Class: DNN::Model

Inherits:
Object
  • Object
show all
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.



21
22
23
24
25
26
 
# File 'lib/dnn/core/model.rb', line 21

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

Instance Attribute Details

#layers ⇒ Object

Returns the value of attribute layers.



6
7
8
 
# File 'lib/dnn/core/model.rb', line 6

def layers
  @layers
end

#optimizer ⇒ Object (readonly)

Returns the value of attribute optimizer.



7
8
9
 
# File 'lib/dnn/core/model.rb', line 7

def optimizer
  @optimizer
end

Class Method Details

.load(file_name) ⇒ Object 



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

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

.load_json(json_str) ⇒ Object 



13
14
15
16
17
18
19
 
# File 'lib/dnn/core/model.rb', line 13

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 



66
67
68
69
70
71
72
 
# File 'lib/dnn/core/model.rb', line 66

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

#accurate(x, y, batch_size = 1, &batch_proc) ⇒ Object 



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 147

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

#backward(y) ⇒ Object 



191
192
193
194
195
196
197
 
# File 'lib/dnn/core/model.rb', line 191

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

#compile(optimizer) ⇒ Object 



74
75
76
77
78
79
80
81
82
83
84
85
 
# File 'lib/dnn/core/model.rb', line 74

def compile(optimizer)
  unless optimizer.is_a?(Optimizers::Optimizer)
    raise 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) 


87
88
89
 
# File 'lib/dnn/core/model.rb', line 87

def compiled?
  @compiled
end

#forward(x, training) ⇒ Object 



180
181
182
183
184
185
186
187
188
189
 
# File 'lib/dnn/core/model.rb', line 180

def forward(x, training)
  unless compiled?
    raise DNN_Error.new("The model is not compiled.")
  end
  @training = training
  @layers.each do |layer|
    x = layer.forward(x)
  end
  x
end

#load_json_params(json_str) ⇒ Object 



28
29
30
31
32
33
34
35
36
37
38
39
 
# File 'lib/dnn/core/model.rb', line 28

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] = Xumo::SFloat.cast(param)
    end
    has_param_layers_index += 1
  end
end

#params_to_json ⇒ Object 



58
59
60
61
62
63
64
 
# File 'lib/dnn/core/model.rb', line 58

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(Xumo::SFloat.cast([x]))[0, false]
end

#save(file_name) ⇒ Object 



41
42
43
44
45
46
47
48
49
50
 
# File 'lib/dnn/core/model.rb', line 41

def save(file_name)
  marshal = Marshal.dump(self)
  begin
    File.binwrite(file_name, marshal)
  rescue Errno::ENOENT => ex
    dir_name = file_name.match(%r`(.*)/.+$`)[1]
    Dir.mkdir(dir_name)
    File.binwrite(file_name, marshal)
  end
end

#to_json ⇒ Object 



52
53
54
55
56
 
# File 'lib/dnn/core/model.rb', line 52

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 



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
134
135
136
 
# File 'lib/dnn/core/model.rb', line 95

def train(x, y, epochs,
          batch_size: 1,
          test: nil,
          verbose: true,
          batch_proc: nil,
          &epoch_proc)
  unless compiled?
    raise DNN_Error.new("The model is not compiled.")
  end
  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_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_proc) ⇒ Object 



138
139
140
141
142
143
144
145
 
# File 'lib/dnn/core/model.rb', line 138

def train_on_batch(x, y, &batch_proc)
  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) 


91
92
93
 
# File 'lib/dnn/core/model.rb', line 91

def training?
  @training
end