torchvision 0.1.2 → 0.1.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 107e429f990a063e57f6218ee6d4fbed3cff80aa6746f0794798d59e1c13b099
-  data.tar.gz: 556fdc4c413803d415ea5575747ec2239f18b0dff9b39a37a4fd6366adec37a6
+  metadata.gz: 44c29605f12dddf8196432223f2137ef9b9bef490996b718f5a9bdbc13dbd33f
+  data.tar.gz: 8790200a0ed8f7a275f99327431dc8be99a7578c473ec03411f9411cd10c6c93
 SHA512:
-  metadata.gz: 21b712578516c146888be30bed64a6da6339a42974f5c88fa685278caa9231e4bc4b75e250af3ad37d5450cd205891b31b281cf23fa362456c7ae00998c2736d
-  data.tar.gz: ac86f13e8b5d6a400842ba37b1bf593139360a8df9a19ab4674e71a4327c821a6d5735774185dcbaed368ee735b00bf33d9faedb13d46cd168314da89d900c38
+  metadata.gz: 65816ef10f524781553327f9634bb8818a7efa6fb072e81468949d937b5430dcddc7f6c8cf3b305c977dc4b1279d23b38fb034a4c277eecc1adcc0f2b8c99e3e
+  data.tar.gz: 01f485a78cd5a19c9a0dc987f4e46931b033ffb3a84af703b602b0e90e8c221c99b5e6318c86b18361562cc3ca582b3a0822de151a5edf63964002317a684bfa

data/CHANGELOG.md

@@ -1,3 +1,11 @@
+## 0.1.3 (2020-06-29)
+
+- Added AlexNet model
+- Added ResNet34, ResNet50, ResNet101, and ResNet152 models
+- Added ResNeXt model
+- Added VGG11, VGG13, VGG16, and VGG19 models
+- Added Wide ResNet model
+
 ## 0.1.2 (2020-04-29)
 
 - Added CIFAR10, CIFAR100, FashionMNIST, and KMNIST datasets

data/README.md

@@ -45,8 +45,53 @@ TorchVision::Transforms::Compose.new([
 
 ## Models
 
+- [AlexNet](#alexnet)
+- [ResNet](#resnet)
+- [ResNeXt](#resnext)
+- [VGG](#vgg)
+- [Wide ResNet](#wide-resnet)
+
+### AlexNet
+
+```ruby
+TorchVision::Models::AlexNet.new
+```
+
+### ResNet
+
+```ruby
+TorchVision::Models::ResNet18.new
+TorchVision::Models::ResNet34.new
+TorchVision::Models::ResNet50.new
+TorchVision::Models::ResNet101.new
+TorchVision::Models::ResNet152.new
+```
+
+### ResNeXt
+
+```ruby
+TorchVision::Models::ResNext52_32x4d.new
+TorchVision::Models::ResNext101_32x8d.new
+```
+
+### VGG
+
+```ruby
+TorchVision::Models::VGG11.new
+TorchVision::Models::VGG11BN.new
+TorchVision::Models::VGG13.new
+TorchVision::Models::VGG13BN.new
+TorchVision::Models::VGG16.new
+TorchVision::Models::VGG16BN.new
+TorchVision::Models::VGG19.new
+TorchVision::Models::VGG19BN.new
+```
+
+### Wide ResNet
+
 ```ruby
-TorchVision::Models::Resnet18.new
+TorchVision::Models::WideResNet52_2.new
+TorchVision::Models::WideResNet101_2.new
 ```
 
 ## Disclaimer

data/lib/torchvision.rb

@@ -21,10 +21,28 @@ require "torchvision/datasets/fashion_mnist"
 require "torchvision/datasets/kmnist"
 
 # models
+require "torchvision/models/alexnet"
 require "torchvision/models/basic_block"
 require "torchvision/models/bottleneck"
 require "torchvision/models/resnet"
 require "torchvision/models/resnet18"
+require "torchvision/models/resnet34"
+require "torchvision/models/resnet50"
+require "torchvision/models/resnet101"
+require "torchvision/models/resnet152"
+require "torchvision/models/resnext50_32x4d"
+require "torchvision/models/resnext101_32x8d"
+require "torchvision/models/vgg"
+require "torchvision/models/vgg11"
+require "torchvision/models/vgg11_bn"
+require "torchvision/models/vgg13"
+require "torchvision/models/vgg13_bn"
+require "torchvision/models/vgg16"
+require "torchvision/models/vgg16_bn"
+require "torchvision/models/vgg19"
+require "torchvision/models/vgg19_bn"
+require "torchvision/models/wide_resnet50_2"
+require "torchvision/models/wide_resnet101_2"
 
