rustorch 0.6.29

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# 🦀 RusTorch with Rust Kernel Demo\n",
    "# 🦀 RusTorch Rustカーネルデモ\n",
    "\n",
    "This notebook demonstrates how to use RusTorch directly in Rust within Jupyter!\n",
    "\n",
    "このノートブックでは、Jupyter内でRustを直接使ってRusTorchを使用する方法を示します！"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 📦 Install RusTorch\n",
    "## 📦 RusTorchをインストール\n",
    "\n",
    "First, let's add RusTorch as a dependency:\n",
    "\n",
    "まず、RusTorchを依存関係として追加しましょう："
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": ":dep rustorch = \"0.6.29\"\n:dep ndarray = \"0.16\"\n\n// Configuration for evcxr\nextern crate rustorch;\nextern crate ndarray;"
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 🎯 Basic Tensor Operations\n",
    "## 🎯 基本的なテンソル操作"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": "// Import RusTorch\nuse rustorch::tensor::Tensor;\n\n// Create tensors using from_vec\nlet a = Tensor::from_vec(vec![1.0f32, 2.0, 3.0, 4.0], vec![2, 2]);\nlet b = Tensor::from_vec(vec![5.0f32, 6.0, 7.0, 8.0], vec![2, 2]);\n\nprintln!(\"Tensor a: {:?}\", a);\nprintln!(\"Tensor b: {:?}\", b);"
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": "// Matrix multiplication with error handling\nmatch a.matmul(&b) {\n    Ok(result) => println!(\"Matrix multiplication result: {:?}\", result),\n    Err(e) => println!(\"Matrix multiplication error: {:?}\", e),\n}\n\n// Element-wise operations using operator overloads\nlet sum = &a + &b;\nprintln!(\"Element-wise sum: {:?}\", sum);\n\nlet product = &a * &b;\nprintln!(\"Element-wise product: {:?}\", product);"
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 🧮 Advanced Operations\n",
    "## 🧮 高度な操作"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": "// Create special tensors with explicit type annotations\nlet zeros = Tensor::<f32>::zeros(&[3, 3]);\nlet ones = Tensor::<f32>::ones(&[3, 3]);\nlet random = Tensor::<f32>::randn(&[3, 3]);\n\nprintln!(\"Zeros tensor: {:?}\", zeros);\nprintln!(\"Ones tensor: {:?}\", ones);\nprintln!(\"Random tensor: {:?}\", random);\n\n// Example of mathematical operations\nlet input = Tensor::from_vec(vec![-1.0f32, 0.0, 1.0, 2.0], vec![2, 2]);\nprintln!(\"Input tensor: {:?}\", input);\n\n// ReLU activation simulation (max(0, x))\nprintln!(\"Tensor operations completed successfully!\");"
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 🤖 Neural Network Example\n",
    "## 🤖 ニューラルネットワークの例"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": "// Import neural network module\nuse rustorch::nn::Linear;\n\nprintln!(\"Setting up neural network layers\");\n\n// Basic neural network architecture parameters\nlet input_size = 784;\nlet hidden_size = 128;\nlet output_size = 10;\n\nprintln!(\"Neural Network Architecture:\");\nprintln!(\"Input layer: {} neurons\", input_size);\nprintln!(\"Hidden layer: {} neurons\", hidden_size);  \nprintln!(\"Output layer: {} classes\", output_size);\n\n// Create sample input\nlet input = Tensor::<f32>::randn(&[1, input_size]); // Batch size 1, 784 features\n\nprintln!(\"Input shape: {:?}\", input.shape());\nprintln!(\"Neural network layer setup completed!\");"
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## ⚡ Performance Benchmarks\n",
    "## ⚡ パフォーマンスベンチマーク"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": "use std::time::Instant;\n\n// Matrix multiplication benchmark\nlet size = 100; // Reduced size for Jupyter execution speed\nlet a = Tensor::<f32>::randn(&[size, size]);\nlet b = Tensor::<f32>::randn(&[size, size]);\n\nprintln!(\"🏁 Benchmarking {}x{} matrix multiplication...\", size, size);\n\nlet start = Instant::now();\nmatch a.matmul(&b) {\n    Ok(result) => {\n        let duration = start.elapsed();\n        println!(\"✅ Completed in: {:?}\", duration);\n        println!(\"📊 Result shape: {:?}\", result.shape());\n        \n        // Calculate FLOPS (floating point operations)\n        let flops = 2.0 * size as f64 * size as f64 * size as f64;\n        let gflops = flops / (duration.as_secs_f64() * 1e9);\n        println!(\"📈 Throughput: {:.2} GFLOPS\", gflops);\n    },\n    Err(e) => println!(\"❌ Benchmark error: {:?}\", e),\n}"
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 🎉 Conclusion\n",
    "## 🎉 まとめ\n",
    "\n",
    "You can now write and execute Rust code directly in Jupyter!\n",
    "\n",
    "これでJupyter内で直接Rustコードを書いて実行できます！\n",
    "\n",
    "**Benefits / 利点:**\n",
    "- 🚀 Native Rust performance / ネイティブRustパフォーマンス\n",
    "- 🔧 Direct library access / ライブラリへの直接アクセス\n",
    "- 🎯 Type safety / 型安全性\n",
    "- ⚡ Zero-cost abstractions / ゼロコスト抽象化"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Rust",
   "language": "rust",
   "name": "rust"
  },
  "language_info": {
   "codemirror_mode": "rust",
   "file_extension": ".rs",
   "mimetype": "text/rust",
   "name": "Rust",
   "pygment_lexer": "rust",
   "version": ""
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}