Class: DNN::Model

Inherits:
Object
  • Object
show all
Includes:
Numo
Defined in:
lib/dnn/core/model.rb

Overview

This class deals with the model of the network.

Instance Attribute Summary collapse

Class Method Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize ⇒ Model

Returns a new instance of Model.



24
25
26
27
28
29
30
 
# File 'lib/dnn/core/model.rb', line 24

def initialize
  @layers = []
  @optimizer = nil
  @batch_size = nil
  @training = false
  @compiled = false
end

Instance Attribute Details

#batch_size ⇒ Object (readonly)

Returns the value of attribute batch_size.



10
11
12
 
# File 'lib/dnn/core/model.rb', line 10

def batch_size
  @batch_size
end

#layers ⇒ Object

Returns the value of attribute layers.



8
9
10
 
# File 'lib/dnn/core/model.rb', line 8

def layers
  @layers
end

#optimizer ⇒ Object (readonly)

Returns the value of attribute optimizer.



9
10
11
 
# File 'lib/dnn/core/model.rb', line 9

def optimizer
  @optimizer
end

Class Method Details

.load(file_name) ⇒ Object 



12
13
14
 
# File 'lib/dnn/core/model.rb', line 12

def self.load(file_name)
  Marshal.load(File.binread(file_name))
end

.load_json(json_str) ⇒ Object 



16
17
18
19
20
21
22
 
# File 'lib/dnn/core/model.rb', line 16

def self.load_json(json_str)
  hash = JSON.parse(json_str, symbolize_names: true)
  model = self.new
  model.layers = hash[:layers].map { |hash_layer| Util.load_hash(hash_layer) }
  model.compile(Util.load_hash(hash[:optimizer]))
  model
end

Instance Method Details

#<<(layer) ⇒ Object 



65
66
67
68
69
70
71
 
# File 'lib/dnn/core/model.rb', line 65

def <<(layer)
  unless layer.is_a?(Layers::Layer)
    raise DNN_TypeError.new("layer is not an instance of the DNN::Layers::Layer class.")
  end
  @layers << layer
  self
end

#accurate(x, y, batch_size = nil, &batch_proc) ⇒ Object 



145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
 
# File 'lib/dnn/core/model.rb', line 145

def accurate(x, y, batch_size = nil, &batch_proc)
  unless batch_size
    if @batch_size
      batch_size = @batch_size >= x.shape[0] ? @batch_size : x.shape[0]
    else
      batch_size = 1
    end
  end
  correct = 0
  (x.shape[0].to_f / @batch_size).ceil.times do |i|
    x_batch = SFloat.zeros(@batch_size, *x.shape[1..-1])
    y_batch = SFloat.zeros(@batch_size, *y.shape[1..-1])
    @batch_size.times do |j|
      k = i * @batch_size + j
      break if k >= x.shape[0]
      x_batch[j, false] = x[k, false]
      y_batch[j, false] = y[k, false]
    end
    x_batch, y_batch = batch_proc.call(x_batch, y_batch) if batch_proc
    out = forward(x_batch, false)
    @batch_size.times do |j|
     correct += 1 if out[j, true].max_index == y_batch[j, true].max_index
    end
  end
  correct.to_f / x.shape[0]
end

#backward(y) ⇒ Object 



188
189
190
191
192
193
194
 
# File 'lib/dnn/core/model.rb', line 188

def backward(y)
  dout = y
  @layers[0..-1].reverse.each do |layer|
    dout = layer.backward(dout)
  end
  dout
end

#compile(optimizer) ⇒ Object 



73
74
75
76
77
78
79
80
81
82
83
84
 
# File 'lib/dnn/core/model.rb', line 73

def compile(optimizer)
  unless optimizer.is_a?(Optimizers::Optimizer)
    raise DNN_TypeError.new("optimizer is not an instance of the DNN::Optimizers::Optimizer class.")
  end
  @compiled = true
  layers_check
  @optimizer = optimizer
  @layers.each do |layer|
    layer.build(self)
  end
  layers_shape_check
end

#compiled? ⇒ Boolean

Returns:

  • (Boolean) 


86
87
88
 
# File 'lib/dnn/core/model.rb', line 86

def compiled?
  @compiled
end

#forward(x, training) ⇒ Object 



180
181
182
183
184
185
186
 
# File 'lib/dnn/core/model.rb', line 180

def forward(x, training)
  @training = training
  @layers.each do |layer|
    x = layer.forward(x)
  end
  x
end