 # transforms
 require "torchvision/transforms/compose"

data/lib/torchvision/models/alexnet.rb

@@ -0,0 +1,42 @@
+module TorchVision
+  module Models
+    class AlexNet < Torch::NN::Module
+      def initialize(num_classes: 1000)
+        super()
+        @features = Torch::NN::Sequential.new(
+          Torch::NN::Conv2d.new(3, 64, 11, stride: 4, padding: 2),
+          Torch::NN::ReLU.new(inplace: true),
+          Torch::NN::MaxPool2d.new(3, stride: 2),
+          Torch::NN::Conv2d.new(64, 192, 5, padding: 2),
+          Torch::NN::ReLU.new(inplace: true),
+          Torch::NN::MaxPool2d.new(3, stride: 2),
+          Torch::NN::Conv2d.new(192, 384, 3, padding: 1),
+          Torch::NN::ReLU.new(inplace: true),
+          Torch::NN::Conv2d.new(384, 256, 3, padding: 1),
+          Torch::NN::ReLU.new(inplace: true),
+          Torch::NN::Conv2d.new(256, 256, 3, padding: 1),
+          Torch::NN::ReLU.new(inplace: true),
+          Torch::NN::MaxPool2d.new(3, stride: 2),
+        )
+        @avgpool = Torch::NN::AdaptiveAvgPool2d.new([6, 6])
+        @classifier = Torch::NN::Sequential.new(
+          Torch::NN::Dropout.new,
+          Torch::NN::Linear.new(256 * 6 * 6, 4096),
+          Torch::NN::ReLU.new(inplace: true),
+          Torch::NN::Dropout.new,
+          Torch::NN::Linear.new(4096, 4096),
+          Torch::NN::ReLU.new(inplace: true),
+          Torch::NN::Linear.new(4096, num_classes)
+        )
+      end
+
+      def forward(x)
+        x = @features.call(x)
+        x = @avgpool.call(x)
+        x = Torch.flatten(x, 1)
+        x = @classifier.call(x)
+        x
+      end
+    end
+  end
+end

data/lib/torchvision/models/resnet.rb

@@ -1,6 +1,18 @@
 module TorchVision
   module Models
     class ResNet < Torch::NN::Module
+      MODEL_URLS = {
+        "resnet18" => "https://download.pytorch.org/models/resnet18-5c106cde.pth",
+        "resnet34" => "https://download.pytorch.org/models/resnet34-333f7ec4.pth",
+        "resnet50" => "https://download.pytorch.org/models/resnet50-19c8e357.pth",
+        "resnet101" => "https://download.pytorch.org/models/resnet101-5d3b4d8f.pth",
+        "resnet152" => "https://download.pytorch.org/models/resnet152-b121ed2d.pth",
+        "resnext50_32x4d" => "https://download.pytorch.org/models/resnext50_32x4d-7cdf4587.pth",
+        "resnext101_32x8d" => "https://download.pytorch.org/models/resnext101_32x8d-8ba56ff5.pth",
+        "wide_resnet50_2" => "https://download.pytorch.org/models/wide_resnet50_2-95faca4d.pth",
+        "wide_resnet101_2" => "https://download.pytorch.org/models/wide_resnet101_2-32ee1156.pth"
+      }
+
       def initialize(block, layers, num_classes=1000, zero_init_residual: false,
         groups: 1, width_per_group: 64, replace_stride_with_dilation: nil, norm_layer: nil)
 
