torchvision 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: 19fff61bb461e5fbf850702bf485a442b2013807ac28549bc427e5f3d8c7472b
+  data.tar.gz: bc8004d2ca26e9022f2fa2b1663277bcedf701729f59aae248058a26e605a5ad
+SHA512:
+  metadata.gz: fbd3d7292efa6ee2fd2c0ff8cb85659d37a19761b4d93a9a4923a9990d7400c849738913db12720e7d232d6fdb180c16f06da0ecc3601a922bf0036beb0b44bd
+  data.tar.gz: '09b86d6b01f25d43ac65d9c3d0509b3488ed2108d57090553ae46526f841551cbdd16fefce1cb15ea7f326d946e3abb26d777c3c45e23538f8fb7753fdb6fec9'

data/CHANGELOG.md

@@ -0,0 +1,3 @@
+## 0.1.0 (2020-04-27)
+
+- First release

data/LICENSE.txt

@@ -0,0 +1,30 @@
+BSD 3-Clause License
+
+Copyright (c) Andrew Kane 2020,
+Copyright (c) Soumith Chintala 2016,
+All rights reserved.
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+* Redistributions of source code must retain the above copyright notice, this
+  list of conditions and the following disclaimer.
+
+* Redistributions in binary form must reproduce the above copyright notice,
+  this list of conditions and the following disclaimer in the documentation
+  and/or other materials provided with the distribution.
+
+* Neither the name of the copyright holder nor the names of its
+  contributors may be used to endorse or promote products derived from
+  this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
+FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
+SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
+OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

data/README.md

@@ -0,0 +1,54 @@
+# TorchVision
+
+: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.
+
+## Installation
+
+Add this line to your application’s Gemfile:
+
+```ruby
+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!
+
+## Datasets
+
+MNIST dataset
+
+```ruby
+trainset = TorchVision::Datasets::MNIST.new("./data", train: true, download: true)
+trainset.size
+```
+
+## Disclaimer
+
+This library downloads and prepares public datasets. We don’t host any datasets. Be sure to adhere to the license for each dataset.
+
+If you’re a dataset owner and wish to update any details or remove it from this project, let us know.
+
+## History
+
+View the [changelog](https://github.com/ankane/torchvision/blob/master/CHANGELOG.md)
+
+## Contributing
+
+Everyone is encouraged to help improve this project. Here are a few ways you can help:
+
+- [Report bugs](https://github.com/ankane/torchvision/issues)
+- Fix bugs and [submit pull requests](https://github.com/ankane/torchvision/pulls)
+- Write, clarify, or fix documentation
+- Suggest or add new features
+
+To get started with development:
+
+```sh
+git clone https://github.com/ankane/torchvision.git
+cd torchvision
+bundle install
+bundle exec rake test
+```

data/lib/torchvision.rb

@@ -0,0 +1,25 @@
+# dependencies
+require "mini_magick"
+require "numo/narray"
+require "torch"
+
+# stdlib
+require "digest"
+require "fileutils"
+require "net/http"
+
+# modules
+require "torchvision/version"
+
+# datasets
+require "torchvision/datasets/mnist"
+
+# transforms
+require "torchvision/transforms/compose"
+require "torchvision/transforms/functional"
+require "torchvision/transforms/normalize"
+require "torchvision/transforms/to_tensor"
+
+module TorchVision
+  class Error < StandardError; end
+end

