SoftmaxLayer.__init__() - Code Metrics - Inspection of "learning:nn: Add MLP, SDA, LSTM neural network" - TinghuiWang/pyActLearn - Measure and Improve Code Quality continuously with Scrutinizer

Completed

Push — master ( 39f179...514f8f )

by Tinghui

created 2017-01-23 16:43 UTC

SoftmaxLayer.init() B

↳ Parent: SoftmaxLayer

Complexity

Conditions

Size

Total Lines

Duplication

Lines	28
Ratio	100 %

Importance

Changes	1
Bugs	0	Features	0

Metric	Value
cc	5
c	1
b	0
f	0
dl	28
loc	28
rs	8.0894

import math
import tensorflow as tf
from . import variable_summary


class HiddenLayer:

    """ Typical hidden layer for Multi-layer perceptron
    User is allowed to specify the non-linearity activation function.

    Args:
        n_in (:obj:`int`): Number of input cells.
        n_out (:obj:`int`): Number of output cells.
        name (:obj:`str`): Name of the hidden layer.
        x (:class:`tensorflow.placeholder`): Input tensor.
        W (:class:`tensorflow.Variable`): Weight matrix.
        b (:class:`tensorflow.Variable`): Bias matrix.
        activation_fn: Activation function used in this hidden layer.
           Common values   :method:`tensorflow.sigmoid` for ``sigmoid`` function, :method:`tensorflow.tanh` for ``tanh``
           function, :method:`tensorflow.relu` for RELU.

    Attributes:
        n_in (:obj:`int`): Number of inputs into this layer.
        n_out (:obj:`int`): Number of outputs out of this layer.
        name (:obj:`str`): Name of the hidden layer.
        x (:class:`tensorflow.placeholder`): Tensorflow placeholder or tensor that represents the input of this layer.
        W (:class:`tensorflow.Variable`): Weight matrix of current layer.
        b (:class:`tensorflow.Variable`): Bias matrix of current layer.
        variables (:obj:`list` of :class:`tensorflow.Variable`): variables of current layer.
        logits (:obj:`tensorflow.Tensor`): Tensorflow tensor of linear logits computed in current layer.
        y (:class:`tensorflow.Tensor`): Tensorflow tensor represents the output function of this layer.
        summaries (:obj:`list`): List of Tensorflow summary buffer.
    """
    def __init__(self, n_in, n_out, name, x=None, W=None, b=None, activation_fn=tf.sigmoid):
        self.n_in = n_in
        self.n_out = n_out
        self.name = name
        with tf.name_scope(name):
            if x is None:
                self.x = tf.placeholder(tf.float32, shape=[None, n_in])
            else:
                self.x = x
            if W is None:
                self.W = tf.Variable(
                    tf.truncated_normal(shape=[n_in, n_out],stddev=1.0/math.sqrt(float(n_in))),
                    name='weights'
                )
            else:
                self.W = W
            if b is None:
                self.b = tf.Variable(tf.zeros(shape=[n_out]), name='biases')
            else:
                self.b = b
            self.variables = [self.W, self.b]
            self.logits = tf.matmul(self.x, self.W) + self.b
            self.y = activation_fn(self.logits, name='activations')
            self.summaries = []
            self.summaries += variable_summary(self.W, tag=name + '/weights')
            self.summaries += variable_summary(self.b, tag=name + '/bias')
            self.summaries.append(tf.summary.histogram(name + '/pre_act', self.logits))
            self.summaries.append(tf.summary.histogram(name + '/act', self.y))


class SoftmaxLayer:

    """ Softmax Layer as multi-class binary classification output layer

    Parameters:
        n_in (:obj:`int`): Number of input cells.
        n_out (:obj:`int`): Number of output cells.
        name (:obj:`str`): Name of the layer.
        x (:class:`tensorflow.placeholder`): Input tensor.
        W (:class:`tensorflow.Variable`): Weight matrix.
        b (:class:`tensorflow.Variable`): Bias matrix.

