torch-rb 0.2.4 → 0.2.5

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 67c5a0cf556399dc32d73e8793e3aa794c181150f0f42dfa810c4b98a5acf6f2
-  data.tar.gz: 0a23f6a42595fb9d599962e88438b964180583ead5b9cce934cc447951b4a389
+  metadata.gz: 8f6ab78fb5cff27d0d60ddb9c08fb2f526bd60e241dd1011554b21716bdd2f43
+  data.tar.gz: 5568f53d8d5d688e3f29fb55ddbe9457e0b933dc69f59b422035c0cee249e396
 SHA512:
-  metadata.gz: c0f8e9e3395d196d7ea6fa4b40d128284d768033e02f4ed7d2dc9adc985015fd0a80d601601dd97438b803b6a3bd7b81f5dbda353bb5dee4247503a24cd755d7
-  data.tar.gz: c32a22ebbe1b4dfd77324f62a72d6a128639aac0a99d4c5255b16c606e6f961ae2c8b0dbab5012a9b21faa7409511b79a50676bc8314f181c85f90433433fa8b
+  metadata.gz: 9c5dcfbf35382b37678662690677b2b90d0d544e8802703cf83dba6e10483a4df487f9687e4e898c9cc449c568f4e02f9d831daa982b5b3135af6f9ce176ec88
+  data.tar.gz: 34f142d874606e140661ae992a9f8cd4779f95c93c11d9a89a1864dd0bd53c5480c30d9aec5897f1955e2450bd0a3bc56ed0868e3b54d82ff4cdba40af379840

data/CHANGELOG.md

@@ -1,3 +1,9 @@
+## 0.2.5 (2020-06-07)
+
+- Added `download_url_to_file` and `load_state_dict_from_url` to `Torch::Hub`
+- Improved error messages
+- Fixed tensor slicing
+
 ## 0.2.4 (2020-04-29)
 
 - Added `to_i` and `to_f` to tensors

data/README.md

@@ -2,6 +2,8 @@
 
 :fire: Deep learning for Ruby, powered by [LibTorch](https://pytorch.org)
 
+For computer vision tasks, also check out [TorchVision](https://github.com/ankane/torchvision)
+
 [![Build Status](https://travis-ci.org/ankane/torch.rb.svg?branch=master)](https://travis-ci.org/ankane/torch.rb)
 
 ## Installation
@@ -22,6 +24,18 @@ It can take a few minutes to compile the extension.
 
 ## Getting Started
 
+Deep learning is significantly faster with a GPU. If you don’t have an NVIDIA GPU, we recommend using a cloud service. [Paperspace](https://www.paperspace.com/) has a great free plan.
+
+We’ve put together a [Docker image](https://github.com/ankane/ml-stack) to make it easy to get started. On Paperspace, create a notebook with a custom container. Set the container name to:
+
+```text
+ankane/ml-stack:torch-gpu
+```
+
+And leave the other fields in that section blank. Once the notebook is running, you can run the [MNIST example](https://github.com/ankane/ml-stack/blob/master/torch-gpu/MNIST.ipynb).
+
+## API
+
 This library follows the [PyTorch API](https://pytorch.org/docs/stable/torch.html). There are a few changes to make it more Ruby-like:
 
 - Methods that perform in-place modifications end with `!` instead of `_` (`add!` instead of `add_`)
@@ -192,7 +206,7 @@ end
 Define a neural network
 
 ```ruby
-class Net < Torch::NN::Module
+class MyNet < Torch::NN::Module
   def initialize
     super
     @conv1 = Torch::NN::Conv2d.new(1, 6, 3)
@@ -226,7 +240,7 @@ end
 Create an instance of it
 
 ```ruby
-net = Net.new
+net = MyNet.new
 input = Torch.randn(1, 1, 32, 32)
 net.call(input)
 ```
@@ -294,7 +308,7 @@ Torch.save(net.state_dict, "net.pth")
 Load a model
 
