{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": ["# Attendance CNN — training notebook (demo)"]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "%matplotlib inline\n",
    "import torch\n",
    "import torch.nn as nn\n",
    "!pip install torchvision -q"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "class AttendanceCNN(nn.Module):\n",
    "    def __init__(self, num_classes=40):\n",
    "        super().__init__()\n",
    "        self.conv1 = nn.Conv2d(3, 16, kernel_size=3, padding=1)\n",
    "        self.relu1 = nn.ReLU()\n",
    "        self.pool1 = nn.MaxPool2d(2, 2)\n",
    "        self.conv2 = nn.Conv2d(16, 32, kernel_size=3, padding=1)\n",
    "        self.relu2 = nn.ReLU()\n",
    "        self.pool2 = nn.MaxPool2d(2, 2)\n",
    "        self.flatten = nn.Flatten()\n",
    "        self.fc1 = nn.Linear(32 * 32 * 32, 96)\n",
    "        self.dropout = nn.Dropout(0.25)\n",
    "        self.fc2 = nn.Linear(96, num_classes)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "    def forward(self, x):\n",
    "        x = self.pool1(self.relu1(self.conv1(x)))\n",
    "        x = self.pool2(self.relu2(self.conv2(x)))\n",
    "        x = self.flatten(x)\n",
    "        x = self.dropout(self.fc1(x))\n",
    "        return self.fc2(x)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {"display_name": "Python 3", "language": "python", "name": "python3"},
  "language_info": {"name": "python", "version": "3.11"}
 },
 "nbformat": 4,
 "nbformat_minor": 5
}