    Attributes:
        n_in (:obj:`int`): Number of inputs into this layer.
        n_out (:obj:`int`): Number of outputs out of this layer.
        name (:obj:`str`): Name of the hidden layer.
        x (:class:`tensorflow.placeholder`): Tensorflow placeholder or tensor that represents the input of this layer.
        W (:class:`tensorflow.Variable`): Weight matrix of current layer.
        b (:class:`tensorflow.Variable`): Bias matrix of current layer.
        variables (:obj:`list` of :class:`tensorflow.Variable`): variables of current layer.
        logits (:obj:`tensorflow.Tensor`): Tensorflow tensor of linear logits computed in current layer.
        y (:class:`tensorflow.Tensor`): Tensorflow tensor represents the output function of this layer.
    """
    def __init__(self, n_in, n_out, name, x=None, W=None, b=None):
        self.n_in = n_in
        self.n_out = n_out
        with tf.name_scope(name):
            if x is None:
                self.x = tf.placeholder(tf.float32, shape=[None, n_in], name='input-x')
            else:
                self.x = x
            if W is None:
                self.W = tf.Variable(
                    tf.truncated_normal(shape=[n_in, n_out],stddev=1.0/math.sqrt(float(n_in))),
                    name='weights'
                )
            else:
                self.W = W
            if b is None:
                self.b = tf.Variable(tf.zeros(shape=[n_out]), name='biases')
            else:
                self.b = b
            self.variables = [self.W, self.b]
            self.logits = tf.matmul(self.x, self.W) + self.b
            self.name = name
            self.y = tf.nn.softmax(self.logits, name='softmax')
            self.summaries = []
            self.summaries += variable_summary(self.W, tag=name + '/weights')
            self.summaries += variable_summary(self.b, tag=name + '/bias')
            self.summaries.append(tf.summary.histogram(name + '/pre_act', self.logits))
            self.summaries.append(tf.summary.histogram(name + '/act', self.y))


class AutoencoderLayer(HiddenLayer):
    """Autoencoder Layer

    Auto-encoder inherits hidden layer for feed-forward calculation, and adds self encoding
    tensor for unsupervised pre-training.

    Args:
        n_in (:obj:`int`): Number of input cells.
        n_out (:obj:`int`): Number of output cells.
        name (:obj:`str`): Name of the hidden layer.
        x (:class:`tensorflow.placeholder`): Input tensor.
        W (:class:`tensorflow.Variable`): Weight matrix.
        b (:class:`tensorflow.Variable`): Bias matrix.
        shared_weights (:obj:`bool`): If weights is shared between encoding and decoding.

    Attributes:
        n_in (:obj:`int`): Number of inputs into this layer.
        n_out (:obj:`int`): Number of outputs out of this layer.
        name (:obj:`str`): Name of the hidden layer.
        x (:class:`tensorflow.placeholder`): Tensorflow placeholder or tensor that represents the input of this layer.
        W (:class:`tensorflow.Variable`): Weight matrix used in encoding.
        b (:class:`tensorflow.Variable`): Bias matrix in encoding.
        W_prime (:obj:`tensorflow.Tensor`): Weight matrix used in self-decoding process. If weights are shared, it
            equals to transpose of encoding weight matrix.
        b_prime (:obj:`tensorflow.Tensor`): Bias matrix used in self-decoding process.
        variables (:obj:`list` of :class:`tensorflow.Variable`): variables of current layer.
        logits (:obj:`tensorflow.Tensor`): Tensorflow tensor of linear logits computed after encoding.

        y (:class:`tensorflow.Tensor`): Tensorflow tensor represents the output function of this layer.
        summaries (:obj:`list`): List of Tensorflow summary buffer.
    """
    def __init__(self, n_in, n_out, name, x=None, W=None, b=None, shared_weights=True):
        super().__init__(n_in, n_out, name, x, W, b, tf.sigmoid)
        self.b_prime = tf.Variable(tf.zeros(shape=[n_in]), name='biases_prime')
        self.variables.append(self.b_prime)
        if shared_weights:
            self.W_prime = tf.transpose(self.W)
        else:
            self.W_prime = tf.Variable(
                tf.truncated_normal(shape=[n_out, n_in], stddev=1.0 / math.sqrt(float(n_in))),
                name='weights_prime'
            )
            self.variables.append(self.W_prime)
        self.encode_logit = tf.matmul(self.y, self.W_prime) + self.b_prime
        self.encode = tf.sigmoid(self.encode_logit)
        self.encode_loss = tf.reduce_mean(tf.pow(self.x - self.encode, 2))
        self.summaries.append(tf.summary.scalar(name+'/ae_rmse', self.encode_loss))
        self.merged = tf.summary.merge(self.summaries)


