torchvision 0.1.3 → 0.2.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 44c29605f12dddf8196432223f2137ef9b9bef490996b718f5a9bdbc13dbd33f
-  data.tar.gz: 8790200a0ed8f7a275f99327431dc8be99a7578c473ec03411f9411cd10c6c93
+  metadata.gz: 9aa604602112403b7f6738a7bb014812deb528b9a4d480ba89cf7f0c6d01b59c
+  data.tar.gz: 3ffa29d3ff5234040df51113d085a807d94a45c6998f8182db72bf60c25d67e7
 SHA512:
-  metadata.gz: 65816ef10f524781553327f9634bb8818a7efa6fb072e81468949d937b5430dcddc7f6c8cf3b305c977dc4b1279d23b38fb034a4c277eecc1adcc0f2b8c99e3e
-  data.tar.gz: 01f485a78cd5a19c9a0dc987f4e46931b033ffb3a84af703b602b0e90e8c221c99b5e6318c86b18361562cc3ca582b3a0822de151a5edf63964002317a684bfa
+  metadata.gz: 89f61279aed314c84ae33c14efe266b849bf74a40a9f90beb650358610b479cb44f6cd247ff56aa89d0227ef6358973b5055fd1ce9bcf1e973402b2118bfe75d
+  data.tar.gz: 4eb63bfd9a79bd3683238c186e0e70aba494028f54ce8f971a551f362eec4b4e55fe83c8e738c7669fde2c3671e3360a01b02c4d29f6c965640a6c08b3c4379d

data/CHANGELOG.md

@@ -1,3 +1,15 @@
+## 0.2.0 (2021-03-11)
+
+- Added `RandomHorizontalFlip`, `RandomVerticalFlip`, and `Resize` transforms
+- Added `save_image` method
+- Added `data` and `targets` methods to datasets
+- Removed support for Ruby < 2.6
+
+Breaking changes
+
+- Added dependency on libvips
+- MNIST datasets return images instead of tensors
+
 ## 0.1.3 (2020-06-29)
 
 - Added AlexNet model

data/LICENSE.txt

@@ -1,7 +1,7 @@
 BSD 3-Clause License
 
-Copyright (c) Andrew Kane 2020,
 Copyright (c) Soumith Chintala 2016,
+Copyright (c) Andrew Kane 2020-2021,
 All rights reserved.
 
 Redistribution and use in source and binary forms, with or without

data/README.md

@@ -2,12 +2,16 @@
 
 :fire: Computer vision datasets, transforms, and models for Ruby
 
-This gem is currently experimental. There may be breaking changes between each release. Please report any issues you experience.
-
-[![Build Status](https://travis-ci.org/ankane/torchvision.svg?branch=master)](https://travis-ci.org/ankane/torchvision)
+[![Build Status](https://github.com/ankane/torchvision/workflows/build/badge.svg?branch=master)](https://github.com/ankane/torchvision/actions)
 
 ## Installation
 
+First, [install libvips](libvips-installation). For Homebrew, use:
+
+```sh
+brew install vips
+```
+
 Add this line to your application’s Gemfile:
 
 ```ruby
@@ -16,7 +20,12 @@ gem 'torchvision'
 
 ## Getting Started
 
-This library follows the [Python API](https://pytorch.org/docs/master/torchvision/). Many methods and options are missing at the moment. PRs welcome!
+This library follows the [Python API](https://pytorch.org/docs/stable/torchvision/index.html). Many methods and options are missing at the moment. PRs welcome!
+
+## Examples
+
+- [MNIST](https://github.com/ankane/torch.rb/tree/master/examples/mnist)
+- [Generative Adversarial Networks](https://github.com/ankane/torch.rb/tree/master/examples/gan)
 
 ## Datasets
 
@@ -43,6 +52,15 @@ TorchVision::Transforms::Compose.new([
 ])
 ```
 
+Supported transforms are:
+
+- Compose
+- Normalize
+- RandomHorizontalFlip
+- RandomVerticalFlip
+- Resize
+- ToTensor
+
 ## Models
 
