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.



23
24
25
26
27
28
29
 
# File 'lib/dnn/core/model.rb', line 23

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

Instance Attribute Details

#layers ⇒ Object

All layers possessed by the model



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

def layers
  @layers
end

#trainable ⇒ Object

Setting false prevents learning of parameters.



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

def trainable
  @trainable
end

Class Method Details

.load(file_name) ⇒ Object 



11
12
13
 
# File 'lib/dnn/core/model.rb', line 11

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

.load_json(json_str) ⇒ Object 



15
16
17
18
19
20
21
 
# File 'lib/dnn/core/model.rb', line 15

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 



79
80
81
82
83
84
85
 
# File 'lib/dnn/core/model.rb', line 79

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 = 100, &batch_proc) ⇒ Object 



171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
 
# File 'lib/dnn/core/model.rb', line 171

def accurate(x, y, batch_size = 100, &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 



246
247
248
249
250
251
252
 
# File 'lib/dnn/core/model.rb', line 246

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

#build(super_model = nil) ⇒ Object 



98
99
100
101
102
103
 
# File 'lib/dnn/core/model.rb', line 98

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

#compile(optimizer) ⇒ Object 



87
88
89
90
91
92
93
94
95
96
 
# File 'lib/dnn/core/model.rb', line 87

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) 


109
110
111
 
# File 'lib/dnn/core/model.rb', line 109

def compiled?
  @compiled
end

#copy ⇒ Object 



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

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

#dloss ⇒ Object 



242
243
244
 
# File 'lib/dnn/core/model.rb', line 242

def dloss
  @layers[-1].dloss
end

#forward(x, training) ⇒ Object 



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

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_all_layers ⇒ Object 



220
221
222
223
224
 
# File 'lib/dnn/core/model.rb', line 220

def get_all_layers
  @layers.map { |layer|
    layer.is_a?(Model) ? layer.get_all_layers : layer
  }.flatten
end

#get_layer(*args) ⇒ Object 



210
211
212
213
214
215
216
217
218
 
# File 'lib/dnn/core/model.rb', line 210

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 



260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
 
# File 'lib/dnn/core/model.rb', line 260

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 



31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
 
# File 'lib/dnn/core/model.rb', line 31

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)
      data = Xumo::SFloat.from_binary(bin).reshape(*shape)
      if layer.params[key].is_a?(LearningParam)
        layer.params[key].data = data
      else
        layer.params[key] = data
      end
    end
    has_param_layers_index += 1
  end
end

#loss(y) ⇒ Object 



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

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

#optimizer ⇒ Object 



105
106
107
 
# File 'lib/dnn/core/model.rb', line 105

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

#params_to_json ⇒ Object 



67
68
69
70
71
72
73
74
75
76
77
 
# File 'lib/dnn/core/model.rb', line 67

def params_to_json
  has_param_layers = @layers.select { |layer| layer.is_a?(Layers::HasParamLayer) }
  has_param_layers_params = has_param_layers.map do |layer|
    layer.params.map { |key, param|
      param = param.data if param.is_a?(LearningParam)
      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 



197
198
199
200
 
# File 'lib/dnn/core/model.rb', line 197

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

#predict1(x) ⇒ Object 



202
203
204
 
# File 'lib/dnn/core/model.rb', line 202

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

#save(file_name) ⇒ Object 



50
51
52
53
54
55
56
57
58
59
 
# File 'lib/dnn/core/model.rb', line 50

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 



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

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

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



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
152
153
154
155
156
157
158
 
# File 'lib/dnn/core/model.rb', line 117

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 



160
161
162
163
164
165
166
167
168
169
 
# File 'lib/dnn/core/model.rb', line 160

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)
  dloss
  update
  loss_value
end

#training? ⇒ Boolean

Returns:

  • (Boolean) 


113
114
115
 
# File 'lib/dnn/core/model.rb', line 113

def training?
  @training
end

#update ⇒ Object 



254
255
256
257
258
 
# File 'lib/dnn/core/model.rb', line 254

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