|---| | [ View source on GitHub](https://github.com/tensorflow/probability/blob/v0.25.0/tensorflow_probability/python/layers/initializers.py#L24-L123) | Initializer which concats other intializers. #### View aliases **Main aliases** [`tfp.layers.initializers.BlockwiseInitializer`](https://www.tensorflow.org/probability/api_docs/python/tfp/layers/BlockwiseInitializer)
tfp.layers.BlockwiseInitializer( initializers, sizes, validate_args=False )


| ## Args || |---|---| | `initializers` | `list` of Keras initializers, e.g., `"glorot_uniform"` or `tf_keras.initializers.Constant(0.5413)`. | | `sizes` | `list` of `int` scalars representing the number of elements associated with each initializer in `initializers`. | | `validate_args` | Python `bool` indicating we should do (possibly expensive) graph-time assertions, if necessary. |



| ## Attributes || |---|---| | `initializers` |

| | `sizes` |

| | `validate_args` |

|
## Methods ### `from_config` [View source](https://github.com/tensorflow/probability/blob/v0.25.0/tensorflow_probability/python/layers/initializers.py#L115-L123) @classmethod from_config( config ) Instantiates an initializer from a configuration dictionary. ### `get_config` [View source](https://github.com/tensorflow/probability/blob/v0.25.0/tensorflow_probability/python/layers/initializers.py#L103-L113) get_config() Returns initializer configuration as a JSON-serializable dict. ### `__call__` [View source](https://github.com/tensorflow/probability/blob/v0.25.0/tensorflow_probability/python/layers/initializers.py#L54-L101) __call__( shape, dtype=None ) Returns a tensor object initialized as specified by the initializer.


| Args || |---|---| | `shape` | Shape of the tensor. | | `dtype` | Optional dtype of the tensor. If not provided will return tensor of [`tf.float32`](https://www.tensorflow.org/api_docs/python/tf#float32). |