kejingfan/Deep_Learning
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

实验2任务3code完成

Browse Source
This commit is contained in:
typingbugs 2023-10-24 16:35:58 +08:00
parent 52ef87ec87
commit 7e8fea0a3b
2 changed files with 42 additions and 29 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

60
Lab2/前馈神经网络实验.ipynb
View File

@ -22,13 +22,13 @@
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"实验环境：\r\n", "实验环境：\n",
"- OS：Ubuntu 22.04 (Kernel: 6.2.0-34-generic)\r\n", "- OS：Ubuntu 22.04 (Kernel: 6.2.0-34-generic)\n",
"- CPU：12th Gen Intel(R) Core(TM) i7-12700H\r\n", "- CPU：12th Gen Intel(R) Core(TM) i7-12700H\n",
"- GPU：NVIDIA GeForce RTX 3070 Ti Laptop\r\n", "- GPU：NVIDIA GeForce RTX 3070 Ti Laptop\n",
"- cuda: 12.2\r\n", "- cuda: 12.2\n",
"- conda: miniconda 23.9.0\r\n", "- conda: miniconda 23.9.0\n",
"- python：3.10.13\r\n", "- python：3.10.13\n",
"- pytorch：2.1.0" "- pytorch：2.1.0"
] ]
}, },
@ -36,12 +36,24 @@
"cell_type": "code", "cell_type": "code",
"execution_count": 1, "execution_count": 1,
"metadata": {}, "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": [ "source": [
"import time\n", "import time\n",
"import numpy as np\n", "import numpy as np\n",
"import torch\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.utils.data import Dataset, DataLoader\n",
"from torch import nn\n", "from torch import nn\n",
"from torchvision import datasets, transforms\n", "from torchvision import datasets, transforms\n",
@ -70,21 +82,21 @@
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"首先生成数据集。\r\n", "首先生成数据集。\n",
"\r\n", "\n",
"一共有3个数据集：\r\n", "一共有3个数据集：\n",
"\r\n", "\n",
"1. 回归任务数据集。\r\n", "1. 回归任务数据集。\n",
" - 生成单个数据集。\r\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$3000$。\r\n", " - 数据集的大小为$10000$且训练集大小为$7000$，测试集大小为$3000$。\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 $。\r\n", " - 数据集的样本特征维度$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。\r\n", "2. 二分类任务数据集。\n",
" - 共生成两个数据集。\r\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$3000$。\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$3000$。\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$1$。\r\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。\r\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。\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。\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。 " " - 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。 "
] ]
}, },

11
requirements.txt
View File

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