Class: DNN::Model

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

Instance Attribute Summary collapse

Class Method Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize ⇒ Model

Returns a new instance of Model.



11
12
13
14
15
16
 
# File 'lib/dnn/core/model.rb', line 11

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

Instance Attribute Details

#batch_size ⇒ Object (readonly)

Returns the value of attribute batch_size.



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

def batch_size
  @batch_size
end

#layers ⇒ Object

Returns the value of attribute layers.



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

def layers
  @layers
end

#optimizer ⇒ Object (readonly)

Returns the value of attribute optimizer.



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

def optimizer
  @optimizer
end

Class Method Details

.load(file_name) ⇒ Object 



18
19
20
 
# File 'lib/dnn/core/model.rb', line 18

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

.load_json(json_str) ⇒ Object 



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

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 



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

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 



140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
 
# File 'lib/dnn/core/model.rb', line 140

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 



179
180
181
182
183
184
185
 
# File 'lib/dnn/core/model.rb', line 179

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

#compile(optimizer) ⇒ Object 



71
72
73
74
75
76
77
78
79
80
81
82
 
# File 'lib/dnn/core/model.rb', line 71

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) 


84
85
86
 
# File 'lib/dnn/core/model.rb', line 84

def compiled?
  @compiled
end

#forward(x, training) ⇒ Object 



171
172
173
174
175
176
177
 
# File 'lib/dnn/core/model.rb', line 171

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

#load_json_params(json_str) ⇒ Object 



30
31
32
33
34
35
36
37
38
39
40
41
 
# 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, param|
      layer.params[key] = SFloat.cast(param)
    end
    has_param_layers_index += 1
  end
end

#params_to_json ⇒ Object 



55
56
57
58
59
60
61
 
# File 'lib/dnn/core/model.rb', line 55

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 



167
168
169
 
# File 'lib/dnn/core/model.rb', line 167

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

#save(file_name) ⇒ Object 



43
44
45
46
47
 
# File 'lib/dnn/core/model.rb', line 43

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 



49
50
51
52
53
 
# File 'lib/dnn/core/model.rb', line 49

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 



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

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"
      20.times do |i|
        if i < num_trained_data * 20 / num_train_data
          log << "■"
        else
          log << "・"
        end
      end
      log << "  #{num_trained_data}/#{num_train_data} loss: #{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 



131
132
133
134
135
136
137
138
 
# File 'lib/dnn/core/model.rb', line 131

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)
  backward(y)
  @layers.each { |layer| layer.update if layer.respond_to?(:update) }
  @layers[-1].loss(y)
end

#training? ⇒ Boolean

Returns:

  • (Boolean) 


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

def training?
  @training
end