 - [AlexNet](#alexnet)
@@ -94,6 +112,40 @@ TorchVision::Models::WideResNet52_2.new
 TorchVision::Models::WideResNet101_2.new
 ```
 
+## Pretrained Models
+
+You can download pretrained models with [this script](pretrained.py)
+
+```sh
+pip install torchvision
+python pretrained.py
+```
+
+And load them
+
+```ruby
+net = TorchVision::Models::ResNet18.new
+net.load_state_dict(Torch.load("net.pth"))
+```
+
+## libvips Installation
+
+### Ubuntu
+
+```sh
+sudo apt install libvips
+```
+
+### Mac
+
+```sh
+brew install vips
+```
+
+### Windows
+
+Check out [the options](https://libvips.github.io/libvips/install.html).
+
 ## Disclaimer
 
 This library downloads and prepares public datasets. We don’t host any datasets. Be sure to adhere to the license for each dataset.

data/lib/torchvision.rb

@@ -1,5 +1,6 @@
 # dependencies
 require "numo/narray"
+require "vips"
 require "torch"
 
 # stdlib
@@ -10,6 +11,7 @@ require "rubygems/package"
 require "tmpdir"
 
 # modules
+require "torchvision/utils"
 require "torchvision/version"
 
 # datasets
@@ -48,6 +50,9 @@ require "torchvision/models/wide_resnet101_2"
 require "torchvision/transforms/compose"
 require "torchvision/transforms/functional"
 require "torchvision/transforms/normalize"
+require "torchvision/transforms/random_horizontal_flip"
+require "torchvision/transforms/random_vertical_flip"
+require "torchvision/transforms/resize"
 require "torchvision/transforms/to_tensor"
 
 module TorchVision

data/lib/torchvision/datasets/cifar10.rb

@@ -43,7 +43,8 @@ module TorchVision
         # TODO remove trues when Numo supports it
         img, target = @data[index, true, true, true], @targets[index]
 
-        # TODO convert to image
+        img = Utils.image_from_array(img)
+
         img = @transform.call(img) if @transform
 
         target = @target_transform.call(target) if @target_transform

data/lib/torchvision/datasets/mnist.rb

@@ -2,7 +2,6 @@ module TorchVision
   module Datasets
     class MNIST < VisionDataset
       # http://yann.lecun.com/exdb/mnist/
-
       def initialize(root, train: true, download: false, transform: nil, target_transform: nil)
         super(root, transform: transform, target_transform: target_transform)
         @train = train
@@ -24,7 +23,8 @@ module TorchVision
       def [](index)
         img, target = @data[index], @targets[index].item
 
-        # TODO convert to image
+        img = Utils.image_from_array(img)
+
         img = @transform.call(img) if @transform
 
         target = @target_transform.call(target) if @target_transform

data/lib/torchvision/datasets/vision_dataset.rb

@@ -2,6 +2,8 @@ module TorchVision
   module Datasets
     # TODO inherit Torch::Utils::Data::Dataset
     class VisionDataset
+      attr_reader :data, :targets
+
       def initialize(root, transforms: nil, transform: nil, target_transform: nil)
         @root = root
 

data/lib/torchvision/transforms/compose.rb

@@ -1,11 +1,11 @@
 module TorchVision
   module Transforms
-    class Compose
+    class Compose < Torch::NN::Module
       def initialize(transforms)
         @transforms = transforms
       end
 
-      def call(img)
+      def forward(img)
         @transforms.each do |t|
           img = t.call(img)
         end

data/lib/torchvision/transforms/functional.rb

@@ -32,10 +32,30 @@ module TorchVision
           tensor
         end
 
+        def resize(img, size)
+          raise "img should be Vips::Image. Got #{img.class.name}" unless img.is_a?(Vips::Image)
+          # TODO support array size
+          raise "Got inappropriate size arg: #{size}" unless size.is_a?(Integer)
+
+          w, h = img.size
+          if (w <= h && w == size) || (h <= w && h == size)
+            return img
+          end
+          if w < h
+            ow = size
+            oh = (size * h / w).to_i
+            img.thumbnail_image(ow, height: oh)
+          else
+            oh = size
+            ow = (size * w / h).to_i
+            img.thumbnail_image(ow, height: oh)
+          end
+        end
+
         # TODO improve
         def to_tensor(pic)
-          if !pic.is_a?(Numo::NArray) && !pic.is_a?(Torch::Tensor)
-            raise ArgumentError, "pic should be tensor or Numo::NArray. Got #{pic.class.name}"
+          if !pic.is_a?(Numo::NArray) && !pic.is_a?(Vips::Image)
+            raise ArgumentError, "pic should be Vips::Image or Numo::NArray. Got #{pic.class.name}"
           end
 
           if pic.is_a?(Numo::NArray) && ![2, 3].include?(pic.ndim)
@@ -44,15 +64,44 @@ module TorchVision
 
           if pic.is_a?(Numo::NArray)
             if pic.ndim == 2
-              raise Torch::NotImplementedYet
+              pic = pic.reshape(*pic.shape, 1)
             end
 
             img = Torch.from_numo(pic.transpose(2, 0, 1))
-            return img.float.div(255)