data/lib/torchvision/datasets/mnist.rb

@@ -0,0 +1,146 @@
+module TorchVision
+  module Datasets
+    class MNIST
+      RESOURCES = [
+        {
+          url: "http://yann.lecun.com/exdb/mnist/train-images-idx3-ubyte.gz",
+          sha256: "440fcabf73cc546fa21475e81ea370265605f56be210a4024d2ca8f203523609"
+        },
+        {
+          url: "http://yann.lecun.com/exdb/mnist/train-labels-idx1-ubyte.gz",
+          sha256: "3552534a0a558bbed6aed32b30c495cca23d567ec52cac8be1a0730e8010255c"
+        },
+        {
+          url: "http://yann.lecun.com/exdb/mnist/t10k-images-idx3-ubyte.gz",
+          sha256: "8d422c7b0a1c1c79245a5bcf07fe86e33eeafee792b84584aec276f5a2dbc4e6"
+        },
+        {
+          url: "http://yann.lecun.com/exdb/mnist/t10k-labels-idx1-ubyte.gz",
+          sha256: "f7ae60f92e00ec6debd23a6088c31dbd2371eca3ffa0defaefb259924204aec6"
+        }
+      ]
+      TRAINING_FILE = "training.pt"
+      TEST_FILE = "test.pt"
+
+      def initialize(root, train: true, download: false, transform: nil)
+        @root = root
+        @train = train
+        @transform = transform
+
+        self.download if download
+
+        if !check_exists
+          raise Error, "Dataset not found. You can use download: true to download it"
+        end
+
+        data_file = @train ? TRAINING_FILE : TEST_FILE
+        @data, @targets = Torch.load(File.join(processed_folder, data_file))
+      end
+
+      def size
+        @data.size[0]
+      end
+
+      def [](index)
+        img = @data[index]
+        img = MiniMagick::Image.import_pixels(img.numo.to_binary, img.size(0), img.size(1), 8, "gray")
+        img = @transform.call(img) if @transform
+
+        target = @targets[index].item
+
+        [img, target]
+      end
+
+      def raw_folder
+        File.join(@root, "MNIST", "raw")
+      end
+
+      def processed_folder
+        File.join(@root, "MNIST", "processed")
+      end
+
+      def check_exists
+        File.exist?(File.join(processed_folder, TRAINING_FILE)) &&
+          File.exist?(File.join(processed_folder, TEST_FILE))
+      end
+
+      def download
+        return if check_exists
+
+        FileUtils.mkdir_p(raw_folder)
+        FileUtils.mkdir_p(processed_folder)
+
+        RESOURCES.each do |resource|
+          filename = resource[:url].split("/").last
+          download_file(resource[:url], download_root: raw_folder, filename: filename, sha256: resource[:sha256])
+        end
+
+        puts "Processing..."
+
+        training_set = [
+          unpack_mnist("train-images-idx3-ubyte", 16, [60000, 28, 28]),
+          unpack_mnist("train-labels-idx1-ubyte", 8, [60000])
+        ]
+        test_set = [
+          unpack_mnist("t10k-images-idx3-ubyte", 16, [10000, 28, 28]),
+          unpack_mnist("t10k-labels-idx1-ubyte", 8, [10000])
+        ]
+
+        Torch.save(training_set, File.join(processed_folder, TRAINING_FILE))
+        Torch.save(test_set, File.join(processed_folder, TEST_FILE))
+
+        puts "Done!"
+      end
+
+      private
+
+      def unpack_mnist(path, offset, shape)
+        path = File.join(raw_folder, "#{path}.gz")
+        File.open(path, "rb") do |f|
+          gz = Zlib::GzipReader.new(f)
+          gz.read(offset)
+          Torch.tensor(Numo::UInt8.from_string(gz.read, shape))
+        end
+      end
+
+      def download_file(url, download_root:, filename:, sha256:)
+        FileUtils.mkdir_p(download_root)
+
+        dest = File.join(download_root, filename)
+        return dest if File.exist?(dest)
+
+        temp_path = "#{Dir.tmpdir}/#{Time.now.to_f}" # TODO better name
+
+        digest = Digest::SHA256.new
+
+        uri = URI(url)
+
+        # Net::HTTP automatically adds Accept-Encoding for compression
+        # of response bodies and automatically decompresses gzip
+        # and deflateresponses unless a Range header was sent.
+        # https://ruby-doc.org/stdlib-2.6.4/libdoc/net/http/rdoc/Net/HTTP.html
+        Net::HTTP.start(uri.host, uri.port, use_ssl: uri.scheme == "https") do |http|
+          request = Net::HTTP::Get.new(uri)
+
+          puts "Downloading #{url}..."
+          File.open(temp_path, "wb") do |f|
+            http.request(request) do |response|
+              response.read_body do |chunk|
+                f.write(chunk)
+                digest.update(chunk)
+              end
+            end
+          end
+        end
+
+        if digest.hexdigest != sha256
+          raise Error, "Bad hash: #{digest.hexdigest}"
+        end
+
+        FileUtils.mv(temp_path, dest)
+
+        dest
+      end
+    end
+  end
+end