1		import math
2		import tensorflow as tf
3		from . import variable_summary
4
5
6	View Code Duplication	class HiddenLayer:
		0 ignored issues – show Duplication introduced 2017-01-23 16:44 UTC by Report Bug Copy Issue Report This code seems to be duplicated in your project. Loading history...
7		""" Typical hidden layer for Multi-layer perceptron
8		User is allowed to specify the non-linearity activation function.
9
10		Args:
11		n_in (:obj:`int`): Number of input cells.
12		n_out (:obj:`int`): Number of output cells.
13		name (:obj:`str`): Name of the hidden layer.
14		x (:class:`tensorflow.placeholder`): Input tensor.
15		W (:class:`tensorflow.Variable`): Weight matrix.
16		b (:class:`tensorflow.Variable`): Bias matrix.
17		activation_fn: Activation function used in this hidden layer.
18		Common values :method:`tensorflow.sigmoid` for ``sigmoid`` function, :method:`tensorflow.tanh` for ``tanh``
19		function, :method:`tensorflow.relu` for RELU.
20
21		Attributes:
22		n_in (:obj:`int`): Number of inputs into this layer.
23		n_out (:obj:`int`): Number of outputs out of this layer.
24		name (:obj:`str`): Name of the hidden layer.
25		x (:class:`tensorflow.placeholder`): Tensorflow placeholder or tensor that represents the input of this layer.
26		W (:class:`tensorflow.Variable`): Weight matrix of current layer.
27		b (:class:`tensorflow.Variable`): Bias matrix of current layer.
28		variables (:obj:`list` of :class:`tensorflow.Variable`): variables of current layer.
29		logits (:obj:`tensorflow.Tensor`): Tensorflow tensor of linear logits computed in current layer.
30		y (:class:`tensorflow.Tensor`): Tensorflow tensor represents the output function of this layer.
31		summaries (:obj:`list`): List of Tensorflow summary buffer.
32		"""
33		def __init__(self, n_in, n_out, name, x=None, W=None, b=None, activation_fn=tf.sigmoid):
34		self.n_in = n_in
35		self.n_out = n_out
36		self.name = name
37		with tf.name_scope(name):
38		if x is None:
39		self.x = tf.placeholder(tf.float32, shape=[None, n_in])
40		else:
41		self.x = x
42		if W is None:
43		self.W = tf.Variable(
44		tf.truncated_normal(shape=[n_in, n_out],stddev=1.0/math.sqrt(float(n_in))),
45		name='weights'
46		)
47		else:
48		self.W = W
49		if b is None:
50		self.b = tf.Variable(tf.zeros(shape=[n_out]), name='biases')
51		else:
52		self.b = b
53		self.variables = [self.W, self.b]
54		self.logits = tf.matmul(self.x, self.W) + self.b
55		self.y = activation_fn(self.logits, name='activations')
56		self.summaries = []
57		self.summaries += variable_summary(self.W, tag=name + '/weights')
58		self.summaries += variable_summary(self.b, tag=name + '/bias')
59		self.summaries.append(tf.summary.histogram(name + '/pre_act', self.logits))
60		self.summaries.append(tf.summary.histogram(name + '/act', self.y))
61
62
63	View Code Duplication	class SoftmaxLayer:
		0 ignored issues – show Duplication introduced 2017-01-23 16:44 UTC by Report Bug Copy Issue Report This code seems to be duplicated in your project. Loading history...
64		""" Softmax Layer as multi-class binary classification output layer
65
66		Parameters:
67		n_in (:obj:`int`): Number of input cells.
68		n_out (:obj:`int`): Number of output cells.
69		name (:obj:`str`): Name of the layer.
70		x (:class:`tensorflow.placeholder`): Input tensor.
71		W (:class:`tensorflow.Variable`): Weight matrix.
72		b (:class:`tensorflow.Variable`): Bias matrix.
73
74		Attributes:
75		n_in (:obj:`int`): Number of inputs into this layer.
76		n_out (:obj:`int`): Number of outputs out of this layer.
77		name (:obj:`str`): Name of the hidden layer.
78		x (:class:`tensorflow.placeholder`): Tensorflow placeholder or tensor that represents the input of this layer.
79		W (:class:`tensorflow.Variable`): Weight matrix of current layer.
80		b (:class:`tensorflow.Variable`): Bias matrix of current layer.
81		variables (:obj:`list` of :class:`tensorflow.Variable`): variables of current layer.
