{
 "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/18_embedding.ipynb)\n",
    "\n",
    "# 🟢 Easy: Embedding Layer\n",
    "\n",
    "Implement an **embedding lookup table** from scratch.\n",
    "\n",
    "### Signature\n",
    "```python\n",
    "class MyEmbedding(nn.Module):\n",
    "    def __init__(self, num_embeddings: int, embedding_dim: int): ...\n",
    "    def forward(self, indices: Tensor) -> Tensor: ...\n",
    "```\n",
    "\n",
    "### Rules\n",
    "- `self.weight`: `nn.Parameter` of shape `(num_embeddings, embedding_dim)`\n",
    "- Forward: index into weight matrix — `weight[indices]`\n",
    "- Do NOT use `nn.Embedding`"
   ],
   "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": {},
   "outputs": [],
   "source": [
    "import torch\n",
    "import torch.nn as nn"
   ],
   "execution_count": null
  },
  {
   "cell_type": "code",
   "metadata": {},
   "outputs": [],
   "source": [
    "# ✏️ YOUR IMPLEMENTATION HERE\n",
    "\n",
    "class MyEmbedding(nn.Module):\n",
    "    def __init__(self, num_embeddings, embedding_dim):\n",
    "        super().__init__()\n",
    "        pass\n",
    "\n",
    "    def forward(self, indices):\n",
    "        pass"
   ],
   "execution_count": null
  },
  {
   "cell_type": "code",
   "metadata": {},
   "outputs": [],
   "source": [
    "# 🧪 Debug\n",
    "emb = MyEmbedding(10, 4)\n",
    "idx = torch.tensor([0, 3, 7])\n",
    "print('Output shape:', emb(idx).shape)\n",
    "print('Matches manual:', torch.equal(emb(idx)[0], emb.weight[0]))"
   ],
   "execution_count": null
  },
  {
   "cell_type": "code",
   "metadata": {},
   "outputs": [],
   "source": [
    "# ✅ SUBMIT\n",
    "from torch_judge import check\n",
    "check('embedding')"
   ],
   "execution_count": null
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "name": "python",
   "version": "3.11.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}