torchvision 0.1.0 → 0.2.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 19fff61bb461e5fbf850702bf485a442b2013807ac28549bc427e5f3d8c7472b
-  data.tar.gz: bc8004d2ca26e9022f2fa2b1663277bcedf701729f59aae248058a26e605a5ad
+  metadata.gz: bbb87c59c0f081c0de57ccdd62e30bfc551e1cb69523e4ffd498c997e1a2d8b3
+  data.tar.gz: 890da113706e659d57194980c5c9262075beb8398a75da2997c0812b70abe308
 SHA512:
-  metadata.gz: fbd3d7292efa6ee2fd2c0ff8cb85659d37a19761b4d93a9a4923a9990d7400c849738913db12720e7d232d6fdb180c16f06da0ecc3601a922bf0036beb0b44bd
-  data.tar.gz: '09b86d6b01f25d43ac65d9c3d0509b3488ed2108d57090553ae46526f841551cbdd16fefce1cb15ea7f326d946e3abb26d777c3c45e23538f8fb7753fdb6fec9'
+  metadata.gz: 3445b62b7824ae16205034881d37c48ac4c70d7e5677014755ae5600632f9ce45168f41b0d3e98c8104eb8337e1566db4df3e0ad5ace5e6a46a5d213d01b6c8d
+  data.tar.gz: 93f22c385586ff8a010880676806f6bc9ba2f614c4c14886235a300ea6e2abce0f80c260e255644e1b4d24e6ecddfd21830dde2960a92a9492239e69622d4548

data/CHANGELOG.md

@@ -1,3 +1,38 @@
+## 0.2.1 (2021-03-14)
+
+- Added `ImageFolder` and `DatasetFolder`
+- Added `CenterCrop` and `RandomResizedCrop` transforms
+- Added `crop` method
+
+## 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
+- 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
+- Added ResNet18 model
+
+## 0.1.1 (2020-04-28)
+
+- Removed `mini_magick` for performance
+
 ## 0.1.0 (2020-04-27)
 
 - First release

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

@@ -2,10 +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://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
@@ -14,17 +20,139 @@ 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)
+- [Transfer learning](https://github.com/ankane/torch.rb/tree/master/examples/transfer-learning)
+- [Generative adversarial networks](https://github.com/ankane/torch.rb/tree/master/examples/gan)
 
 ## Datasets
 
-MNIST dataset
+Load a dataset
+
+```ruby
+TorchVision::Datasets::MNIST.new("./data", train: true, download: true)
+```
+
+Supported datasets are:
+
+- CIFAR10
+- CIFAR100
+- FashionMNIST
+- KMNIST
+- MNIST
+
+## Transforms
+
+```ruby
+TorchVision::Transforms::Compose.new([
+  TorchVision::Transforms::ToTensor.new,
+  TorchVision::Transforms::Normalize.new([0.1307], [0.3081])
+])
+```
+
+Supported transforms are:
+
+- CenterCrop
+- Compose
+- Normalize
+- RandomHorizontalFlip
+- RandomResizedCrop
+- RandomVerticalFlip
+- Resize
+- ToTensor
+
+## 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
-trainset = TorchVision::Datasets::MNIST.new("./data", train: true, download: true)
-trainset.size
+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
+
+### Linux
+
+Check your package manager. For Ubuntu, use:
+
+```sh
+sudo apt install libvips
+```
+
+You can also [build from source](https://libvips.github.io/libvips/install.html).
+
+### 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

@@ -1,23 +1,62 @@
 # dependencies
-require "mini_magick"
 require "numo/narray"
+require "vips"
 require "torch"
 
 # stdlib
 require "digest"
 require "fileutils"
 require "net/http"
+require "rubygems/package"
+require "tmpdir"
 
 # modules
+require "torchvision/utils"
 require "torchvision/version"
 
 # datasets
+require "torchvision/datasets/vision_dataset"
+require "torchvision/datasets/dataset_folder"
+require "torchvision/datasets/image_folder"
+require "torchvision/datasets/cifar10"
+require "torchvision/datasets/cifar100"
 require "torchvision/datasets/mnist"
+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/center_crop"
 require "torchvision/transforms/compose"
 require "torchvision/transforms/functional"
 require "torchvision/transforms/normalize"
+require "torchvision/transforms/random_horizontal_flip"
+require "torchvision/transforms/random_resized_crop"
+require "torchvision/transforms/random_vertical_flip"
+require "torchvision/transforms/resize"
 require "torchvision/transforms/to_tensor"
 
