754), - the maximum `Tensor` index, i.e., `2**31-1`.

In other words, Note: This condition is validated only when `self.validate_args = True`.

#### Examples

Creates a 3-class distribution with the 2nd class being most likely. Creates a 3-class distribution with the 2nd class being most likely. Parameterized by [logits](https://en.wikipedia.org/wiki/Logit) rather than probabilities. Creates a 3-class distribution with the 3rd class being most likely. The distribution functions can be evaluated on counts.

Show Example

K <= min(2**31-1, {
              tf.float16: 2**11,
              tf.float32: 2**24,
              tf.float64: 2**53 }[param.dtype])

Properties

Public properties

object allow_nan_stats get;

object allow_nan_stats_dyn get;

TensorShape batch_shape get;

object batch_shape_dyn get;

object dtype get;

object dtype_dyn get;

TensorShape event_shape get;

object event_shape_dyn get;

Tensor event_size get;

Scalar `int32` tensor: the number of classes.

object event_size_dyn get;

Scalar `int32` tensor: the number of classes.

object logits get;

Vector of coordinatewise logits.

object logits_dyn get;

Vector of coordinatewise logits.

string name get;

object name_dyn get;

IDictionary<object, object> parameters get;

object parameters_dyn get;

Tensor probs get;

Vector of coordinatewise probabilities.

object probs_dyn get;