ruby-dnn 0.14.2 → 0.14.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 26d153a8ef243d2a069fd5b48a08e0216c28d8dd0307f570fce2ef146eef3cfe
-  data.tar.gz: 9130ce3f31d2e7b5b3a3ecb48d9e4e10cddd307b2f900e13799206f8b16c3022
+  metadata.gz: 9e4633ce695dc370e62c6653d5ff07d81f9306625f7165750f8e455c4a28ca61
+  data.tar.gz: e4275720191b14592e2fb93581e9826e437ce9fcc75f6473cb963892d8f9f893
 SHA512:
-  metadata.gz: f6167f81c1c7c76ae0539d17e9f9d252f03b603a15ee376cf91d0aa620d8d60aa5f434d3587f3331221679f661d22978207564d60a7ae59cf22551c482beb62c
-  data.tar.gz: 0ab323a64dd7d68692c901257fa38981355c6533eb106a76ed1f4072c4d338bb4c5c72b0a4db2704c146ae49b827c75f45b79db924cdde92352f72f332bd7c9c
+  metadata.gz: d9831b1b3a73423742bce7f989a13c7ac3d63426a2bd8366143be1717a1e90fbdf6aa79a9e90508e193e00fbcd120942b7ccd0c8b6b13eb9cc4e237471712030
+  data.tar.gz: 60344f9eb3645b0560dd9d1f63a86dcc554f7c9b923a3b84a0bc301264120d50ca034d2887c1cc41989f223891ace4d64c570c9935e2b3f6f467a05f0fab910f

data/README.md

@@ -55,7 +55,7 @@ class MLP < Model
   end
 
   def call(x)
-    x = InputLayer.(x)
+    x = InputLayer.new(784).(x)
     x = @l1.(x)
     x = ReLU.(x)
     x = @l2.(x)

data/examples/dcgan/dcgan.rb

@@ -121,6 +121,6 @@ class DCGAN < Model
     label = Numo::SFloat.cast([1] * batch_size).reshape(batch_size, 1)
     dcgan_loss = train_on_batch(noise, label)
 
-    { dis_loss: dis_loss.mean, dcgan_loss: dcgan_loss.mean }
+    { dis_loss: dis_loss, dcgan_loss: dcgan_loss }
   end
 end

data/examples/dcgan/train.rb

@@ -19,11 +19,12 @@ dcgan = DCGAN.new(gen, dis)
 
 dis.setup(Adam.new(alpha: 0.00001, beta1: 0.1), SigmoidCrossEntropy.new)
 dcgan.setup(Adam.new(alpha: 0.0002, beta1: 0.5), SigmoidCrossEntropy.new)
+dcgan.add_callback(CheckPoint.new("trained/dcgan_model"))
+dcgan.predict1(Numo::SFloat.zeros(20))
 
 x_train, * = MNIST.load_train
 x_train = Numo::SFloat.cast(x_train)
 x_train = x_train / 127.5 - 1
 
-dcgan.add_callback(CheckPoint.new("trained/dcgan_model"))
-dcgan.predict1(Numo::SFloat.zeros(20))
-dcgan.train(x_train, x_train, epochs, batch_size: batch_size, last_round_down: true)
+iter = DNN::Iterator.new(x_train, x_train, last_round_down: true)
+dcgan.fit_by_iterator(iter, epochs, batch_size: batch_size)

data/examples/mnist_define_by_run.rb

@@ -32,7 +32,7 @@ class MLP < Model
   end
 
   def call(x)
-    x = InputLayer.(x)
+    x = InputLayer.new(784).(x)
     x = @l1.(x)
     x = @bn1.(x)
     x = ReLU.(x)

data/lib/dnn/core/cnn_layers.rb

@@ -385,6 +385,29 @@ module DNN
       end
     end
 
+    class GlobalAvgPool2D < Layer
+      def build(input_shape)
+        unless input_shape.length == 3
+          raise DNN_ShapeError, "Input shape is #{input_shape}. But input shape must be 3 dimensional."
+        end
+        super
+        @avg_pool2d = AvgPool2D.new(input_shape[0..1])
+        @avg_pool2d.build(input_shape)
+        @flatten = Flatten.new
+        @flatten.build([1, 1, input_shape[2]])
+      end
+
+      def forward(x)
+        y = @avg_pool2d.forward(x)
+        @flatten.forward(y)
+      end
+
+      def backward(dy)
+        dy = @flatten.backward(dy)
+        @avg_pool2d.backward(dy)
+      end
+    end
+
     class UnPool2D < Layer
       include Conv2DUtils
 

data/lib/dnn/core/models.rb

@@ -370,13 +370,19 @@ module DNN
       # @param [Array] stack All layers possessed by the model.
       def initialize(stack = [])
         super()
-        @stack = stack.clone
+        @stack = []
+        stack.each do |layer|
+          add(layer)
+        end
       end
 
       # Add layer to the model.
       # @param [DNN::Layers::Layer] layer Layer to add to the model.
       # @return [DNN::Models::Model] Return self.
       def add(layer)
+        if layer.is_a?(MergeLayers::MergeLayer)
+          raise TypeError, "layer: #{layer.class.name} should not be a DNN::MergeLayers::MergeLayer class."
+        end
         unless layer.is_a?(Layers::Layer) || layer.is_a?(Model)
           raise TypeError, "layer: #{layer.class.name} is not an instance of the DNN::Layers::Layer class or DNN::Models::Model class."
         end
@@ -386,13 +392,23 @@ module DNN
 
       alias << add
 
+      # Insert layer to the model by index position.
+      # @param [DNN::Layers::Layer] layer Layer to add to the model.
+      # @return [DNN::Models::Model] Return self.
+      def insert(index, layer)
+        if layer.is_a?(MergeLayers::MergeLayer)
+          raise TypeError, "layer: #{layer.class.name} should not be a DNN::MergeLayers::MergeLayer class."
+        end
+        unless layer.is_a?(Layers::Layer) || layer.is_a?(Model)
+          raise TypeError, "layer: #{layer.class.name} is not an instance of the DNN::Layers::Layer class or DNN::Models::Model class."
+        end
+        @stack.insert(index, layer)
+      end
+
       # Remove layer to the model.
       # @param [DNN::Layers::Layer] layer Layer to remove to the model.
       # @return [Boolean] Return true if success for remove layer.
       def remove(layer)
-        unless layer.is_a?(Layers::Layer) || layer.is_a?(Model)
-          raise TypeError, "layer: #{layer.class.name} is not an instance of the DNN::Layers::Layer class or DNN::Models::Model class."
-        end
         @stack.delete(layer) ? true : false
       end
 

data/lib/dnn/version.rb

@@ -1,3 +1,3 @@
 module DNN
-  VERSION = "0.14.2"
+  VERSION = "0.14.3"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: ruby-dnn
 version: !ruby/object:Gem::Version
-  version: 0.14.2
+  version: 0.14.3
 platform: ruby
 authors:
 - unagiootoro
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2019-10-26 00:00:00.000000000 Z
+date: 2019-11-03 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: numo-narray
@@ -170,7 +170,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.0.1
+rubygems_version: 3.0.3
 signing_key: 
 specification_version: 4
 summary: ruby deep learning library.