百科.dev
全部条目在线工具AI 编程趋势榜开源项目技术资讯提交条目
登录
< 返回工具列表
T

tensorflow-ruby

> 编程语言
开源

深度学习 适用于 Ruby

383 stars0 点赞0 次浏览
访问官网GitHub

工具介绍

深度学习 适用于 Ruby

TensorFlow Ruby

:fire: TensorFlow - the end-to-end machine learning platform - for Ruby

This gem is currently experimental and only supports basic tensor operations at the moment. Check out Torch.rb for a more complete deep learning library.

To run a TensorFlow model in Ruby, convert it to ONNX and use ONNX Runtime. Check out this tutorial for a full example.

Installation

Install TensorFlow. For Homebrew, use:

bash
brew install libtensorflow

Add this line to your application’s Gemfile:

ruby
gem "tensorflow"

Getting Started

This library follows the TensorFlow 2 Python API. Many methods and options are missing at the moment. Here’s the current plan. Additional PRs welcome!

Constants

ruby
a = Tf.constant([1, 2, 3])
b = Tf.constant([4, 5, 6])
a + b

Variables

ruby
v = Tf::Variable.new(0.0)
w = v + 1

Math

ruby
Tf::Math.abs([-1, -2])
Tf::Math.sqrt([1.0, 4.0, 9.0])

FizzBuzz

ruby
def fizzbuzz(max_num)
  max_num.times do |i|
    num = Tf.constant(i + 1)
    if (num % 3).to_i == 0 && (num % 5).to_i == 0
      puts "FizzBuzz"
    elsif (num % 3).to_i == 0
      puts "Fizz"
    elsif (num % 5).to_i == 0
      puts "Buzz"
    else
      puts num.to_i
    end
  end
end

fizzbuzz(15)

Data::Dataset

ruby
# load
train_dataset = Tf::Data::Dataset.from_tensor_slices([train_examples, train_labels])
test_dataset = Tf::Data::Dataset.from_tensor_slices([test_examples, test_labels])

# shuffle and batch
train_dataset = train_dataset.shuffle(100).batch(32)
test_dataset = test_dataset.batch(32)

# iterate
train_dataset.each do |examples, labels|
  # ...
end

Keras [coming soon]

ruby
mnist = Tf::Keras::Datasets::MNIST
(x_train, y_train), (x_test, y_test) = mnist.load_data
x_train = x_train / 255.0
x_test = x_test / 255.0

model = Tf::Keras::Models::Sequential.new([
  Tf::Keras::Layers::Flatten.new(input_shape: [28, 28]),
  Tf::Keras::Layers::Dense.new(128, activation: "relu"),
  Tf::Keras::Layers::Dropout.new(0.2),
  Tf::Keras::Layers::Dense.new(10, activation: "softmax")
])

model.compile(optimizer: "adam", loss: "sparse_categorical_crossentropy", metrics: ["accuracy"])
model.fit(x_train, y_train, epochs: 5)
model.evaluate(x_test, y_test)

TensorFlow Installation

Mac

Run:

bash
brew install tensorflow

Alternatively, download the shared library and move the files in lib to /usr/local/lib.

Linux

Download the shared library and move the files in lib to /usr/local/lib.

Windows

Download the shared library and move tensorflow.dll to C:\Windows\System32.

History

View the changelog

Contributing

Everyone is encouraged to help improve this project. Here are a few ways you can help:

  • Report bugs
  • Fix bugs and submit pull requests
  • Write, clarify, or fix documentation
  • Suggest or add new features

To get started with development:

bash
git clone https://github.com/ankane/tensorflow-ruby.git
cd tensorflow-ruby
bundle install
bundle exec rake test

Issues· 0 开放

查看全部 Issues在 GitHub 打开

暂无开放 Issues,或尚未同步最近议题。

> 标签

Ruby

暂无评论,来聊聊你的看法吧

> 工具信息

发布日期2026年8月1日
最后更新2026年9月17日
分类编程语言
定价开源

> 相关工具

T
TypeScript
JavaScript 的超集,为前端与全栈提供静态类型
P
Python
通用编程语言,广泛用于 Web、数据与 AI
G
Go
Google 推出的简洁高效系统语言