{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "ed9e0a13",
   "metadata": {},
   "outputs": [],
   "source": [
    "import torch\n",
    "from torch import nn\n",
    "from torch.utils.data import DataLoader\n",
    "from torchvision import datasets\n",
    "from torchvision.transforms import v2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "c838fd53",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100.0%\n",
      "100.0%\n",
      "100.0%\n",
      "100.0%\n"
     ]
    }
   ],
   "source": [
    "training_data = datasets.FashionMNIST(\n",
    "    root=\"data\",\n",
    "    train=True,\n",
    "    download=True,\n",
    "    transform=v2.Compose([v2.ToImage(), v2.ToDtype(torch.float32, scale=True)]),\n",
    ")\n",
    "\n",
    "test_data = datasets.FashionMNIST(\n",
    "    root=\"data\",\n",
    "    train=False,\n",
    "    download=True,\n",
    "    transform=v2.Compose([v2.ToImage(), v2.ToDtype(torch.float32, scale=True)]),\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "744a8ecb",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Shape of X [N, C, H, W]: torch.Size([64, 1, 28, 28])\n",
      "Shape of y: torch.Size([64]) torch.int64\n"
     ]
    }
   ],
   "source": [
    "batch_size = 64\n",
    "\n",
    "train_dataloader = DataLoader(training_data, batch_size=batch_size)\n",
    "test_dataloader = DataLoader(test_data, batch_size=batch_size)\n",
    "\n",
    "for X, y in test_dataloader:\n",
    "    print(f\"Shape of X [N, C, H, W]: {X.shape}\")\n",
    "    print(f\"Shape of y: {y.shape} {y.dtype}\")\n",
    "    break"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "25639067",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Using cuda device\n",
      "NeuralNetwork(\n",
      "  (flatten): Flatten(start_dim=1, end_dim=-1)\n",
      "  (linear_relu_stack): Sequential(\n",
      "    (0): Linear(in_features=784, out_features=512, bias=True)\n",
      "    (1): ReLU()\n",
      "    (2): Linear(in_features=512, out_features=512, bias=True)\n",
      "    (3): ReLU()\n",
      "    (4): Linear(in_features=512, out_features=10, bias=True)\n",
      "  )\n",
      ")\n"
     ]
    }
   ],
   "source": [
    "device = torch.accelerator.current_accelerator().type if torch.accelerator.is_available() else \"cpu\"\n",
    "print(f\"Using {device} device\")\n",
    "\n",
    "class NeuralNetwork(nn.Module):\n",
    "    def __init__(self):\n",
    "        super().__init__()\n",
    "        self.flatten = nn.Flatten()\n",
    "        self.linear_relu_stack = nn.Sequential(\n",
    "            nn.Linear(28*28, 512),\n",
    "            nn.ReLU(),\n",
    "            nn.Linear(512, 512),\n",
    "            nn.ReLU(),\n",
    "            nn.Linear(512, 10)\n",
    "        )\n",
    "    def forward(self, x):\n",
    "        x = self.flatten(x)\n",
    "        logits = self.linear_relu_stack(x)\n",
    "        return logits\n",
    "    \n",
    "model = NeuralNetwork().to(device)\n",
    "print(model)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "4d995f06",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": ".venv (3.11.15)",
   "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": "3.11.15"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}