+            if img.dtype == :uint8
+              return img.float.div(255)
+            else
+              return img
+            end
+          end
+
+          case pic.format
+          when :uchar
+            img = Torch::ByteTensor.new(Torch::ByteStorage.from_buffer(pic.write_to_memory))
+          else
+            raise Error, "Format not supported yet: #{pic.format}"
           end
 
-          pic = pic.float
-          pic.unsqueeze!(0).div!(255)
+          img = img.view(pic.height, pic.width, pic.bands)
+          # put it from HWC to CHW format
+          img = img.permute([2, 0, 1]).contiguous
+          img.float.div(255)
+        end
+
+        def hflip(img)
+          if img.is_a?(Torch::Tensor)
+            img.flip(-1)
+          else
+            img.flip(:horizontal)
+          end
+        end
+
+        def vflip(img)
+          if img.is_a?(Torch::Tensor)
+            img.flip(-2)
+          else
+            img.flip(:vertical)
+          end
         end
       end
     end

data/lib/torchvision/transforms/normalize.rb

@@ -1,13 +1,13 @@
 module TorchVision
   module Transforms
-    class Normalize
+    class Normalize < Torch::NN::Module
       def initialize(mean, std, inplace: false)
         @mean = mean
         @std = std
         @inplace = inplace
       end
 
-      def call(tensor)
+      def forward(tensor)
         F.normalize(tensor, @mean, @std, inplace: @inplace)
       end
     end

data/lib/torchvision/transforms/random_horizontal_flip.rb

@@ -0,0 +1,18 @@
+module TorchVision
+  module Transforms
+    class RandomHorizontalFlip < Torch::NN::Module
+      def initialize(p: 0.5)
+        super()
+        @p = p
+      end
+
+      def forward(img)
+        if Torch.rand(1).item < @p
+          F.hflip(img)
+        else
+          img
+        end
+      end
+    end
+  end
+end

data/lib/torchvision/transforms/random_vertical_flip.rb

@@ -0,0 +1,18 @@
+module TorchVision
+  module Transforms
+    class RandomVerticalFlip < Torch::NN::Module
+      def initialize(p: 0.5)
+        super()
+        @p = p
+      end
+
+      def forward(img)
+        if Torch.rand(1).item < @p
+          F.vflip(img)
+        else
+          img
+        end
+      end
+    end
+  end
+end

data/lib/torchvision/transforms/resize.rb

@@ -0,0 +1,13 @@
+module TorchVision
+  module Transforms
+    class Resize < Torch::NN::Module
+      def initialize(size)
+        @size = size
+      end
+
+      def forward(img)
+        F.resize(img, @size)
+      end
+    end
+  end
+end

data/lib/torchvision/transforms/to_tensor.rb

@@ -1,7 +1,7 @@
 module TorchVision
   module Transforms
-    class ToTensor
-      def call(pic)
+    class ToTensor < Torch::NN::Module
+      def forward(pic)
         F.to_tensor(pic)
       end
     end

data/lib/torchvision/utils.rb

@@ -0,0 +1,120 @@
+module TorchVision
+  module Utils
+    class << self
+      def make_grid(tensor, nrow: 8, padding: 2, normalize: false, range: nil, scale_each: false, pad_value: 0)
+        unless Torch.tensor?(tensor) || (tensor.is_a?(Array) && tensor.all? { |t| Torch.tensor?(t) })
+          raise ArgumentError, "tensor or list of tensors expected, got #{tensor.class.name}"
+        end
+
+        # if list of tensors, convert to a 4D mini-batch Tensor
+        if tensor.is_a?(Array)
+          tensor = Torch.stack(tensor, dim: 0)
+        end
+
+        if tensor.dim == 2 # single image H x W
+          tensor = tensor.unsqueeze(0)
+        end
+        if tensor.dim == 3 # single image
+          if tensor.size(0) == 1 # if single-channel, convert to 3-channel
+            tensor = Torch.cat([tensor, tensor, tensor], 0)
+          end
+          tensor = tensor.unsqueeze(0)
+        end
+
+        if tensor.dim == 4 && tensor.size(1) == 1 # single-channel images
+          tensor = Torch.cat([tensor, tensor, tensor], 1)
+        end
+
+        if normalize
+          tensor = tensor.clone # avoid modifying tensor in-place
+          if !range.nil? && !range.is_a?(Array)
+            raise "range has to be an array (min, max) if specified. min and max are numbers"
+          end
+
+          norm_ip = lambda do |img, min, max|
+            img.clamp!(min, max)
+            img.add!(-min).div!(max - min + 1e-5)
+          end
+
+          norm_range = lambda do |t, range|
+            if !range.nil?
+              norm_ip.call(t, range[0], range[1])
+            else
+              norm_ip.call(t, t.min.to_f, t.max.to_f)
+            end
+          end
+
+          if scale_each
+            tensor.each do |t| # loop over mini-batch dimension
+              norm_range.call(t, range)
+            end
+          else
+            norm_range.call(tensor, range)
+          end
+        end
+
+        if tensor.size(0) == 1
+          return tensor.squeeze(0)
+        end
