Type init_ops_v2
Namespace tensorflow.python.ops.init_ops_v2
Methods
- he_normal
- he_normal_dyn
- he_uniform
- he_uniform_dyn
- lecun_normal
- lecun_normal_dyn
- lecun_uniform
- lecun_uniform_dyn
Properties
- _RandomGenerator_fn
- Constant_fn
- GlorotNormal_fn
- GlorotUniform_fn
- he_normal_fn
- he_uniform_fn
- Identity_fn
- Initializer_fn
- lecun_normal_fn
- lecun_uniform_fn
- normal
- normal_dyn
- one
- one_dyn
- ones
- ones_dyn
- Ones_fn
- Orthogonal_fn
- random_normal
- random_normal_dyn
- random_uniform
- random_uniform_dyn
- RandomNormal_fn
- RandomUniform_fn
- TruncatedNormal_fn
- uniform
- uniform_dyn
- VarianceScaling_fn
- zero
- zero_dyn
- zeros
- zeros_dyn
- Zeros_fn
Public static methods
VarianceScaling he_normal(Nullable<int> seed)
He normal initializer. It draws samples from a truncated normal distribution centered on 0
with standard deviation (after truncation) given by
`stddev = sqrt(2 / fan_in)` where `fan_in` is the number of
input units in the weight tensor.
Parameters
-
Nullable<int>seed - A Python integer. Used to seed the random generator.
Returns
-
VarianceScaling - An initializer. References: [He et al., 2015] (https://www.cv-foundation.org/openaccess/content_iccv_2015/html/He_Delving_Deep_into_ICCV_2015_paper.html) # pylint: disable=line-too-long ([pdf](https://www.cv-foundation.org/openaccess/content_iccv_2015/papers/He_Delving_Deep_into_ICCV_2015_paper.pdf))
object he_normal_dyn(object seed)
He normal initializer. It draws samples from a truncated normal distribution centered on 0
with standard deviation (after truncation) given by
`stddev = sqrt(2 / fan_in)` where `fan_in` is the number of
input units in the weight tensor.
Parameters
-
objectseed - A Python integer. Used to seed the random generator.
Returns
-
object - An initializer. References: [He et al., 2015] (https://www.cv-foundation.org/openaccess/content_iccv_2015/html/He_Delving_Deep_into_ICCV_2015_paper.html) # pylint: disable=line-too-long ([pdf](https://www.cv-foundation.org/openaccess/content_iccv_2015/papers/He_Delving_Deep_into_ICCV_2015_paper.pdf))
VarianceScaling he_uniform(Nullable<int> seed)
He uniform variance scaling initializer. It draws samples from a uniform distribution within [-limit, limit]
where `limit` is `sqrt(6 / fan_in)`
where `fan_in` is the number of input units in the weight tensor.
Parameters
-
Nullable<int>seed - A Python integer. Used to seed the random generator.
Returns
-
VarianceScaling - An initializer. References: [He et al., 2015] (https://www.cv-foundation.org/openaccess/content_iccv_2015/html/He_Delving_Deep_into_ICCV_2015_paper.html) # pylint: disable=line-too-long ([pdf](https://www.cv-foundation.org/openaccess/content_iccv_2015/papers/He_Delving_Deep_into_ICCV_2015_paper.pdf))
object he_uniform_dyn(object seed)
He uniform variance scaling initializer. It draws samples from a uniform distribution within [-limit, limit]
where `limit` is `sqrt(6 / fan_in)`
where `fan_in` is the number of input units in the weight tensor.
Parameters
-
objectseed - A Python integer. Used to seed the random generator.
Returns
-
object - An initializer. References: [He et al., 2015] (https://www.cv-foundation.org/openaccess/content_iccv_2015/html/He_Delving_Deep_into_ICCV_2015_paper.html) # pylint: disable=line-too-long ([pdf](https://www.cv-foundation.org/openaccess/content_iccv_2015/papers/He_Delving_Deep_into_ICCV_2015_paper.pdf))
VarianceScaling lecun_normal(Nullable<int> seed)
LeCun normal initializer. It draws samples from a truncated normal distribution centered on 0
with standard deviation (after truncation) given by
`stddev = sqrt(1 / fan_in)` where `fan_in` is the number of
input units in the weight tensor.
Parameters
-
Nullable<int>seed - A Python integer. Used to seed the random generator.
Returns
-
VarianceScaling - An initializer. References: - Self-Normalizing Neural Networks, [Klambauer et al., 2017](https://papers.nips.cc/paper/6698-self-normalizing-neural-networks) # pylint: disable=line-too-long ([pdf](https://papers.nips.cc/paper/6698-self-normalizing-neural-networks.pdf)) - Efficient Backprop, [Lecun et al., 1998](http://yann.lecun.com/exdb/publis/pdf/lecun-98b.pdf)
object lecun_normal_dyn(object seed)
LeCun normal initializer. It draws samples from a truncated normal distribution centered on 0
with standard deviation (after truncation) given by
`stddev = sqrt(1 / fan_in)` where `fan_in` is the number of
input units in the weight tensor.
Parameters
-
objectseed - A Python integer. Used to seed the random generator.
Returns
-
object - An initializer. References: - Self-Normalizing Neural Networks, [Klambauer et al., 2017](https://papers.nips.cc/paper/6698-self-normalizing-neural-networks) # pylint: disable=line-too-long ([pdf](https://papers.nips.cc/paper/6698-self-normalizing-neural-networks.pdf)) - Efficient Backprop, [Lecun et al., 1998](http://yann.lecun.com/exdb/publis/pdf/lecun-98b.pdf)
VarianceScaling lecun_uniform(Nullable<int> seed)
LeCun uniform initializer. It draws samples from a uniform distribution within [-limit, limit]
where `limit` is `sqrt(3 / fan_in)`
where `fan_in` is the number of input units in the weight tensor.
Parameters
-
Nullable<int>seed - A Python integer. Used to seed the random generator.
Returns
-
VarianceScaling - An initializer. References: - Self-Normalizing Neural Networks, [Klambauer et al., 2017](https://papers.nips.cc/paper/6698-self-normalizing-neural-networks) # pylint: disable=line-too-long ([pdf](https://papers.nips.cc/paper/6698-self-normalizing-neural-networks.pdf)) - Efficient Backprop, [Lecun et al., 1998](http://yann.lecun.com/exdb/publis/pdf/lecun-98b.pdf)
object lecun_uniform_dyn(object seed)
LeCun uniform initializer. It draws samples from a uniform distribution within [-limit, limit]
where `limit` is `sqrt(3 / fan_in)`
where `fan_in` is the number of input units in the weight tensor.
Parameters
-
objectseed - A Python integer. Used to seed the random generator.
Returns
-
object - An initializer. References: - Self-Normalizing Neural Networks, [Klambauer et al., 2017](https://papers.nips.cc/paper/6698-self-normalizing-neural-networks) # pylint: disable=line-too-long ([pdf](https://papers.nips.cc/paper/6698-self-normalizing-neural-networks.pdf)) - Efficient Backprop, [Lecun et al., 1998](http://yann.lecun.com/exdb/publis/pdf/lecun-98b.pdf)