@@ -102,6 +114,16 @@ module TorchVision
       def forward(x)
         _forward_impl(x)
       end
+
+      def self.make_model(arch, block, layers, pretrained: false, **kwargs)
+        model = ResNet.new(block, layers, **kwargs)
+        if pretrained
+          url = MODEL_URLS[arch]
+          state_dict = Torch::Hub.load_state_dict_from_url(url)
+          model.load_state_dict(state_dict)
+        end
+        model
+      end
     end
   end
 end

data/lib/torchvision/models/resnet101.rb

@@ -0,0 +1,9 @@
+module TorchVision
+  module Models
+    module ResNet101
+      def self.new(**kwargs)
+        ResNet.make_model("resnet101", Bottleneck, [3, 4, 23, 3], **kwargs)
+      end
+    end
+  end
+end

data/lib/torchvision/models/resnet152.rb

@@ -0,0 +1,9 @@
+module TorchVision
+  module Models
+    module ResNet152
+      def self.new(**kwargs)
+        ResNet.make_model("resnet152", Bottleneck, [3, 8, 36, 3], **kwargs)
+      end
+    end
+  end
+end

data/lib/torchvision/models/resnet18.rb

@@ -1,14 +1,8 @@
 module TorchVision
   module Models
     module ResNet18
-      def self.new(pretrained: false, **kwargs)
-        model = ResNet.new(BasicBlock, [2, 2, 2, 2], **kwargs)
-        if pretrained
-          url = "https://download.pytorch.org/models/resnet18-5c106cde.pth"
-          state_dict = Torch::Hub.load_state_dict_from_url(url)
-          model.load_state_dict(state_dict)
-        end
-        model
+      def self.new(**kwargs)
+        ResNet.make_model("resnet18", BasicBlock, [2, 2, 2, 2], **kwargs)
       end
     end
   end

data/lib/torchvision/models/resnet34.rb

@@ -0,0 +1,9 @@
+module TorchVision
+  module Models
+    module ResNet34
+      def self.new(**kwargs)
+        ResNet.make_model("resnet34", BasicBlock, [3, 4, 6, 3], **kwargs)
+      end
+    end
+  end
+end

data/lib/torchvision/models/resnet50.rb

@@ -0,0 +1,9 @@
+module TorchVision
+  module Models
+    module ResNet50
+      def self.new(**kwargs)
+        ResNet.make_model("resnet50", Bottleneck, [3, 4, 6, 3], **kwargs)
+      end
+    end
+  end
+end

data/lib/torchvision/models/resnext101_32x8d.rb

@@ -0,0 +1,11 @@
+module TorchVision
+  module Models
+    module ResNext101_32x8d
+      def self.new(**kwargs)
+        kwargs[:groups] = 32
+        kwargs[:width_per_group] = 8
+        ResNet.make_model("resnext101_32x8d", Bottleneck, [3, 4, 23, 3], **kwargs)
+      end
+    end
+  end
+end

data/lib/torchvision/models/resnext50_32x4d.rb

@@ -0,0 +1,11 @@
+module TorchVision
+  module Models
+    module ResNext50_32x4d
+      def self.new(**kwargs)
+        kwargs[:groups] = 32
+        kwargs[:width_per_group] = 4
+        ResNet.make_model("resnext50_32x4d", Bottleneck, [3, 4, 6, 3], **kwargs)
+      end
+    end
+  end
+end

