tfmot.sparsity.keras.PruningSchedule
Stay organized with collections
Save and categorize content based on your preferences.
Specifies when to prune layer and the sparsity(%) at each training step.
PruningSchedule controls pruning during training by notifying at each step
whether the layer's weights should be pruned or not, and the sparsity(%) at
which they should be pruned.
It can be invoked as a callable by providing the training step Tensor. It
returns a tuple of bool and float tensors.
should_prune, sparsity = pruning_schedule(step)
You can inherit this class to write your own custom pruning schedule.
Methods
from_config
View source
@classmethod
from_config(
config
)
Instantiates a PruningSchedule from its config.
| Args |
|---|
config
|
Output of get_config().
|
| Returns |
|---|
A PruningSchedule instance.
|
get_config
View source
@abc.abstractmethod
get_config()
__call__
View source
@abc.abstractmethod
__call__(
step
)
Returns the sparsity(%) to be applied.
If the returned sparsity(%) is 0, pruning is ignored for the step.
| Args |
|---|
step
|
Current step in graph execution.
|
| Returns |
|---|
|
Sparsity (%) that should be applied to the weights for the step.
|
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 2023-05-26 UTC.
[null,null,["Last updated 2023-05-26 UTC."],[],[],null,["# tfmot.sparsity.keras.PruningSchedule\n\n\u003cbr /\u003e\n\n|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| [View source on GitHub](https://github.com/tensorflow/model-optimization/blob/v0.7.5/tensorflow_model_optimization/python/core/sparsity/keras/pruning_schedule.py#L22-L131) |\n\nSpecifies when to prune layer and the sparsity(%) at each training step.\n\nPruningSchedule controls pruning during training by notifying at each step\nwhether the layer's weights should be pruned or not, and the sparsity(%) at\nwhich they should be pruned.\n\nIt can be invoked as a `callable` by providing the training `step` Tensor. It\nreturns a tuple of bool and float tensors. \n\n should_prune, sparsity = pruning_schedule(step)\n\nYou can inherit this class to write your own custom pruning schedule.\n\nMethods\n-------\n\n### `from_config`\n\n[View source](https://github.com/tensorflow/model-optimization/blob/v0.7.5/tensorflow_model_optimization/python/core/sparsity/keras/pruning_schedule.py#L121-L131) \n\n @classmethod\n from_config(\n config\n )\n\nInstantiates a `PruningSchedule` from its config.\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Args ||\n|----------|---------------------------|\n| `config` | Output of `get_config()`. |\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Returns ||\n|---|---|\n| A `PruningSchedule` instance. ||\n\n\u003cbr /\u003e\n\n### `get_config`\n\n[View source](https://github.com/tensorflow/model-optimization/blob/v0.7.5/tensorflow_model_optimization/python/core/sparsity/keras/pruning_schedule.py#L116-L119) \n\n @abc.abstractmethod\n get_config()\n\n### `__call__`\n\n[View source](https://github.com/tensorflow/model-optimization/blob/v0.7.5/tensorflow_model_optimization/python/core/sparsity/keras/pruning_schedule.py#L101-L114) \n\n @abc.abstractmethod\n __call__(\n step\n )\n\nReturns the sparsity(%) to be applied.\n\nIf the returned sparsity(%) is 0, pruning is ignored for the step.\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Args ||\n|--------|----------------------------------|\n| `step` | Current step in graph execution. |\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Returns ||\n|---|---|\n| Sparsity (%) that should be applied to the weights for the step. ||\n\n\u003cbr /\u003e"]]
View source on GitHub