82		logits (:obj:`tensorflow.Tensor`): Tensorflow tensor of linear logits computed in current layer.
83		y (:class:`tensorflow.Tensor`): Tensorflow tensor represents the output function of this layer.
84		"""
85		def __init__(self, n_in, n_out, name, x=None, W=None, b=None):
86		self.n_in = n_in
87		self.n_out = n_out
88		with tf.name_scope(name):
89		if x is None:
90		self.x = tf.placeholder(tf.float32, shape=[None, n_in], name='input-x')
91		else:
92		self.x = x
93		if W is None:
94		self.W = tf.Variable(
95		tf.truncated_normal(shape=[n_in, n_out],stddev=1.0/math.sqrt(float(n_in))),
96		name='weights'
97		)
98		else:
99		self.W = W
100		if b is None:
101		self.b = tf.Variable(tf.zeros(shape=[n_out]), name='biases')
102		else:
103		self.b = b
104		self.variables = [self.W, self.b]
105		self.logits = tf.matmul(self.x, self.W) + self.b
106		self.name = name
107		self.y = tf.nn.softmax(self.logits, name='softmax')
108		self.summaries = []
109		self.summaries += variable_summary(self.W, tag=name + '/weights')
110		self.summaries += variable_summary(self.b, tag=name + '/bias')
111		self.summaries.append(tf.summary.histogram(name + '/pre_act', self.logits))
112		self.summaries.append(tf.summary.histogram(name + '/act', self.y))
113
114
115		class AutoencoderLayer(HiddenLayer):
116		"""Autoencoder Layer
117
118		Auto-encoder inherits hidden layer for feed-forward calculation, and adds self encoding
119		tensor for unsupervised pre-training.
120
121		Args:
122		n_in (:obj:`int`): Number of input cells.
123		n_out (:obj:`int`): Number of output cells.
124		name (:obj:`str`): Name of the hidden layer.
125		x (:class:`tensorflow.placeholder`): Input tensor.
126		W (:class:`tensorflow.Variable`): Weight matrix.
127		b (:class:`tensorflow.Variable`): Bias matrix.
128		shared_weights (:obj:`bool`): If weights is shared between encoding and decoding.
129
130		Attributes:
131		n_in (:obj:`int`): Number of inputs into this layer.
132		n_out (:obj:`int`): Number of outputs out of this layer.
133		name (:obj:`str`): Name of the hidden layer.
134		x (:class:`tensorflow.placeholder`): Tensorflow placeholder or tensor that represents the input of this layer.
135		W (:class:`tensorflow.Variable`): Weight matrix used in encoding.
136		b (:class:`tensorflow.Variable`): Bias matrix in encoding.
137		W_prime (:obj:`tensorflow.Tensor`): Weight matrix used in self-decoding process. If weights are shared, it
138		equals to transpose of encoding weight matrix.
139		b_prime (:obj:`tensorflow.Tensor`): Bias matrix used in self-decoding process.
140		variables (:obj:`list` of :class:`tensorflow.Variable`): variables of current layer.
141		logits (:obj:`tensorflow.Tensor`): Tensorflow tensor of linear logits computed after encoding.
142
143		y (:class:`tensorflow.Tensor`): Tensorflow tensor represents the output function of this layer.
144		summaries (:obj:`list`): List of Tensorflow summary buffer.
145		"""
146		def __init__(self, n_in, n_out, name, x=None, W=None, b=None, shared_weights=True):
147		super().__init__(n_in, n_out, name, x, W, b, tf.sigmoid)
148		self.b_prime = tf.Variable(tf.zeros(shape=[n_in]), name='biases_prime')
149		self.variables.append(self.b_prime)
150		if shared_weights:
151		self.W_prime = tf.transpose(self.W)
152		else:
153		self.W_prime = tf.Variable(
154		tf.truncated_normal(shape=[n_out, n_in], stddev=1.0 / math.sqrt(float(n_in))),
155		name='weights_prime'
156		)
157		self.variables.append(self.W_prime)
158		self.encode_logit = tf.matmul(self.y, self.W_prime) + self.b_prime
159		self.encode = tf.sigmoid(self.encode_logit)
160		self.encode_loss = tf.reduce_mean(tf.pow(self.x - self.encode, 2))
161		self.summaries.append(tf.summary.scalar(name+'/ae_rmse', self.encode_loss))
162		self.merged = tf.summary.merge(self.summaries)
163

TinghuiWang / pyActLearn

Push — master ( 39f179...514f8f )

SoftmaxLayer.__init__() B

Complexity

Size

Duplication

Importance

Duplication Side-by-Side

Filter issues like

SoftmaxLayer.init() B