data/lib/torchvision/models/vgg.rb

@@ -0,0 +1,93 @@
+module TorchVision
+  module Models
+    class VGG < Torch::NN::Module
+      MODEL_URLS = {
+        "vgg11" => "https://download.pytorch.org/models/vgg11-bbd30ac9.pth",
+        "vgg13" => "https://download.pytorch.org/models/vgg13-c768596a.pth",
+        "vgg16" => "https://download.pytorch.org/models/vgg16-397923af.pth",
+        "vgg19" => "https://download.pytorch.org/models/vgg19-dcbb9e9d.pth",
+        "vgg11_bn" => "https://download.pytorch.org/models/vgg11_bn-6002323d.pth",
+        "vgg13_bn" => "https://download.pytorch.org/models/vgg13_bn-abd245e5.pth",
+        "vgg16_bn" => "https://download.pytorch.org/models/vgg16_bn-6c64b313.pth",
+        "vgg19_bn" => "https://download.pytorch.org/models/vgg19_bn-c79401a0.pth"
+      }
+
+      def initialize(features, num_classes: 1000, init_weights: true)
+        super()
+        @features = features
+        @avgpool = Torch::NN::AdaptiveAvgPool2d.new([7, 7])
+        @classifier = Torch::NN::Sequential.new(
+          Torch::NN::Linear.new(512 * 7 * 7, 4096),
+          Torch::NN::ReLU.new(inplace: true),
+          Torch::NN::Dropout.new,
+          Torch::NN::Linear.new(4096, 4096),
+          Torch::NN::ReLU.new(inplace: true),
+          Torch::NN::Dropout.new,
+          Torch::NN::Linear.new(4096, num_classes)
+        )
+        _initialize_weights if init_weights
+      end
+
+      def forward(x)
+        x = @features.call(x)
+        x = @avgpool.call(x)
+        x = Torch.flatten(x, 1)
+        x = @classifier.call(x)
+        x
+      end
+
+      def _initialize_weights
+        modules.each do |m|
+          case m
+          when Torch::NN::Conv2d
+            Torch::NN::Init.kaiming_normal!(m.weight, mode: "fan_out", nonlinearity: "relu")
+            Torch::NN::Init.constant!(m.bias, 0) if m.bias
+          when Torch::NN::BatchNorm2d
+            Torch::NN::Init.constant!(m.weight, 1)
+            Torch::NN::Init.constant!(m.bias, 0)
+          when Torch::NN::Linear
+            Torch::NN::Init.normal!(m.weight, mean: 0, std: 0.01)
+            Torch::NN::Init.constant!(m.bias, 0)
+          end
+        end
+      end
+
+      CFGS = {
+        "A" => [64, "M", 128, "M", 256, 256, "M", 512, 512, "M", 512, 512, "M"],
+        "B" => [64, 64, "M", 128, 128, "M", 256, 256, "M", 512, 512, "M", 512, 512, "M"],
+        "D" => [64, 64, "M", 128, 128, "M", 256, 256, 256, "M", 512, 512, 512, "M", 512, 512, 512, "M"],
+        "E" => [64, 64, "M", 128, 128, "M", 256, 256, 256, 256, "M", 512, 512, 512, 512, "M", 512, 512, 512, 512, "M"],
+      }
+
+      def self.make_model(arch, cfg, batch_norm, pretrained: false, **kwargs)
+        kwargs[:init_weights] = false if pretrained
+        model = VGG.new(make_layers(CFGS[cfg], batch_norm), **kwargs)
+        if pretrained
+          url = MODEL_URLS[arch]
+          state_dict = Torch::Hub.load_state_dict_from_url(url)
+          model.load_state_dict(state_dict)
+        end
+        model
+      end
+
+      def self.make_layers(cfg, batch_norm)
+        layers = []
+        in_channels = 3
+        cfg.each do |v|
+          if v == "M"
+            layers += [Torch::NN::MaxPool2d.new(2, stride: 2)]
+          else
+            conv2d = Torch::NN::Conv2d.new(in_channels, v, 3, padding: 1)
+            if batch_norm
+              layers += [conv2d, Torch::NN::BatchNorm2d.new(v), Torch::NN::ReLU.new(inplace: true)]
+            else
+              layers += [conv2d, Torch::NN::ReLU.new(inplace: true)]
+            end
+            in_channels = v
+          end
+        end
+        Torch::NN::Sequential.new(*layers)
+      end
+    end
+  end
+end

data/lib/torchvision/models/vgg11.rb

@@ -0,0 +1,9 @@
+module TorchVision
+  module Models
+    module VGG11
+      def self.new(**kwargs)
+        VGG.make_model("vgg11", "A", false, **kwargs)
+      end
+    end
+  end
+end

data/lib/torchvision/models/vgg11_bn.rb

@@ -0,0 +1,9 @@
+module TorchVision
+  module Models
+    module VGG11BN
+      def self.new(**kwargs)
+        VGG.make_model("vgg11_bn", "A", true, **kwargs)
+      end
+    end
+  end
+end

data/lib/torchvision/models/vgg13.rb

@@ -0,0 +1,9 @@
+module TorchVision
+  module Models
+    module VGG13
+      def self.new(**kwargs)
+        VGG.make_model("vgg13", "B", false, **kwargs)
+      end
+    end
+  end
+end

data/lib/torchvision/models/vgg13_bn.rb

@@ -0,0 +1,9 @@
+module TorchVision
+  module Models
+    module VGG13BN
+      def self.new(**kwargs)
+        VGG.make_model("vgg13_bn", "B", true, **kwargs)
+      end
+    end
+  end
+end

