# tfc.entropy_models.PowerLawEntropyModel

<br />

|---|
| [![](https://www.tensorflow.org/images/GitHub-Mark-32px.png) View source on GitHub](https://github.com/tensorflow/compression/blob/v2.14.1/tensorflow_compression/python/entropy_models/power_law.py#L27-L209) |

Entropy model for power-law distributed random variables.

#### View aliases


**Main aliases**

[`tfc.PowerLawEntropyModel`](https://www.tensorflow.org/api_docs/python/tfc/entropy_models/PowerLawEntropyModel)

<br />

    tfc.entropy_models.PowerLawEntropyModel(
        coding_rank, alpha=0.01, bottleneck_dtype=None
    )

This entropy model handles quantization and compression of a bottleneck tensor
and implements a penalty that encourages compressibility under the Elias gamma
code.

The gamma code has code lengths `1 + 2 floor(log_2(x))`, for `x` a positive
integer, and is close to optimal if `x` is distributed according to a power
law. Being a universal code, it also guarantees that in the worst case, the
expected code length is no more than 3 times the entropy of the empirical
distribution of `x`, as long as probability decreases with increasing `x`. For
details on the gamma code, see:
> "Universal Codeword Sets and Representations of the Integers"  
>
> P. Elias  
>
> <https://doi.org/10.1109/TIT.1975.1055349>

Given a signed integer, `run_length_gamma_encode` encodes zeros using a
run-length code, the sign using a uniform bit, and applies the gamma code to
the magnitude.

The penalty applied by this class is given by:

    log((abs(x) + alpha) / alpha)

This encourages `x` to follow a symmetrized power law, but only approximately
for `alpha > 0`. Without `alpha`, the penalty would have a singularity at
zero. Setting `alpha` to a small positive value ensures that the penalty is
non-negative, and that its gradients are useful for optimization.

<br />

<br />

<br />

| ## Args ||
|---|---|
| `coding_rank` | Integer. Number of innermost dimensions considered a coding unit. Each coding unit is compressed to its own bit string, and the estimated rate is summed over each coding unit in `bits()`. |
| `alpha` | Float. Regularization parameter preventing gradient singularity around zero. |
| `bottleneck_dtype` | [`tf.dtypes.DType`](https://www.tensorflow.org/api_docs/python/tf/dtypes/DType). Data type of bottleneck tensor. Defaults to [`tf.keras.mixed_precision.global_policy().compute_dtype`](https://www.tensorflow.org/api_docs/python/tf/keras/config/dtype_policy). |

<br />

<br />

<br />

<br />

| ## Attributes ||
|---|---|
| `alpha` | Alpha parameter. |
| `bottleneck_dtype` | Data type of the bottleneck tensor. |
| `coding_rank` | Number of innermost dimensions considered a coding unit. |
| `name` | Returns the name of this module as passed or determined in the ctor. <br /> > [!NOTE] > **Note:** This is not the same as the `self.name_scope.name` which includes parent module names. |
| `name_scope` | Returns a [`tf.name_scope`](https://www.tensorflow.org/api_docs/python/tf/name_scope) instance for this class. |
| `non_trainable_variables` | Sequence of non-trainable variables owned by this module and its submodules. > [!NOTE] > **Note:** this method uses reflection to find variables on the current instance and submodules. For performance reasons you may wish to cache the result of calling this method if you don't expect the return value to change. |
| `submodules` | Sequence of all sub-modules. Submodules are modules which are properties of this module, or found as properties of modules which are properties of this module (and so on). a = tf.Module() b = tf.Module() c = tf.Module() a.b = b b.c = c list(a.submodules) == [b, c] True list(b.submodules) == [c] True list(c.submodules) == [] True <br /> |
| `trainable_variables` | Sequence of trainable variables owned by this module and its submodules. <br /> > [!NOTE] > **Note:** this method uses reflection to find variables on the current instance and submodules. For performance reasons you may wish to cache the result of calling this method if you don't expect the return value to change. |
| `variables` | Sequence of variables owned by this module and its submodules. > [!NOTE] > **Note:** this method uses reflection to find variables on the current instance and submodules. For performance reasons you may wish to cache the result of calling this method if you don't expect the return value to change. |

## Methods

### `compress`

[View source](https://github.com/tensorflow/compression/blob/v2.14.1/tensorflow_compression/python/entropy_models/power_law.py#L149-L186)

    compress(
        bottleneck
    )

Compresses a floating-point tensor.

Compresses the tensor to bit strings. `bottleneck` is first quantized
as in `quantize()`, and then compressed using the run-length gamma code. The
quantized tensor can later be recovered by calling `decompress()`.