 ```ruby
-net = Net.new
+net = MyNet.new
 net.load_state_dict(Torch.load("net.pth"))
 net.eval
 ```
@@ -413,9 +427,7 @@ Then install the gem (no need for `bundle config`).
 
 ### Linux
 
-Deep learning is significantly faster on GPUs.
-
-Install [CUDA](https://developer.nvidia.com/cuda-downloads) and [cuDNN](https://developer.nvidia.com/cudnn) and reinstall the gem.
+Deep learning is significantly faster on a GPU. Install [CUDA](https://developer.nvidia.com/cuda-downloads) and [cuDNN](https://developer.nvidia.com/cudnn) and reinstall the gem.
 
 Check if CUDA is available
 

data/ext/torch/ext.cpp

@@ -23,7 +23,7 @@ class Parameter: public torch::autograd::Variable {
     Parameter(Tensor&& t) : torch::autograd::Variable(t) { }
 };
 
-void handle_error(c10::Error const & ex)
+void handle_error(torch::Error const & ex)
 {
   throw Exception(rb_eRuntimeError, ex.what_without_backtrace());
 }
@@ -32,15 +32,19 @@ extern "C"
 void Init_ext()
 {
   Module rb_mTorch = define_module("Torch");
+  rb_mTorch.add_handler<torch::Error>(handle_error);
   add_torch_functions(rb_mTorch);
 
   Class rb_cTensor = define_class_under<torch::Tensor>(rb_mTorch, "Tensor");
+  rb_cTensor.add_handler<torch::Error>(handle_error);
   add_tensor_functions(rb_cTensor);
 
   Module rb_mNN = define_module_under(rb_mTorch, "NN");
+  rb_mNN.add_handler<torch::Error>(handle_error);
   add_nn_functions(rb_mNN);
 
   Module rb_mRandom = define_module_under(rb_mTorch, "Random")
+    .add_handler<torch::Error>(handle_error)
     .define_singleton_method(
       "initial_seed",
       *[]() {
@@ -55,6 +59,7 @@ void Init_ext()
 
   // https://pytorch.org/cppdocs/api/structc10_1_1_i_value.html
   Class rb_cIValue = define_class_under<torch::IValue>(rb_mTorch, "IValue")
+    .add_handler<torch::Error>(handle_error)
     .define_constructor(Constructor<torch::IValue>())
     .define_method("bool?", &torch::IValue::isBool)
     .define_method("bool_list?", &torch::IValue::isBoolList)
@@ -317,7 +322,6 @@ void Init_ext()
       });
 
   rb_cTensor
-    .add_handler<c10::Error>(handle_error)
     .define_method("cuda?", &torch::Tensor::is_cuda)
     .define_method("sparse?", &torch::Tensor::is_sparse)
     .define_method("quantized?", &torch::Tensor::is_quantized)
@@ -374,6 +378,21 @@ void Init_ext()
         s << self.device();
         return s.str();
       })
+    .define_method(
+      "_data_str",
+      *[](Tensor& self) {
+        Tensor tensor = self;
+
+        // move to CPU to get data
+        if (tensor.device().type() != torch::kCPU) {
+          torch::Device device("cpu");
+          tensor = tensor.to(device);
+        }
+
+        auto data_ptr = (const char *) tensor.data_ptr();
+        return std::string(data_ptr, tensor.numel() * tensor.element_size());
+      })
+    // TODO figure out a better way to do this
     .define_method(
       "_flat_data",
       *[](Tensor& self) {
@@ -388,46 +407,40 @@ void Init_ext()
         Array a;
         auto dtype = tensor.dtype();
 
+        Tensor view = tensor.reshape({tensor.numel()});
+
         // TODO DRY if someone knows C++
         if (dtype == torch::kByte) {
-          uint8_t* data = tensor.data_ptr<uint8_t>();
           for (int i = 0; i < tensor.numel(); i++) {
-            a.push(data[i]);
+            a.push(view[i].item().to<uint8_t>());
           }
         } else if (dtype == torch::kChar) {
-          int8_t* data = tensor.data_ptr<int8_t>();
           for (int i = 0; i < tensor.numel(); i++) {
-            a.push(to_ruby<int>(data[i]));
+            a.push(to_ruby<int>(view[i].item().to<int8_t>()));
           }
         } else if (dtype == torch::kShort) {
-          int16_t* data = tensor.data_ptr<int16_t>();
           for (int i = 0; i < tensor.numel(); i++) {
-            a.push(data[i]);
