实验2任务3code完成

Lab2/前馈神经网络实验.ipynb

@@ -22,13 +22,13 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "实验环境：\r\n",
-    "- OS：Ubuntu 22.04 (Kernel: 6.2.0-34-generic)\r\n",
-    "- CPU：12th Gen Intel(R) Core(TM) i7-12700H\r\n",
-    "- GPU：NVIDIA GeForce RTX 3070 Ti Laptop\r\n",
-    "- cuda: 12.2\r\n",
-    "- conda: miniconda 23.9.0\r\n",
-    "- python：3.10.13\r\n",
+    "实验环境：\n",
+    "- OS：Ubuntu 22.04 (Kernel: 6.2.0-34-generic)\n",
+    "- CPU：12th Gen Intel(R) Core(TM) i7-12700H\n",
+    "- GPU：NVIDIA GeForce RTX 3070 Ti Laptop\n",
+    "- cuda: 12.2\n",
+    "- conda: miniconda 23.9.0\n",
+    "- python：3.10.13\n",
     "- pytorch：2.1.0"
    ]
   },
@@ -36,12 +36,24 @@
    "cell_type": "code",
    "execution_count": 1,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "ename": "ModuleNotFoundError",
+     "evalue": "No module named 'matplotlib'",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mModuleNotFoundError\u001b[0m                       Traceback (most recent call last)",
+      "\u001b[1;32m/home/kejingfan/Codedir/School-DeepLearningCourse-Lab/Lab2/前馈神经网络实验.ipynb Cell 3\u001b[0m line \u001b[0;36m8\n\u001b[1;32m      <a href='vscode-notebook-cell://wsl%2Bubuntu-22.04/home/kejingfan/Codedir/School-DeepLearningCourse-Lab/Lab2/%E5%89%8D%E9%A6%88%E7%A5%9E%E7%BB%8F%E7%BD%91%E7%BB%9C%E5%AE%9E%E9%AA%8C.ipynb#W2sdnNjb2RlLXJlbW90ZQ%3D%3D?line=5'>6</a>\u001b[0m \u001b[39mfrom\u001b[39;00m \u001b[39mtorch\u001b[39;00m \u001b[39mimport\u001b[39;00m nn\n\u001b[1;32m      <a href='vscode-notebook-cell://wsl%2Bubuntu-22.04/home/kejingfan/Codedir/School-DeepLearningCourse-Lab/Lab2/%E5%89%8D%E9%A6%88%E7%A5%9E%E7%BB%8F%E7%BD%91%E7%BB%9C%E5%AE%9E%E9%AA%8C.ipynb#W2sdnNjb2RlLXJlbW90ZQ%3D%3D?line=6'>7</a>\u001b[0m \u001b[39mfrom\u001b[39;00m \u001b[39mtorchvision\u001b[39;00m \u001b[39mimport\u001b[39;00m datasets, transforms\n\u001b[0;32m----> <a href='vscode-notebook-cell://wsl%2Bubuntu-22.04/home/kejingfan/Codedir/School-DeepLearningCourse-Lab/Lab2/%E5%89%8D%E9%A6%88%E7%A5%9E%E7%BB%8F%E7%BD%91%E7%BB%9C%E5%AE%9E%E9%AA%8C.ipynb#W2sdnNjb2RlLXJlbW90ZQ%3D%3D?line=7'>8</a>\u001b[0m \u001b[39mimport\u001b[39;00m \u001b[39mmatplotlib\u001b[39;00m\u001b[39m.\u001b[39;00m\u001b[39mpyplot\u001b[39;00m \u001b[39mas\u001b[39;00m \u001b[39mplt\u001b[39;00m\n",
+      "\u001b[0;31mModuleNotFoundError\u001b[0m: No module named 'matplotlib'"
+     ]
+    }
+   ],
    "source": [
     "import time\n",
     "import numpy as np\n",
     "import torch\n",
-    "from torch.nn.functional import one_hot, softmax\n",
+    "from torch.nn.functional import *\n",
     "from torch.utils.data import Dataset, DataLoader\n",
     "from torch import nn\n",
     "from torchvision import datasets, transforms\n",
@@ -70,21 +82,21 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "首先生成数据集。\r\n",
-    "\r\n",
-    "一共有3个数据集：\r\n",
-    "\r\n",
-    "1. 回归任务数据集。\r\n",
-    "   - 生成单个数据集。\r\n",
-    "   - 数据集的大小为$10000$且训练集大小为$7000$，测试集大小为$3000$。\r\n",
-    "   - 数据集的样本特征维度$p$为$500$，且服从如下的高维线性函数：$y = 0.028 + \\sum_{p}^{i=1}0.0056 x_i + \\epsilon $。\r\n",
-    "2. 二分类任务数据集。\r\n",
-    "   - 共生成两个数据集。\r\n",
-    "   - 两个数据集的大小均为$10000$且训练集大小为$7000$，测试集大小为$3000$。\r\n",
-    "   - 两个数据集的样本特征$x$的维度均为$200$，且分别服从均值互为相反数且方差相同的正态分布。\r\n",
-    "   - 两个数据集的样本标签分别为$0$和$1$。\r\n",
-    "3. MNIST手写体数据集。\r\n",
-    "   - 该数据集包含$60,000$个用于训练的图像样本和$10,000$个用于测试的图像样本。\r\n",
+    "首先生成数据集。\n",
+    "\n",
+    "一共有3个数据集：\n",
+    "\n",
+    "1. 回归任务数据集。\n",
+    "   - 生成单个数据集。\n",
+    "   - 数据集的大小为$10000$且训练集大小为$7000$，测试集大小为$3000$。\n",
+    "   - 数据集的样本特征维度$p$为$500$，且服从如下的高维线性函数：$y = 0.028 + \\sum_{p}^{i=1}0.0056 x_i + \\epsilon $。\n",
+    "2. 二分类任务数据集。\n",
+    "   - 共生成两个数据集。\n",
+    "   - 两个数据集的大小均为$10000$且训练集大小为$7000$，测试集大小为$3000$。\n",
+    "   - 两个数据集的样本特征$x$的维度均为$200$，且分别服从均值互为相反数且方差相同的正态分布。\n",
+    "   - 两个数据集的样本标签分别为$0$和$1$。\n",
+    "3. MNIST手写体数据集。\n",
+    "   - 该数据集包含$60,000$个用于训练的图像样本和$10,000$个用于测试的图像样本。\n",
     "   - 图像是固定大小（$28\\times 28$像素），其值为$0$到$1$。为每个图像都被平展并转换为$784$（$28 \\times 28$）个特征的一维numpy数组。 "
    ]
   },

requirements.txt

@@ -1,8 +1,9 @@
-black==23.9.1
-ipdb==0.13.13
-jupyter==1.0.0
-numpy==1.26.0
+black
+ipdb
+jupyter
+numpy
 torch==2.1.0
 torchaudio==2.1.0
 torchvision==0.16.0
-tqdm==4.66.1
+tqdm
+matplotlib