data/lib/torchvision/transforms/compose.rb

@@ -0,0 +1,16 @@
+module TorchVision
+  module Transforms
+    class Compose
+      def initialize(transforms)
+        @transforms = transforms
+      end
+
+      def call(img)
+        @transforms.each do |t|
+          img = t.call(img)
+        end
+        img
+      end
+    end
+  end
+end

data/lib/torchvision/transforms/functional.rb

@@ -0,0 +1,45 @@
+module TorchVision
+  module Transforms
+    class Functional
+      class << self
+        def normalize(tensor, mean, std, inplace: false)
+          unless Torch.tensor?(tensor)
+            raise ArgumentError, "tensor should be a torch tensor. Got #{tensor.class.name}"
+          end
+
+          if tensor.ndimension != 3
+            raise ArgumentError, "Expected tensor to be a tensor image of size (C, H, W). Got tensor.size() = #{tensor.size}"
+          end
+
+          tensor = tensor.clone unless inplace
+
+          dtype = tensor.dtype
+          # TODO Torch.as_tensor
+          mean = Torch.tensor(mean, dtype: dtype, device: tensor.device)
+          std = Torch.tensor(std, dtype: dtype, device: tensor.device)
+
+          # TODO
+          if std.to_a.any? { |v| v == 0 }
+            raise ArgumentError, "std evaluated to zero after conversion to #{dtype}, leading to division by zero."
+          end
+          # if mean.ndim == 1
+          #   raise Torch::NotImplementedYet
+          # end
+          # if std.ndim == 1
+          #   raise Torch::NotImplementedYet
+          # end
+          tensor.sub!(mean).div!(std)
+          tensor
+        end
+
+        # TODO improve
+        def to_tensor(pic)
+          Torch.tensor(pic.get_pixels, dtype: :float)
+        end
+      end
+    end
+
+    # shortcut
+    F = Functional
+  end
+end

data/lib/torchvision/transforms/normalize.rb

@@ -0,0 +1,15 @@
+module TorchVision
+  module Transforms
+    class Normalize
+      def initialize(mean, std, inplace: false)
+        @mean = mean
+        @std = std
+        @inplace = inplace
+      end
+
+      def call(tensor)
+        F.normalize(tensor, @mean, @std, inplace: @inplace)
+      end
+    end
+  end
+end

data/lib/torchvision/transforms/to_tensor.rb

@@ -0,0 +1,9 @@
+module TorchVision
+  module Transforms
+    class ToTensor
+      def call(pic)
+        F.to_tensor(pic)
+      end
+    end
+  end
+end

data/lib/torchvision/version.rb

@@ -0,0 +1,3 @@
+module TorchVision
+  VERSION = "0.1.0"
+end

metadata

@@ -0,0 +1,136 @@
+--- !ruby/object:Gem::Specification
+name: torchvision
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- Andrew Kane
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2020-04-27 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: mini_magick
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: numo-narray
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: torch-rb
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 0.2.2
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 0.2.2
+- !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'
+- !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
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '5'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '5'
+description: 
+email: andrew@chartkick.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- CHANGELOG.md
+- LICENSE.txt
+- README.md
+- lib/torchvision.rb
+- lib/torchvision/datasets/mnist.rb
+- lib/torchvision/transforms/compose.rb
+- lib/torchvision/transforms/functional.rb
+- lib/torchvision/transforms/normalize.rb
+- lib/torchvision/transforms/to_tensor.rb
+- lib/torchvision/version.rb
+homepage: https://github.com/ankane/torchvision
+licenses:
+- BSD-3-Clause
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '2.4'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubygems_version: 3.1.2
+signing_key: 
+specification_version: 4
+summary: Computer vision datasets, transforms, and models for Ruby
+test_files: []