{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/duoan/TorchCode/blob/master/templates/01_relu.ipynb)\n",
    "\n",
    "# 🟢 Easy: Implement ReLU\n",
    "\n",
    "Implement the **ReLU** (Rectified Linear Unit) activation function from scratch.\n",
    "\n",
    "$$\\text{ReLU}(x) = \\max(0, x)$$\n",
    "\n",
    "### Signature\n",
    "```python\n",
    "def relu(x: torch.Tensor) -> torch.Tensor:\n",
    "    ...\n",
    "```\n",
    "\n",
    "### Rules\n",
    "- Do **NOT** use `torch.relu`, `F.relu`, `torch.clamp`, or any built-in activation\n",
    "- Must support autograd (gradients should flow back)\n",
    "\n",
    "### Example\n",
    "```\n",
    "Input:  tensor([-2., -1., 0., 1., 2.])\n",
    "Output: tensor([ 0.,  0., 0., 1., 2.])\n",
    "```"
   ],
   "outputs": []
  },
  {
   "cell_type": "code",
   "metadata": {},
   "source": [
    "# Install torch-judge in Colab (no-op in JupyterLab/Docker)\n",
    "try:\n",
    "    import google.colab\n",
    "    get_ipython().run_line_magic('pip', 'install -q torch-judge')\n",
    "except ImportError:\n",
    "    pass\n"
   ],
   "outputs": [],
   "execution_count": null
  },
  {
   "cell_type": "code",
   "metadata": {},
   "source": [
    "import torch"
   ],
   "outputs": [],
   "execution_count": null
  },
  {
   "cell_type": "code",
   "metadata": {},
   "source": [
    "# ✏️ YOUR IMPLEMENTATION HERE\n",
    "\n",
    "def relu(x: torch.Tensor) -> torch.Tensor:\n",
    "    pass  # Replace this\n",
    ""
   ],
   "outputs": [],
   "execution_count": null
  },
  {
   "cell_type": "code",
   "metadata": {},
   "source": [
    "# 🧪 Test your implementation (feel free to add more debug prints)\n",
    "x = torch.tensor([-2., -1., 0., 1., 2.])\n",
    "print(\"Input: \", x)\n",
    "print(\"Output:\", relu(x))\n",
    "print(\"Shape: \", relu(x).shape)"
   ],
   "outputs": [],
   "execution_count": null
  },
  {
   "cell_type": "code",
   "metadata": {},
   "source": [
    "# ✅ SUBMIT — Run this cell to check your solution\n",
    "from torch_judge import check\n",
    "check(\"relu\")"
   ],
   "outputs": [],
   "execution_count": null
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.11.14"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}