Python 可培训的多参数活动。函数(RBF)NeuPy/Theano
如何在Neupy或Theano中实现自定义激活函数(通过梯度下降调整均值和方差的RBF核),以便在Neupy中使用 {快速背景:梯度下降适用于网络中的每个参数。我想创建一个包含优化特征参数的专用特征空间,以便Neupy} 我认为我的问题在于参数的创建、它们的大小以及它们之间的连接方式 感兴趣的主要功能 激活函数类 径向基函数 功能塑造?Python 可培训的多参数活动。函数(RBF)NeuPy/Theano,python,machine-learning,theano,neupy,Python,Machine Learning,Theano,Neupy,如何在Neupy或Theano中实现自定义激活函数(通过梯度下降调整均值和方差的RBF核),以便在Neupy中使用 {快速背景:梯度下降适用于网络中的每个参数。我想创建一个包含优化特征参数的专用特征空间,以便Neupy} 我认为我的问题在于参数的创建、它们的大小以及它们之间的连接方式 感兴趣的主要功能 激活函数类 径向基函数 功能塑造? 非常感谢您的帮助,因为这将为您提供有关如何定制neupy networks的深刻见解。文档可能需要在某些方面做一些工作,至少……当层更改输入变量的形状时,它必须
非常感谢您的帮助,因为这将为您提供有关如何定制neupy networks的深刻见解。文档可能需要在某些方面做一些工作,至少……当层更改输入变量的形状时,它必须将更改通知后续层。对于这种情况,它必须具有自定义的
output\u shape
属性。例如:
from neupy import layers
from neupy.utils import as_tuple
import theano.tensor as T
class Flatten(layers.BaseLayer):
"""
Slight modification of the Reshape layer from the neupy library:
https://github.com/itdxer/neupy/blob/master/neupy/layers/reshape.py
"""
@property
def output_shape(self):
# Number of output feature depends on the input shape
# When layer receives input with shape (10, 3, 4)
# than output will be (10, 12). First number 10 defines
# number of samples which you typically don't need to
# change during propagation
n_output_features = np.prod(self.input_shape)
return (n_output_features,)
def output(self, input_value):
n_samples = input_value.shape[0]
return T.reshape(input_value, as_tuple(n_samples, self.output_shape))
如果您在终端中运行它,您将看到它工作正常
>>> network = layers.Input((3, 4)) > Flatten()
>>> predict = network.compile()
>>> predict(np.random.random((10, 3, 4))).shape
(10, 12)
在您的示例中,我可以看到一些问题:
rbf
函数不返回no表达式。它应该在函数编译期间失败np.linalg.norm这样的函数将返回标量李>
以下解决方案应该适合您
import numpy as np
from neupy import layers, init
import theano.tensor as T
def norm(value, axis=None):
return T.sqrt(T.sum(T.square(value), axis=axis))
class RBF(layers.BaseLayer):
def initialize(self):
super(RBF, self).initialize()
# It's more flexible when shape of the parameters
# denend on the input shape
self.add_parameter(
name='mean', shape=self.input_shape,
value=init.Constant(0.), trainable=True)
self.add_parameter(
name='std_dev', shape=self.input_shape,
value=init.Constant(1.), trainable=True)
def output(self, input_value):
K = input_value - self.mean
return T.exp(-norm(K, axis=0) / self.std_dev)
network = layers.Input(1) > RBF()
predict = network.compile()
print(predict(np.random.random((10, 1))))
network = layers.Input(4) > RBF()
predict = network.compile()
print(predict(np.random.random((10, 4))))
虽然itdxer充分回答了这个问题,但我想补充一下这个问题的确切解决方案
建筑创作
激活函数
径向基函数类
训练
如果你对培训感兴趣。就这么简单,
# Set training algorithm
gdnet = algorithms.Momentum(
network,
momenutm = 0.1
)
# Train.
gdnet.train(x,y,max_iter=100)
通过适当的输入和目标进行编译,并在元素基础上更新均值和方差。两项建议:(1)添加关于可培训性的评论/演示;(2)绘图总是有帮助的。但这非常有效,而且非常有指导意义。谢谢
>>> network = layers.Input((3, 4)) > Flatten()
>>> predict = network.compile()
>>> predict(np.random.random((10, 3, 4))).shape
(10, 12)
import numpy as np
from neupy import layers, init
import theano.tensor as T
def norm(value, axis=None):
return T.sqrt(T.sum(T.square(value), axis=axis))
class RBF(layers.BaseLayer):
def initialize(self):
super(RBF, self).initialize()
# It's more flexible when shape of the parameters
# denend on the input shape
self.add_parameter(
name='mean', shape=self.input_shape,
value=init.Constant(0.), trainable=True)
self.add_parameter(
name='std_dev', shape=self.input_shape,
value=init.Constant(1.), trainable=True)
def output(self, input_value):
K = input_value - self.mean
return T.exp(-norm(K, axis=0) / self.std_dev)
network = layers.Input(1) > RBF()
predict = network.compile()
print(predict(np.random.random((10, 1))))
network = layers.Input(4) > RBF()
predict = network.compile()
print(predict(np.random.random((10, 4))))
network = layers.Input(size) > RBF() > layers.Softmax(num_out)
# Elementwise Gaussian (RBF)
def rbf(value, mean, std):
return T.exp(-.5*T.sqr(value-mean)/T.sqr(std))/(std*T.sqrt(2*np.pi))
class RBF(layers.BaseLayer):
def initialize(self):
# Begin by initializing.
super(RBF, self).initialize()
# Add parameters to train
self.add_parameter(name='means', shape=self.input_shape,
value=init.Normal(), trainable=True)
self.add_parameter(name='std_dev', shape=self.input_shape,
value=init.Normal(), trainable=True)
# Define output function for the RBF layer.
def output(self, input_value):
K = input_value - self.means
return rbf(input_value,self.means,self.std_dev
# Set training algorithm
gdnet = algorithms.Momentum(
network,
momenutm = 0.1
)
# Train.
gdnet.train(x,y,max_iter=100)