niftynet.engine.application_initializer module
Loading modules from a string representing the class name
or a short name that matches the dictionary item defined
in this module
all classes and docs are taken from
https://github.com/tensorflow/tensorflow/blob/r1.3/tensorflow/python/ops/init_ops.py
-
class
Constant
[source]
Bases: object
initialize with a constant value
-
static
get_instance
(args)[source]
create an instance of the initializer
-
class
Zeros
[source]
Bases: object
initialize with zeros
-
static
get_instance
(args)[source]
create an instance of the initializer
-
class
Ones
[source]
Bases: object
initialize with ones
-
static
get_instance
(args)[source]
create an instance of the initializer
-
class
UniformUnitScaling
[source]
Bases: object
-
static
get_instance
(args)[source]
create an instance of the initializer
-
class
Orthogonal
[source]
Bases: object
-
static
get_instance
(args)[source]
create an instance of the initializer
-
class
VarianceScaling
[source]
Bases: object
-
static
get_instance
(args)[source]
create an instance of the initializer
-
class
GlorotNormal
[source]
Bases: object
-
static
get_instance
(args)[source]
create an instance of the initializer
-
class
GlorotUniform
[source]
Bases: object
-
static
get_instance
(args)[source]
create an instance of the initializer
-
class
HeUniform
[source]
Bases: object
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.
# Arguments
seed: A Python integer. Used to seed the random generator.
# Returns
An initializer.
# References
He et al., https://arxiv.org/abs/1502.01852
-
static
get_instance
(args)[source]
create an instance of the initializer
-
class
HeNormal
[source]
Bases: object
He normal initializer.
It draws samples from a truncated normal distribution centered on 0
with stddev = sqrt(2 / fan_in)
where fan_in
is the number of input units in the weight tensor.
# Arguments
seed: A Python integer. Used to seed the random generator.
# Returns
An initializer.
# References
He et al., https://arxiv.org/abs/1502.01852
-
static
get_instance
(args)[source]
create an instance of the initializer