ruby-dnn 1.2.0 → 1.2.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: d152e645981ddb8f244abc88719c4c68a154679fa18abf6b02fa8852510e0c27
-  data.tar.gz: 2987a4ce59a8f7d60a160ac192125ab97a4e14735ae29e151d23412a22f3c13b
+  metadata.gz: 8475052a51f8b81f176c8b3a77c953d116fb1098b7f24fe8a2ad9135b2f2a33b
+  data.tar.gz: f291c99be16b9a35fee59a09cefda3b9aece1bbaef5d6b482fad6d238043e68b
 SHA512:
-  metadata.gz: 13e9cb2995d1d2851850931a0aedb01ca4fb71b6b03fa81a0ac9e78176b8ed4f520ac6284a39e9c71aaf2629c55475eac33987e6f49535bfe27153729f37624c
-  data.tar.gz: a492f778d4094fce114149841a54e2b0d8a4eff77778b8074198c8df009916598cb96bfd67494c88520e10fd99618591862854773a1f20baf00247fe2bb1f1ea
+  metadata.gz: '08f061510f73297b12b53cd3da5748dd47e67605d1b40c35388779a94e023e37450d2c9ebd9ec1bf0970c1580c7481f46c6cef05d54af5748fe175522b198c5e'
+  data.tar.gz: fdfe99ac9b5a63e4914aaab4f71a37e56b097c6b00560245a82438c6fd70ab658683de95c1ddef0283f4cc2f0b9e261dda798158cd374cf19cc17966ed338b16

data/examples/judge-number/mnist_predict.rb

@@ -12,7 +12,7 @@ end
 def mnist_predict(img, width, height)
   load_model
   img = DNN::Image.from_binary(img, height, width, DNN::Image::RGBA)
-  img = img[true, true, 0...DNN::Image::RGB]
+  img = DNN::Image.to_rgb(img)
   img = DNN::Image.to_gray_scale(img)
   x = Numo::SFloat.cast(img) / 255
   out = $model.predict1(x)

data/examples/pix2pix/dcgan.rb

@@ -70,77 +70,6 @@ class Generator < Model
   end
 end
 
-class Discriminator < Model
-  def initialize(gen_input_shape, gen_output_shape)
-    super()
-    @gen_input_shape = gen_input_shape
-    @gen_output_shape = gen_output_shape
-    @l1_1 = Conv2D.new(32, 4, padding: true)
-    @l1_2 = Conv2D.new(32, 4, padding: true)
-    @l2 = Conv2D.new(32, 4, strides: 2, padding: true)
-    @l3 = Conv2D.new(32, 4, padding: true)
-    @l4 = Conv2D.new(64, 4, strides: 2, padding: true)
-    @l5 = Conv2D.new(64, 4, padding: true)
-    @l6 = Dense.new(1024)
-    @l7 = Dense.new(1)
-    @bn1 = BatchNormalization.new
-    @bn2 = BatchNormalization.new
-    @bn3 = BatchNormalization.new
-    @bn4 = BatchNormalization.new
-    @bn5 = BatchNormalization.new
-    @bn6 = BatchNormalization.new
-  end
-
-  def forward(inputs)
-    input, images = *inputs
-    x = InputLayer.new(@gen_input_shape).(input)
-    x = @l1_1.(x)
-    x = @bn1.(x)
-    x1 = LeakyReLU.(x, 0.2)
-
-    x = InputLayer.new(@gen_output_shape).(images)
-    x = @l1_2.(x)
-    x = @bn2.(x)
-    x2 = LeakyReLU.(x, 0.2)
-
-    x = Concatenate.(x1, x2)
-    x = @l2.(x)
-    x = @bn3.(x)
-    x = LeakyReLU.(x, 0.2)
-
-    x = @l3.(x)
-    x = @bn4.(x)
-    x = LeakyReLU.(x, 0.2)
-
-    x = @l4.(x)
-    x = @bn5.(x)
-    x = LeakyReLU.(x, 0.2)
-
-    x = @l5.(x)
-    x = @bn6.(x)
-    x = LeakyReLU.(x, 0.2)
-
-    x = Flatten.(x)
-    x = @l6.(x)
-    x = LeakyReLU.(x, 0.2)
-
-    x = @l7.(x)
-    x
-  end
-
-  def enable_training
-    trainable_layers.each do |layer|
-      layer.trainable = true
-    end
-  end
-  
-  def disable_training
-    trainable_layers.each do |layer|
-      layer.trainable = false
-    end
-  end
-end
-
 class Discriminator < Model
   def initialize(gen_input_shape, gen_output_shape, base_num_filters)
     super()

data/lib/dnn/core/layers/basic_layers.rb

@@ -436,8 +436,8 @@ module DNN
       def forward_node(x)
         if DNN.learning_phase
           Xumo::SFloat.srand(@rnd.rand(1 << 31))
-          @mask = Xumo::SFloat.new(*x.shape).rand < @dropout_ratio
-          x[@mask] = 0
+          @mask = Xumo::SFloat.cast(Xumo::SFloat.new(*x.shape).rand >= @dropout_ratio)
+          x = x * @mask
         elsif @use_scale
           x *= (1 - @dropout_ratio)
         end
@@ -445,8 +445,7 @@ module DNN
       end
 
       def backward_node(dy)
-        dy[@mask] = 0
-        dy
+        dy * @mask
       end
 
       def to_hash

data/lib/dnn/image.rb

@@ -114,6 +114,41 @@ module DNN
       Numo::UInt8.cast(x)
     end
 
+    # Image convert image channel to RGB.
+    # @param [Numo::UInt8] img Image to RGB.
+    def self.to_rgb(img)
+      img_check(img)
+      case img.shape[2]
+      when 1
+        return img.concatenate(img, axis: 2).concatenate(img, axis: 2)
+      when 2
+        img = img[true, true, 0...1]
+        return img.concatenate(img, axis: 2).concatenate(img, axis: 2)
+      when 4
+        return img[true, true, 0...3].clone
+      end
+      img
+    end
+
+    # Image convert image channel to RGBA.
+    # @param [Numo::UInt8] img Image to RGBA.
+    def self.to_rgba(img)
+      img_check(img)
+      case img.shape[2]
+      when 1
+        alpha = Numo::UInt8.new(*img.shape[0..1], 1).fill(255)
+        return img.concatenate(img, axis: 2).concatenate(img, axis: 2).concatenate(alpha, axis: 2)
+      when 2
+        alpha = img[true, true, 1...2]
+        img = img[true, true, 0...1]
+        return img.concatenate(img, axis: 2).concatenate(img, axis: 2).concatenate(alpha, axis: 2)
+      when 3
+        alpha = Numo::UInt8.new(*img.shape[0..1], 1).fill(255)
+        return img.concatenate(alpha, axis: 2)
+      end
+      img
+    end
+
     private_class_method def self.img_check(img)
       raise TypeError, "img: #{img.class} is not an instance of the Numo::UInt8 class." unless img.is_a?(Numo::UInt8)
       if img.shape.length != 3

data/lib/dnn/version.rb

@@ -1,3 +1,3 @@
 module DNN
-  VERSION = "1.2.0"
+  VERSION = "1.2.1"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: ruby-dnn
 version: !ruby/object:Gem::Version
-  version: 1.2.0
+  version: 1.2.1
 platform: ruby
 authors:
 - unagiootoro
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2020-05-16 00:00:00.000000000 Z
+date: 2020-05-24 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: numo-narray