data/lib/torchvision/models/vgg16.rb

@@ -0,0 +1,9 @@
+module TorchVision
+  module Models
+    module VGG16
+      def self.new(**kwargs)
+        VGG.make_model("vgg16", "D", false, **kwargs)
+      end
+    end
+  end
+end

data/lib/torchvision/models/vgg16_bn.rb

@@ -0,0 +1,9 @@
+module TorchVision
+  module Models
+    module VGG16BN
+      def self.new(**kwargs)
+        VGG.make_model("vgg16_bn", "D", true, **kwargs)
+      end
+    end
+  end
+end

data/lib/torchvision/models/vgg19.rb

@@ -0,0 +1,9 @@
+module TorchVision
+  module Models
+    module VGG19
+      def self.new(**kwargs)
+        VGG.make_model("vgg19", "E", false, **kwargs)
+      end
+    end
+  end
+end

data/lib/torchvision/models/vgg19_bn.rb

@@ -0,0 +1,9 @@
+module TorchVision
+  module Models
+    module VGG19BN
+      def self.new(**kwargs)
+        VGG.make_model("vgg19_bn", "E", true, **kwargs)
+      end
+    end
+  end
+end

data/lib/torchvision/models/wide_resnet101_2.rb

@@ -0,0 +1,10 @@
+module TorchVision
+  module Models
+    module WideResNet101_2
+      def self.new(**kwargs)
+        kwargs[:width_per_group] = 64 * 2
+        ResNet.make_model("wide_resnet101_2", Bottleneck, [3, 4, 23, 3], **kwargs)
+      end
+    end
+  end
+end

data/lib/torchvision/models/wide_resnet50_2.rb

@@ -0,0 +1,10 @@
+module TorchVision
+  module Models
+    module WideResNet50_2
+      def self.new(**kwargs)
+        kwargs[:width_per_group] = 64 * 2
+        ResNet.make_model("wide_resnet50_2", Bottleneck, [3, 4, 6, 3], **kwargs)
+      end
+    end
+  end
+end

data/lib/torchvision/version.rb

@@ -1,3 +1,3 @@
 module TorchVision
-  VERSION = "0.1.2"
+  VERSION = "0.1.3"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: torchvision
 version: !ruby/object:Gem::Version
-  version: 0.1.2
+  version: 0.1.3
 platform: ruby
 authors:
 - Andrew Kane
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2020-04-29 00:00:00.000000000 Z
+date: 2020-06-30 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: numo-narray
@@ -30,14 +30,14 @@ dependencies:
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: 0.2.4
+        version: 0.2.7
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: 0.2.4
+        version: 0.2.7
 - !ruby/object:Gem::Dependency
   name: bundler
   requirement: !ruby/object:Gem::Requirement
@@ -96,10 +96,28 @@ files:
 - lib/torchvision/datasets/kmnist.rb
 - lib/torchvision/datasets/mnist.rb
 - lib/torchvision/datasets/vision_dataset.rb
+- lib/torchvision/models/alexnet.rb
 - lib/torchvision/models/basic_block.rb
 - lib/torchvision/models/bottleneck.rb
 - lib/torchvision/models/resnet.rb
+- lib/torchvision/models/resnet101.rb
+- lib/torchvision/models/resnet152.rb
 - lib/torchvision/models/resnet18.rb
+- lib/torchvision/models/resnet34.rb
+- lib/torchvision/models/resnet50.rb
+- lib/torchvision/models/resnext101_32x8d.rb
+- lib/torchvision/models/resnext50_32x4d.rb
+- lib/torchvision/models/vgg.rb
+- lib/torchvision/models/vgg11.rb
+- lib/torchvision/models/vgg11_bn.rb
+- lib/torchvision/models/vgg13.rb
+- lib/torchvision/models/vgg13_bn.rb
+- lib/torchvision/models/vgg16.rb
+- lib/torchvision/models/vgg16_bn.rb
+- lib/torchvision/models/vgg19.rb
+- lib/torchvision/models/vgg19_bn.rb
+- lib/torchvision/models/wide_resnet101_2.rb
+- lib/torchvision/models/wide_resnet50_2.rb
 - lib/torchvision/transforms/compose.rb
 - lib/torchvision/transforms/functional.rb
 - lib/torchvision/transforms/normalize.rb