#load_json_params(json_str) ⇒ Object 



32
33
34
35
36
37
38
39
40
41
42
43
 
# File 'lib/dnn/core/model.rb', line 32

def load_json_params(json_str)
  has_param_layers_params = JSON.parse(json_str, symbolize_names: true)
  has_param_layers_index = 0
  @layers.each do |layer|
    next unless layer.is_a?(HasParamLayer)
    hash_params = has_param_layers_params[has_param_layers_index]
    hash_params.each do |key, param|
      layer.params[key] = SFloat.cast(param)
    end
    has_param_layers_index += 1
  end
end

#params_to_json ⇒ Object 



57
58
59
60
61
62
63
 
# File 'lib/dnn/core/model.rb', line 57

def params_to_json
  has_param_layers = @layers.select { |layer| layer.is_a?(HasParamLayer) }
  has_param_layers_params = has_param_layers.map do |layer|
    layer.params.map { |key, param| [key, param.to_a] }.to_h
  end
  JSON.dump(has_param_layers_params)
end

#predict(x) ⇒ Object 



172
173
174
 
# File 'lib/dnn/core/model.rb', line 172

def predict(x)
  forward(x, false)
end

#predict1(x) ⇒ Object 



176
177
178
 
# File 'lib/dnn/core/model.rb', line 176

def predict1(x)
  predict(SFloat.cast([x]))[0, false]
end

#save(file_name) ⇒ Object 



45
46
47
48
49
 
# File 'lib/dnn/core/model.rb', line 45

def save(file_name)
  dir_name = file_name.match(%r`(.*)/.+$`)[1]
  Dir.mkdir(dir_name) unless Dir.exist?(dir_name)
  File.binwrite(file_name, Marshal.dump(self))
end

#to_json ⇒ Object 



51
52
53
54
55
 
# File 'lib/dnn/core/model.rb', line 51

def to_json
  hash_layers = @layers.map { |layer| layer.to_hash }
  hash = {version: VERSION, layers: hash_layers, optimizer: @optimizer.to_hash}
  JSON.dump(hash)
end

#train(x, y, epochs, batch_size: 1, test: nil, verbose: true, batch_proc: nil, &epoch_proc) ⇒ Object 



94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
 
# File 'lib/dnn/core/model.rb', line 94

def train(x, y, epochs,
          batch_size: 1,
          test: nil,
          verbose: true,
          batch_proc: nil,
          &epoch_proc)
  @batch_size = batch_size
  num_train_data = x.shape[0]
  (1..epochs).each do |epoch|
    puts "【 epoch #{epoch}/#{epochs} 】" if verbose
    (num_train_data.to_f / @batch_size).ceil.times do |index|
      x_batch, y_batch = Util.get_minibatch(x, y, @batch_size)
      loss = train_on_batch(x_batch, y_batch, @batch_size, &batch_proc)
      if loss.nan?
        puts "\nloss is nan" if verbose
        return
      end
      num_trained_data = (index + 1) * batch_size
      num_trained_data = num_trained_data > num_train_data ? num_train_data : num_trained_data
      log = "\r"
      40.times do |i|
        if i < num_trained_data * 40 / num_train_data
          log << "="
        elsif i == num_trained_data * 40 / num_train_data
          log << ">"
        else
          log << "_"
        end
      end
      log << "  #{num_trained_data}/#{num_train_data} loss: #{sprintf('%.8f', loss)}"
      print log if verbose
    end
    if verbose && test
      acc = accurate(test[0], test[1], batch_size,&batch_proc)
      print "  accurate: #{acc}"
    end
    puts "" if verbose
    epoch_proc.call(epoch) if epoch_proc
  end
end

#train_on_batch(x, y, batch_size, &batch_proc) ⇒ Object 



135
136
137
138
139
140
141
142
143
 
# File 'lib/dnn/core/model.rb', line 135

def train_on_batch(x, y, batch_size, &batch_proc)
  @batch_size = batch_size
  x, y = batch_proc.call(x, y) if batch_proc
  forward(x, true)
  loss = @layers[-1].loss(y)
  backward(y)
  @layers.each { |layer| layer.update if layer.respond_to?(:update) }
  loss
end

#training? ⇒ Boolean

Returns:

  • (Boolean) 


90
91
92
 
# File 'lib/dnn/core/model.rb', line 90

def training?
  @training
end