 module TorchVision

data/lib/torchvision/datasets/cifar10.rb

@@ -0,0 +1,117 @@
+module TorchVision
+  module Datasets
+    class CIFAR10 < VisionDataset
+      # https://www.cs.toronto.edu/~kriz/cifar.html
+
+      def initialize(root, train: true, download: false, transform: nil, target_transform: nil)
+        super(root, transform: transform, target_transform: target_transform)
+        @train = train
+
+        self.download if download
+
+        if !_check_integrity
+          raise Error, "Dataset not found or corrupted. You can use download=True to download it"
+        end
+
+        downloaded_list = @train ? train_list : test_list
+
+        @data = String.new
+        @targets = String.new
+
+        downloaded_list.each do |file|
+          file_path = File.join(@root, base_folder, file[:filename])
+          File.open(file_path, "rb") do |f|
+            while !f.eof?
+              f.read(1) if multiple_labels?
+              @targets << f.read(1)
+              @data << f.read(3072)
+            end
+          end
+        end
+
+        @targets = @targets.unpack("C*")
+        # TODO switch i to -1 when Numo supports it
+        @data = Numo::UInt8.from_binary(@data).reshape(@targets.size, 3, 32, 32)
+        @data = @data.transpose(0, 2, 3, 1)
+      end
+
+      def size
+        @data.shape[0]
+      end
+
+      def [](index)
+        # TODO remove trues when Numo supports it
+        img, target = @data[index, true, true, true], @targets[index]
+
+        img = Utils.image_from_array(img)
+
+        img = @transform.call(img) if @transform
+
+        target = @target_transform.call(target) if @target_transform
+
+        [img, target]
+      end
+
+      def _check_integrity
+        root = @root
+        (train_list + test_list).each do |fentry|
+          fpath = File.join(root, base_folder, fentry[:filename])
+          return false unless check_integrity(fpath, fentry[:sha256])
+        end
+        true
+      end
+
+      def download
+        if _check_integrity
+          puts "Files already downloaded and verified"
+          return
+        end
+
+        download_file(url, download_root: @root, filename: filename, sha256: tgz_sha256)
+
+        path = File.join(@root, filename)
+        File.open(path, "rb") do |io|
+          Gem::Package.new("").extract_tar_gz(io, @root)
+        end
+      end
+
+      private
+
+      def base_folder
+        "cifar-10-batches-bin"
+      end
+
+      def url
+        "https://www.cs.toronto.edu/~kriz/cifar-10-binary.tar.gz"
+      end
+
+      def filename
+        "cifar-10-binary.tar.gz"
+      end
+
+      def tgz_sha256
+        "c4a38c50a1bc5f3a1c5537f2155ab9d68f9f25eb1ed8d9ddda3db29a59bca1dd"
+      end
+
+      def train_list
+        [
+          {filename: "data_batch_1.bin", sha256: "cee916563c9f80d84e3cc88e17fdc0941787f1244f00a67874d45b261883ada5"},
+          {filename: "data_batch_2.bin", sha256: "a591ca11fa1708a91ee40f54b3da4784ccd871ecf2137de63f51ada8b3fa57ed"},
+          {filename: "data_batch_3.bin", sha256: "bbe8596564c0f86427f876058170b84dac6670ddf06d79402899d93ceea26f67"},
+          {filename: "data_batch_4.bin", sha256: "014e562d6e23c72197cc727519169a60359f5eccd8945ad5a09d710285ff4e48"},
+          {filename: "data_batch_5.bin", sha256: "755304fc0b379caeae8c14f0dac912fbc7d6cd469eb67a1029a08a39453a9add"},
+        ]
+      end
+
+      def test_list
+        [
+          {filename: "test_batch.bin", sha256: "8e2eb146ae340b09e24670f29cabc6326dba54da8789dab6768acf480273f65b"}
+        ]
+      end
+
+      def multiple_labels?
+        false
+      end
+    end
+  end
+end

data/lib/torchvision/datasets/cifar100.rb

@@ -0,0 +1,41 @@
+module TorchVision
+  module Datasets
+    class CIFAR100 < CIFAR10
+      # https://www.cs.toronto.edu/~kriz/cifar.html
+
+      private
+
+      def base_folder
+        "cifar-100-binary"
+      end
+
+      def url
+        "https://www.cs.toronto.edu/~kriz/cifar-100-binary.tar.gz"
+      end
+
+      def filename
+        "cifar-100-binary.tar.gz"
+      end
+
+      def tgz_sha256
+        "58a81ae192c23a4be8b1804d68e518ed807d710a4eb253b1f2a199162a40d8ec"
+      end
+
+      def train_list
+        [
+          {filename: "train.bin", sha256: "f31298fc616915fa142368359df1c4ca2ae984d6915ca468b998a5ec6aeebf29"}
+        ]
+      end
+
+      def test_list
+        [
+          {filename: "test.bin", sha256: "d8b1e6b7b3bee4020055f0699b111f60b1af1e262aeb93a0b659061746f8224a"}
+        ]
+      end
+
+      def multiple_labels?
+        true
+      end
+    end
+  end
+end