+            a.push(view[i].item().to<int16_t>());
           }
         } else if (dtype == torch::kInt) {
-          int32_t* data = tensor.data_ptr<int32_t>();
           for (int i = 0; i < tensor.numel(); i++) {
-            a.push(data[i]);
+            a.push(view[i].item().to<int32_t>());
           }
         } else if (dtype == torch::kLong) {
-          int64_t* data = tensor.data_ptr<int64_t>();
           for (int i = 0; i < tensor.numel(); i++) {
-            a.push(data[i]);
+            a.push(view[i].item().to<int64_t>());
           }
         } else if (dtype == torch::kFloat) {
-          float* data = tensor.data_ptr<float>();
           for (int i = 0; i < tensor.numel(); i++) {
-            a.push(data[i]);
+            a.push(view[i].item().to<float>());
           }
         } else if (dtype == torch::kDouble) {
-          double* data = tensor.data_ptr<double>();
           for (int i = 0; i < tensor.numel(); i++) {
-            a.push(data[i]);
+            a.push(view[i].item().to<double>());
           }
         } else if (dtype == torch::kBool) {
-          bool* data = tensor.data_ptr<bool>();
           for (int i = 0; i < tensor.numel(); i++) {
-            a.push(data[i] ? True : False);
+            a.push(view[i].item().to<bool>() ? True : False);
           }
         } else {
           throw std::runtime_error("Unsupported type");
@@ -449,7 +462,7 @@ void Init_ext()
       });
 
   Class rb_cTensorOptions = define_class_under<torch::TensorOptions>(rb_mTorch, "TensorOptions")
-    .add_handler<c10::Error>(handle_error)
+    .add_handler<torch::Error>(handle_error)
     .define_constructor(Constructor<torch::TensorOptions>())
     .define_method(
       "dtype",
@@ -555,6 +568,7 @@ void Init_ext()
       });
 
   Class rb_cParameter = define_class_under<Parameter, torch::Tensor>(rb_mNN, "Parameter")
+    .add_handler<torch::Error>(handle_error)
     .define_method(
       "grad",
       *[](Parameter& self) {
@@ -564,6 +578,7 @@ void Init_ext()
 
   Class rb_cDevice = define_class_under<torch::Device>(rb_mTorch, "Device")
     .define_constructor(Constructor<torch::Device, std::string>())
+    .add_handler<torch::Error>(handle_error)
     .define_method("index", &torch::Device::index)
     .define_method("index?", &torch::Device::has_index)
     .define_method(
@@ -575,6 +590,7 @@ void Init_ext()
       });
 
   Module rb_mCUDA = define_module_under(rb_mTorch, "CUDA")
+    .add_handler<torch::Error>(handle_error)
     .define_singleton_method("available?", &torch::cuda::is_available)
     .define_singleton_method("device_count", &torch::cuda::device_count);
 }

data/lib/torch.rb

@@ -1,6 +1,11 @@
 # ext
 require "torch/ext"
 
+# stdlib
+require "fileutils"
+require "net/http"
+require "tmpdir"
+
 # native functions
 require "torch/native/generator"
 require "torch/native/parser"

data/lib/torch/hub.rb

@@ -5,12 +5,56 @@ module Torch
         raise NotImplementedYet
       end
 
-      def download_url_to_file(url)
-        raise NotImplementedYet
+      def download_url_to_file(url, dst)
+        uri = URI(url)
+        tmp = "#{Dir.tmpdir}/#{Time.now.to_f}" # TODO better name
+        location = nil
+
+        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(tmp, "wb") do |f|
+            http.request(request) do |response|
+              case response
+              when Net::HTTPRedirection
+                location = response["location"]
+              when Net::HTTPSuccess
+                response.read_body do |chunk|
+                  f.write(chunk)
+                end
+              else
+                raise Error, "Bad response"
+              end
+            end
+          end
+        end
+
+        if location
+          download_url_to_file(location, dst)
+        else
