Class: TensorStream::NN

Inherits:
Object
  • Object
show all
Extended by:
OpHelper
Defined in:
lib/tensor_stream/nn/nn_ops.rb

Overview

High level machine learning functions

Class Method Summary collapse

Methods included from OpHelper

_op, cons, dtype_eval, format_source, fp_type?, i_cons, i_op, shape_eval, val_to_dtype

Class Method Details

.relu(features, name: nil) ⇒ Object 



9
10
11
 
# File 'lib/tensor_stream/nn/nn_ops.rb', line 9

def self.relu(features, name: nil)
  TensorStream.max(features, 0, name: "relu_#{name}")
end

.sigmoid(input, name: nil) ⇒ Object 



13
14
15
 
# File 'lib/tensor_stream/nn/nn_ops.rb', line 13

def self.sigmoid(input, name: nil)
  TensorStream.sigmoid(input, name)
end

.sigmoid_cross_entropy_with_logits(labels: nil, logits: nil, name: nil) ⇒ Object 



28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
 
# File 'lib/tensor_stream/nn/nn_ops.rb', line 28

def self.sigmoid_cross_entropy_with_logits(labels: nil, logits: nil, name: nil)
  TensorStream.name_scope(name, default: 'logistic_loss', values: [logits, labels]) do |name|
    tf = TensorStream
    logits = tf.convert_to_tensor(logits, name: 'logits')
    labels = tf.convert_to_tensor(labels, name: 'labels')
    zeros = tf.zeros_like(logits, dtype: logits.dtype)
    cond = (logits >= zeros)
    relu_logits = tf.where(cond, logits, zeros)
    neg_abs_logits = tf.where(cond, -logits, logits)

    return tf.add(
        relu_logits - logits * labels,
        tf.log1p(tf.exp(neg_abs_logits)),
        name: name)
  end
end

.softmax(logits, axis: nil, name: nil) ⇒ Object 



5
6
7
 
# File 'lib/tensor_stream/nn/nn_ops.rb', line 5

def self.softmax(logits, axis: nil, name: nil)
  _op(:softmax, logits, nil, axis: axis, name: name)
end

.softmax_cross_entropy_with_logits(labels: nil, logits: nil, name: nil) ⇒ Object 



17
18
19
20
21
22
23
24
25
26
 
# File 'lib/tensor_stream/nn/nn_ops.rb', line 17

def self.softmax_cross_entropy_with_logits(labels: nil, logits: nil, name: nil)
  TensorStream.name_scope(name, default: 'softmax_cross_entropy_with_logits', values: [logits, labels]) do |name|
    tf = TensorStream
    logits = tf.convert_to_tensor(logits, name: 'logits')
    labels = tf.convert_to_tensor(labels, name: 'labels')
    labels = tf.cast(labels, logits.dtype)
    softmax_logits = -tf.log(softmax(logits)) * labels
    tf.reduce_sum(softmax_logits, tf.rank(logits) - 1)
  end
end