+
+        # make the mini-batch of images into a grid
+        nmaps = tensor.size(0)
+        xmaps = [nrow, nmaps].min
+        ymaps = (nmaps.to_f / xmaps).ceil
+        height, width = (tensor.size(2) + padding), (tensor.size(3) + padding)
+        num_channels = tensor.size(1)
+        grid = tensor.new_full([num_channels, height * ymaps + padding, width * xmaps + padding], pad_value)
+        k = 0
+        ymaps.times do |y|
+          xmaps.times do |x|
+            break if k >= nmaps
+            grid.narrow(1, y * height + padding, height - padding).narrow(2, x * width + padding, width - padding).copy!(tensor[k])
+            k += 1
+          end
+        end
+        grid
+      end
+
+      def save_image(tensor, fp, nrow: 8, padding: 2, normalize: false, range: nil, scale_each: false, pad_value: 0)
+        grid = make_grid(tensor, nrow: nrow, padding: padding, pad_value: pad_value, normalize: normalize, range: range, scale_each: scale_each)
+        # Add 0.5 after unnormalizing to [0, 255] to round to nearest integer
+        ndarr = grid.mul(255).add!(0.5).clamp!(0, 255).permute(1, 2, 0).to("cpu", dtype: :uint8)
+        im = image_from_array(ndarr)
+        im.write_to_file(fp)
+      end
+
+      # private
+      # Ruby-specific method
+      # TODO use Numo when bridge available
+      def image_from_array(array)
+        case array
+        when Torch::Tensor
+          # TODO support more dtypes
+          raise "Type not supported yet: #{array.dtype}" unless array.dtype == :uint8
+
+          array = array.contiguous unless array.contiguous?
+
+          width, height = array.shape
+          bands = array.shape[2] || 1
+          data = FFI::Pointer.new(:uint8, array._data_ptr)
+          data.define_singleton_method(:bytesize) do
+            array.numel * array.element_size
+          end
+
+          Vips::Image.new_from_memory(data, width, height, bands, :uchar)
+        when Numo::NArray
+          # TODO support more types
+          raise "Type not supported yet: #{array.class.name}" unless array.is_a?(Numo::UInt8)
+
+          width, height = array.shape
+          bands = array.shape[2] || 1
+          data = array.to_binary
+
+          Vips::Image.new_from_memory(data, width, height, bands, :uchar)
+        else
+          raise "Expected Torch::Tensor or Numo::NArray, not #{array.class.name}"
+        end
+      end
+    end
+  end
+end

data/lib/torchvision/version.rb

@@ -1,3 +1,3 @@
 module TorchVision
-  VERSION = "0.1.3"
+  VERSION = "0.2.0"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: torchvision
 version: !ruby/object:Gem::Version
-  version: 0.1.3
+  version: 0.2.0
 platform: ruby
 authors:
 - Andrew Kane
-autorequire: 
+autorequire:
 bindir: bin
 cert_chain: []
-date: 2020-06-30 00:00:00.000000000 Z
+date: 2021-03-11 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: numo-narray
@@ -25,63 +25,35 @@ dependencies:
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
-  name: torch-rb
+  name: ruby-vips
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: 0.2.7
+        version: '2.1'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: 0.2.7
-- !ruby/object:Gem::Dependency
-  name: bundler
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: '0'
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: '0'
+        version: '2.1'
 - !ruby/object:Gem::Dependency
-  name: rake
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: '0'
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: '0'
-- !ruby/object:Gem::Dependency
-  name: minitest
+  name: torch-rb
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: '5'
-  type: :development
+        version: 0.3.7
+  type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: '5'
-description: 
-email: andrew@chartkick.com
+        version: 0.3.7
+description:
+email: andrew@ankane.org
 executables: []
 extensions: []
 extra_rdoc_files: []
@@ -121,13 +93,17 @@ files:
 - lib/torchvision/transforms/compose.rb
 - lib/torchvision/transforms/functional.rb
 - lib/torchvision/transforms/normalize.rb
+- lib/torchvision/transforms/random_horizontal_flip.rb
+- lib/torchvision/transforms/random_vertical_flip.rb
+- lib/torchvision/transforms/resize.rb
 - lib/torchvision/transforms/to_tensor.rb
+- lib/torchvision/utils.rb
 - lib/torchvision/version.rb
 homepage: https://github.com/ankane/torchvision
 licenses:
 - BSD-3-Clause
 metadata: {}
-post_install_message: 
+post_install_message:
 rdoc_options: []
 require_paths:
 - lib
@@ -135,15 +111,15 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: '2.4'
+      version: '2.6'
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.1.2
-signing_key: 
+rubygems_version: 3.2.3
+signing_key:
 specification_version: 4
 summary: Computer vision datasets, transforms, and models for Ruby
 test_files: []