![]() |
Class Zeros
Initializer that generates tensors initialized to 0.
Inherits From: Initializer
Aliases:
- Class
tf.compat.v2.initializers.Zeros
- Class
tf.compat.v2.initializers.zeros
- Class
tf.compat.v2.keras.initializers.zeros
- Class
tf.compat.v2.zeros_initializer
Methods
tf.compat.v2.keras.initializers.Zeros.__call__
__call__(
shape,
dtype=tf.dtypes.float32
)
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 oftf.float32
.
tf.compat.v2.keras.initializers.Zeros.from_config
from_config(
cls,
config
)
Instantiates an initializer from a configuration dictionary.
Example:
initializer = RandomUniform(-1, 1)
config = initializer.get_config()
initializer = RandomUniform.from_config(config)
Args:
config
: A Python dictionary. It will typically be the output ofget_config
.
Returns:
An Initializer instance.
tf.compat.v2.keras.initializers.Zeros.get_config
get_config()
Returns the configuration of the initializer as a JSON-serializable dict.
Returns:
A JSON-serializable Python dict.