+          FileUtils.mv(tmp, dst)
+          nil
+        end
       end
 
-      def load_state_dict_from_url(url)
-        raise NotImplementedYet
+      def load_state_dict_from_url(url, model_dir: nil)
+        unless model_dir
+          torch_home = ENV["TORCH_HOME"] || "#{ENV["XDG_CACHE_HOME"] || "#{ENV["HOME"]}/.cache"}/torch"
+          model_dir = File.join(torch_home, "checkpoints")
+        end
+
+        FileUtils.mkdir_p(model_dir)
+
+        parts = URI(url)
+        filename = File.basename(parts.path)
+        cached_file = File.join(model_dir, filename)
+        unless File.exist?(cached_file)
+          # TODO support hash_prefix
+          download_url_to_file(url, cached_file)
+        end
+
+        Torch.load(cached_file)
       end
     end
   end

data/lib/torch/inspector.rb

@@ -1,6 +1,6 @@
 module Torch
   module Inspector
-    # TODO make more performance, especially when summarizing
+    # TODO make more performant, especially when summarizing
     # how? only read data that will be displayed
     def inspect
       data =
@@ -14,7 +14,7 @@ module Torch
           if dtype == :bool
             fmt = "%s"
           else
-            values = to_a.flatten
+            values = _flat_data
             abs = values.select { |v| v != 0 }.map(&:abs)
             max = abs.max || 1
             min = abs.min || 1

data/lib/torch/tensor.rb

@@ -25,8 +25,17 @@ module Torch
       inspect
     end
 
+    # TODO make more performant
     def to_a
-      reshape_arr(_flat_data, shape)
+      arr = _flat_data
+      if shape.empty?
+        arr
+      else
+        shape[1..-1].reverse.each do |dim|
+          arr = arr.each_slice(dim)
+        end
+        arr.to_a
+      end
     end
 
     # TODO support dtype
@@ -64,7 +73,7 @@ module Torch
       if numel != 1
         raise Error, "only one element tensors can be converted to Ruby scalars"
       end
-      _flat_data.first
+      to_a.first
     end
 
     def to_i
@@ -88,7 +97,7 @@ module Torch
     def numo
       cls = Torch._dtype_to_numo[dtype]
       raise Error, "Cannot convert #{dtype} to Numo" unless cls
-      cls.cast(_flat_data).reshape(*shape)
+      cls.from_string(_data_str).reshape(*shape)
     end
 
     def new_ones(*size, **options)
@@ -116,15 +125,6 @@ module Torch
       _view(size)
     end
 
-    # value and other are swapped for some methods
-    def add!(value = 1, other)
-      if other.is_a?(Numeric)
-        _add__scalar(other, value)
-      else
-        _add__tensor(other, value)
-      end
-    end
-
     def +(other)
       add(other)
     end
@@ -201,6 +201,17 @@ module Torch
       end
     end
 
+    # native functions that need manually defined
+
+    # value and other are swapped for some methods
+    def add!(value = 1, other)
+      if other.is_a?(Numeric)
+        _add__scalar(other, value)
+      else
+        _add__tensor(other, value)
+      end
+    end
+
     # native functions overlap, so need to handle manually
     def random!(*args)
       case args.size
@@ -218,17 +229,5 @@ module Torch
     def copy_to(dst, src)
       dst.copy!(src)
     end
-
-    def reshape_arr(arr, dims)
-      if dims.empty?
-        arr
-      else
-        arr = arr.flatten
-        dims[1..-1].reverse.each do |dim|
-          arr = arr.each_slice(dim)
-        end
-        arr.to_a
-      end
-    end
   end
 end

data/lib/torch/version.rb

@@ -1,3 +1,3 @@
 module Torch
-  VERSION = "0.2.4"
+  VERSION = "0.2.5"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: torch-rb
 version: !ruby/object:Gem::Version
-  version: 0.2.4
+  version: 0.2.5
 platform: ruby
 authors:
 - Andrew Kane
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2020-04-29 00:00:00.000000000 Z
+date: 2020-06-07 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rice