The innermost `self.coding_rank` dimensions are treated as one coding unit,
i.e. are compressed into one string each. Any additional dimensions to the
left are treated as batch dimensions.

<br />

<br />

<br />

| Args ||
|---|---|
| `bottleneck` | [`tf.Tensor`](https://www.tensorflow.org/api_docs/python/tf/Tensor) containing the data to be compressed. Must have at least `self.coding_rank` dimensions. |

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| A [`tf.Tensor`](https://www.tensorflow.org/api_docs/python/tf/Tensor) having the same shape as `bottleneck` without the `self.coding_rank` innermost dimensions, containing a string for each coding unit. ||

<br />

### `decompress`

[View source](https://github.com/tensorflow/compression/blob/v2.14.1/tensorflow_compression/python/entropy_models/power_law.py#L188-L209)

    decompress(
        strings, code_shape
    )

Decompresses a tensor.

Reconstructs the quantized tensor from bit strings produced by `compress()`.

<br />

<br />

<br />

| Args ||
|---|---|
| `strings` | [`tf.Tensor`](https://www.tensorflow.org/api_docs/python/tf/Tensor) containing the compressed bit strings. |
| `code_shape` | Shape of innermost dimensions of the output [`tf.Tensor`](https://www.tensorflow.org/api_docs/python/tf/Tensor). |

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| A [`tf.Tensor`](https://www.tensorflow.org/api_docs/python/tf/Tensor) of shape `tf.shape(strings) + code_shape`. ||

<br />

### `penalty`

[View source](https://github.com/tensorflow/compression/blob/v2.14.1/tensorflow_compression/python/entropy_models/power_law.py#L116-L130)

    penalty(
        bottleneck
    )

Computes penalty encouraging compressibility.

<br />

<br />

<br />

| Args ||
|---|---|
| `bottleneck` | [`tf.Tensor`](https://www.tensorflow.org/api_docs/python/tf/Tensor) containing the data to be compressed. Must have at least `self.coding_rank` dimensions. |

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| Penalty value, which has the same shape as `bottleneck` without the `self.coding_rank` innermost dimensions. ||

<br />

### `quantize`

[View source](https://github.com/tensorflow/compression/blob/v2.14.1/tensorflow_compression/python/entropy_models/power_law.py#L132-L147)

    quantize(
        bottleneck
    )

Quantizes a floating-point bottleneck tensor.

The tensor is rounded to integer values. The gradient of this rounding
operation is overridden with the identity (straight-through gradient
estimator).

<br />

<br />

<br />

| Args ||
|---|---|
| `bottleneck` | [`tf.Tensor`](https://www.tensorflow.org/api_docs/python/tf/Tensor) containing the data to be quantized. |

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| A [`tf.Tensor`](https://www.tensorflow.org/api_docs/python/tf/Tensor) containing the quantized values. ||

<br />

### `with_name_scope`

    @classmethod
    with_name_scope(
        method
    )

Decorator to automatically enter the module name scope.

    class MyModule(tf.Module):
      @tf.Module.with_name_scope
      def __call__(self, x):
        if not hasattr(self, 'w'):
          self.w = tf.Variable(tf.random.normal([x.shape[1], 3]))
        return tf.matmul(x, self.w)

Using the above module would produce [`tf.Variable`](https://www.tensorflow.org/api_docs/python/tf/Variable)s and [`tf.Tensor`](https://www.tensorflow.org/api_docs/python/tf/Tensor)s whose
names included the module name:

    mod = MyModule()
    mod(tf.ones([1, 2]))
    <tf.Tensor: shape=(1, 3), dtype=float32, numpy=..., dtype=float32)>
    mod.w
    <tf.Variable 'my_module/Variable:0' shape=(2, 3) dtype=float32,
    numpy=..., dtype=float32)>

<br />

<br />

<br />

| Args ||
|---|---|
| `method` | The method to wrap. |

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| The original method wrapped such that it enters the module's name scope. ||

<br />

### `__call__`

[View source](https://github.com/tensorflow/compression/blob/v2.14.1/tensorflow_compression/python/entropy_models/power_law.py#L102-L114)

    __call__(
        bottleneck
    )

Perturbs a tensor with (quantization) noise and computes penalty.

<br />

<br />

<br />

| Args ||
|---|---|
| `bottleneck` | [`tf.Tensor`](https://www.tensorflow.org/api_docs/python/tf/Tensor) containing the data to be compressed. Must have at least `self.coding_rank` dimensions. |

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| A tuple `(self.quantize(bottleneck), self.penalty(bottleneck))`. ||

<br />