Add files via upload

屈铄/1.ipynb

@@ -0,0 +1,121 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "ModuleNotFoundError",
+     "evalue": "No module named 'd2l'",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[1;31mModuleNotFoundError\u001b[0m                       Traceback (most recent call last)",
+      "Cell \u001b[1;32mIn[3], line 3\u001b[0m\n\u001b[0;32m      1\u001b[0m \u001b[38;5;28;01mimport\u001b[39;00m \u001b[38;5;21;01mtorch\u001b[39;00m\n\u001b[0;32m      2\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtorch\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m nn\n\u001b[1;32m----> 3\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01md2l\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m torch \u001b[38;5;28;01mas\u001b[39;00m d2l\n\u001b[0;32m      5\u001b[0m batch_size \u001b[38;5;241m=\u001b[39m \u001b[38;5;241m256\u001b[39m\n\u001b[0;32m      6\u001b[0m train_iter, test_iter \u001b[38;5;241m=\u001b[39m d2l\u001b[38;5;241m.\u001b[39mload_data_fashion_mnist(batch_size)\n",
+      "\u001b[1;31mModuleNotFoundError\u001b[0m: No module named 'd2l'"
+     ]
+    }
+   ],
+   "source": [
+    "import torch\n",
+    "from torch import nn\n",
+    "from d2l import torch as d2l\n",
+    "\n",
+    "batch_size = 256\n",
+    "train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "num_inputs, num_outputs, num_hiddens = 784, 10, 256\n",
+    "\n",
+    "W1 = nn.Parameter(torch.randn(\n",
+    "    num_inputs, num_hiddens, requires_grad=True) * 0.01)\n",
+    "b1 = nn.Parameter(torch.zeros(num_hiddens, requires_grad=True))\n",
+    "W2 = nn.Parameter(torch.randn(\n",
+    "    num_hiddens, num_outputs, requires_grad=True) * 0.01)\n",
+    "b2 = nn.Parameter(torch.zeros(num_outputs, requires_grad=True))\n",
+    "\n",
+    "params = [W1, b1, W2, b2]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def relu(X):\n",
+    "    a = torch.zeros_like(X)\n",
+    "    return torch.max(X, a)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def net(X):\n",
+    "    X = X.reshape((-1, num_inputs))\n",
+    "    H = relu(X@W1 + b1)  # @ 矩阵乘法\n",
+    "    return (H@W2 + b2)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "loss = nn.CrossEntropyLoss(reduction='none')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "num_epochs, lr = 10, 0.1\n",
+    "updater = torch.optim.SGD(params, lr=lr)\n",
+    "d2l.train_ch3(net, train_iter, test_iter, loss, num_epochs, updater)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "d2l.predict_ch3(net, test_iter)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "pytorch",
+   "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": "3.11.7"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}