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.



22
23
24
25
26
27
28
 
# File 'lib/dnn/core/model.rb', line 22

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

Instance Attribute Details

#layers ⇒ Object

All layers possessed by the model



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

def layers
  @layers
end

#trainable ⇒ Object

Setting false prevents learning of parameters.



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

def trainable
  @trainable
end

Class Method Details

.load(file_name) ⇒ Object 



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

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

.load_json(json_str) ⇒ Object 



14
15
16
17
18
19
20
 
# File 'lib/dnn/core/model.rb', line 14

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 



72
73
74
75
76
77
78
 
# File 'lib/dnn/core/model.rb', line 72

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 



163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
 
# File 'lib/dnn/core/model.rb', line 163

def accurate(x, y, batch_size = 1, &batch_proc)
  input_data_shape_check(x, y)
  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 



228
229
230
231
232
233
234
 
# File 'lib/dnn/core/model.rb', line 228

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

#build(super_model = nil) ⇒ Object 



91
92
93
94
95
96
 
# File 'lib/dnn/core/model.rb', line 91

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

#compile(optimizer) ⇒ Object 



80
81
82
83
84
85
86
87
88
89
 
# File 'lib/dnn/core/model.rb', line 80

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) 


102
103
104
 
# File 'lib/dnn/core/model.rb', line 102

def compiled?
  @compiled
end

#copy ⇒ Object 



198
199
200
 
# File 'lib/dnn/core/model.rb', line 198

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

#forward(x, training) ⇒ Object 



212
213
214
215
216
217
218
219
220
221
222
 
# File 'lib/dnn/core/model.rb', line 212

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_layer(*args) ⇒ Object 



202
203
204
205
206
207
208
209
210
 
# File 'lib/dnn/core/model.rb', line 202

def get_layer(*args)
  if args.length == 1
    index = args[0]
    @layers[index]
  else
    layer_class, index = args
    @layers.select { |layer| layer.is_a?(layer_class) }[index]
  end
end

#get_prev_layer(layer) ⇒ Object 



242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
 
# File 'lib/dnn/core/model.rb', line 242

def get_prev_layer(layer)
  layer_index = @layers.index(layer)
  prev_layer = if layer_index == 0
    if @super_model
      @super_model.layers[@super_model.layers.index(self) - 1]
    else
      self
    end
  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 



30
31
32
33
34
35
36
37
38
39
40
41
42
 
# File 'lib/dnn/core/model.rb', line 30

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, (shape, base64_param)|
      bin = Base64.decode64(base64_param)
      layer.params[key] = Xumo::SFloat.from_binary(bin).reshape(*shape)
    end
    has_param_layers_index += 1
  end
end

#loss(y) ⇒ Object 



224
225
226
 
# File 'lib/dnn/core/model.rb', line 224

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

#optimizer ⇒ Object 



98
99
100
 
# File 'lib/dnn/core/model.rb', line 98

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

#params_to_json ⇒ Object 



61
62
63
64
65
66
67
68
69
70
 
# File 'lib/dnn/core/model.rb', line 61

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|
      base64_param = Base64.encode64(param.to_binary)
      [key, [param.shape, base64_param]]
    }.to_h
  end
  JSON.dump(has_param_layers_params)
end

#predict(x) ⇒ Object 



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

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

#predict1(x) ⇒ Object 



194
195
196
 
# File 'lib/dnn/core/model.rb', line 194

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

#save(file_name) ⇒ Object 



44
45
46
47
48
49
50
51
52
53
 
# File 'lib/dnn/core/model.rb', line 44

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 



55
56
57
58
59
 
# File 'lib/dnn/core/model.rb', line 55

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 



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
147
148
149
150
151
 
# File 'lib/dnn/core/model.rb', line 110

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 



153
154
155
156
157
158
159
160
161
 
# File 'lib/dnn/core/model.rb', line 153

def train_on_batch(x, y, &batch_proc)
  input_data_shape_check(x, y)
  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) 


106
107
108
 
# File 'lib/dnn/core/model.rb', line 106

def training?
  @training
end

#update ⇒ Object 



236
237
238
239
240
 
# File 'lib/dnn/core/model.rb', line 236

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