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
27
 
# File 'lib/dnn/core/model.rb', line 21

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

Instance Attribute Details

#layers ⇒ Object

All layers possessed by the model



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

def layers
  @layers
end

#trainable ⇒ Object

Setting false prevents learning of parameters.



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

def trainable
  @trainable
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 



67
68
69
70
71
72
73
 
# File 'lib/dnn/core/model.rb', line 67

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

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



157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
 
# File 'lib/dnn/core/model.rb', line 157

def accurate(x, y, batch_size = 1, &batch_proc)
  batch_size = batch_size >= x.shape[0] ? x.shape[0] : batch_size
  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 



210
211
212
213
214
215
216
 
# File 'lib/dnn/core/model.rb', line 210

def backward(y)
  dout = y
  @layers.reverse.each do |layer|
    dout = layer.backward(dout)
  end
  dout
end

#build(super_model = nil) ⇒ Object 



86
87
88
89
90
91
 
# File 'lib/dnn/core/model.rb', line 86

def build(super_model = nil)
  @super_model = super_model
  @layers.each do |layer|
    layer.build(self)
  end
end

#compile(optimizer) ⇒ Object 



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

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
  build
  layers_shape_check
end

#compiled? ⇒ Boolean

Returns:

  • (Boolean) 


97
98
99
 
# File 'lib/dnn/core/model.rb', line 97

def compiled?
  @compiled
end

#copy ⇒ Object 



190
191
192
 
# File 'lib/dnn/core/model.rb', line 190

def copy
  Marshal.load(Marshal.dump(self))
end

#forward(x, training) ⇒ Object 



194
195
196
197
198
199
200
201
202
203
204
 
# File 'lib/dnn/core/model.rb', line 194

def forward(x, training)
  @training = training
  @layers.each do |layer|
    x = if layer.is_a?(Layers::Layer)
      layer.forward(x)
    elsif layer.is_a?(Model)
      layer.forward(x, training)
    end
  end
  x
end

#get_prev_layer(layer) ⇒ Object 



224
225
226
227
228
229
230
231
232
233
234
235
236
 
# File 'lib/dnn/core/model.rb', line 224

def get_prev_layer(layer)
  layer_index = @layers.index(layer)
  prev_layer = if layer_index == 0
    @super_model.layers[@super_model.layers.index(self) - 1]
  else
    @layers[layer_index - 1]
  end
  if prev_layer.is_a?(Layers::Layer)
    prev_layer
  elsif prev_layer.is_a?(Model)
    prev_layer.layers[-1]
  end
end

#load_json_params(json_str) ⇒ Object 



29
30
31
32
33
34
35
36
37
38
39
40
 
# File 'lib/dnn/core/model.rb', line 29

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

#loss(y) ⇒ Object 



206
207
208
 
# File 'lib/dnn/core/model.rb', line 206

def loss(y)
  @layers[-1].loss(y)
end

#optimizer ⇒ Object 



93
94
95
 
# File 'lib/dnn/core/model.rb', line 93

def optimizer
  @optimizer ? @optimizer : @super_model.optimizer
end

#params_to_json ⇒ Object 



59
60
61
62
63
64
65
 
# File 'lib/dnn/core/model.rb', line 59

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 



182
183
184
 
# File 'lib/dnn/core/model.rb', line 182

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

#predict1(x) ⇒ Object 



186
187
188
 
# File 'lib/dnn/core/model.rb', line 186

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

#save(file_name) ⇒ Object 



42
43
44
45
46
47
48
49
50
51
 
# File 'lib/dnn/core/model.rb', line 42

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 



53
54
55
56
57
 
# File 'lib/dnn/core/model.rb', line 53

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 



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
137
138
139
140
141
142
143
144
145
146
 
# File 'lib/dnn/core/model.rb', line 105

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 



148
149
150
151
152
153
154
155
 
# File 'lib/dnn/core/model.rb', line 148

def train_on_batch(x, y, &batch_proc)
  x, y = batch_proc.call(x, y) if batch_proc
  forward(x, true)
  loss_value = loss(y)
  backward(y)
  update
  loss_value
end

#training? ⇒ Boolean

Returns:

  • (Boolean) 


101
102
103
 
# File 'lib/dnn/core/model.rb', line 101

def training?
  @training
end

#update ⇒ Object 



218
219
220
221
222
 
# File 'lib/dnn/core/model.rb', line 218

def update
  @layers.each do |layer|
    layer.update if @trainable && (layer.is_a?(Layers::HasParamLayer) || layer.is_a?(Model))
  end
end