diff --git a/.gitignore b/.gitignore index 378aeaf..c711c3b 100644 --- a/.gitignore +++ b/.gitignore @@ -1,3 +1,5 @@ dataset/ .vscode/ + +.ipynb_checkpoints/ \ No newline at end of file diff --git a/Lab1/.ipynb_checkpoints/Pytorch基本操作实验报告-checkpoint.ipynb b/Lab1/.ipynb_checkpoints/Pytorch基本操作实验报告-checkpoint.ipynb deleted file mode 100644 index ac0b0e3..0000000 --- a/Lab1/.ipynb_checkpoints/Pytorch基本操作实验报告-checkpoint.ipynb +++ /dev/null @@ -1,1325 +0,0 @@ -{ - "cells": [ - { - "cell_type": "markdown", - "id": "3b57686b-7ac8-4897-bf76-3d982b1ff8da", - "metadata": {}, - "source": [ - "

\"school-logo\"

\n", - "\n", - "

本科生《深度学习》课程
实验报告

\n", - "
\n", - "
课程名称:深度学习
\n", - "
实验题目:Pytorch基本操作
\n", - "
学号:21281280
\n", - "
姓名:柯劲帆
\n", - "
班级:物联网2101班
\n", - "
指导老师:张淳杰
\n", - "
报告日期:2023年10月9日
\n", - "
" - ] - }, - { - "cell_type": "markdown", - "id": "e24aa17e-faf9-4d69-9eae-43159116b56f", - "metadata": {}, - "source": [ - "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" - ] - }, - { - "cell_type": "code", - "execution_count": 1, - "id": "a4e12268-bad4-44c4-92d5-883624d93e25", - "metadata": {}, - "outputs": [], - "source": [ - "import numpy as np\n", - "import torch\n", - "from torch.autograd import Variable\n", - "from torch.utils.data import Dataset, DataLoader\n", - "from torch import nn\n", - "from torchvision import datasets, transforms" - ] - }, - { - "cell_type": "markdown", - "id": "cc7f0ce5-d613-425b-807c-78115632cd80", - "metadata": {}, - "source": [ - "引用相关库。" - ] - }, - { - "cell_type": "markdown", - "id": "59a43d35-56ac-4ade-995d-1c6fcbcd1262", - "metadata": {}, - "source": [ - "# 一、Pytorch基本操作考察\n", - "## 题目2\n", - "**使用 𝐓𝐞𝐧𝐬𝐨𝐫 初始化一个 𝟏×𝟑 的矩阵 𝑴 和一个 𝟐×𝟏 的矩阵 𝑵，对两矩阵进行减法操作（要求实现三种不同的形式），给出结果并分析三种方式的不同（如果出现报错，分析报错的原因），同时需要指出在计算过程中发生了什么。**" - ] - }, - { - "cell_type": "code", - "execution_count": 2, - "id": "79ea46db-cf49-436c-9b5b-c6562d0da9e2", - "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "方法1的结果:\n", - "tensor([[-3, -2, -1],\n", - " [-4, -3, -2]])\n", - "方法2的结果:\n", - "tensor([[-3, -2, -1],\n", - " [-4, -3, -2]])\n", - "方法3的结果:\n", - "tensor([[-3, -2, -1],\n", - " [-4, -3, -2]])\n" - ] - } - ], - "source": [ - "A = torch.tensor([[1, 2, 3]])\n", - "\n", - "B = torch.tensor([[4],\n", - " [5]])\n", - "\n", - "# 方法1: 使用PyTorch的减法操作符\n", - "result1 = A - B\n", - "\n", - "# 方法2: 使用PyTorch的sub函数\n", - "result2 = torch.sub(A, B)\n", - "\n", - "# 方法3: 手动实现广播机制并作差\n", - "def my_sub(a:torch.Tensor, b:torch.Tensor):\n", - " if not ((a.size(0) == 1 and b.size(1) == 1) or (a.size(1) == 1 and b.size(0) == 1)):\n", - " raise ValueError(\"输入的张量大小无法满足广播机制的条件。\")\n", - " else:\n", - " target_shape = torch.Size([max(A.size(0), B.size(0)), max(A.size(1), B.size(1))])\n", - " A_broadcasted = A.expand(target_shape)\n", - " B_broadcasted = B.expand(target_shape)\n", - " result = torch.zeros(target_shape, dtype=torch.int64).to(device=A_broadcasted.device)\n", - " for i in range(target_shape[0]):\n", - " for j in range(target_shape[1]):\n", - " result[i, j] = A_broadcasted[i, j] - B_broadcasted[i, j]\n", - " return result\n", - "\n", - "result3 = my_sub(A, B)\n", - "\n", - "print(\"方法1的结果:\")\n", - "print(result1)\n", - "print(\"方法2的结果:\")\n", - "print(result2)\n", - "print(\"方法3的结果:\")\n", - "print(result3)" - ] - }, - { - "cell_type": "markdown", - "id": "bd9bd5cc-b6da-4dd6-a599-76498bc5247d", - "metadata": {}, - "source": [ - "第1、2、3种减法形式实质是一样的。\n", - "\n", - "步骤如下：\n", - "1. 对A、B两个张量进行广播，将A、B向广播的方向复制，得到两个$\\max(A.size(0), B.size(0))\\times \\max(A.size(1), B.size(1))$的张量；\n", - "2. 对广播后的两个张量作差，尺寸不变。\n", - "\n", - "第1种减法形式和第2种是等价的，前者是后者的符号化表示。\n", - "\n", - "第3种形式是手动实现的，将上述两个步骤分别手动实现了。但是torch.Tensor还内置了其他机制，这里仅模拟了广播和作差。" - ] - }, - { - "cell_type": "markdown", - "id": "2489a3ad-f6ff-4561-bb26-e02654090b98", - "metadata": {}, - "source": [ - "## 题目2\n", - "1. **利用Tensor创建两个大小分别$3\\times 2$和$4\\times 2$的随机数矩阵$P$和$Q$，要求服从均值为$0$，标准差$0.01$为的正态分布；**\n", - "2. **对第二步得到的矩阵$Q$进行形状变换得到$Q$的转置$Q^T$；**\n", - "3. **对上述得到的矩阵$P$和矩阵$Q^T$求矩阵相乘。**" - ] - }, - { - "cell_type": "code", - "execution_count": 3, - "id": "41e4ee02-1d05-4101-b3f0-477bac0277fb", - "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "矩阵 P:\n", - "tensor([[ 0.0069, 0.0082],\n", - " [-0.0052, -0.0124],\n", - " [ 0.0055, -0.0014]])\n", - "矩阵 Q:\n", - "tensor([[ 0.0050, 0.0075],\n", - " [ 0.0161, 0.0070],\n", - " [-0.0009, -0.0014],\n", - " [-0.0003, 0.0024]])\n", - "矩阵 QT:\n", - "tensor([[ 0.0050, 0.0161, -0.0009, -0.0003],\n", - " [ 0.0075, 0.0070, -0.0014, 0.0024]])\n", - "矩阵相乘的结果:\n", - "tensor([[ 9.6016e-05, 1.6860e-04, -1.7451e-05, 1.8011e-05],\n", - " [-1.1894e-04, -1.7065e-04, 2.1900e-05, -2.8712e-05],\n", - " [ 1.6918e-05, 7.8455e-05, -2.7165e-06, -4.9904e-06]])\n" - ] - } - ], - "source": [ - "mean = 0\n", - "stddev = 0.01\n", - "\n", - "P = torch.normal(mean=mean, std=stddev, size=(3, 2))\n", - "Q = torch.normal(mean=mean, std=stddev, size=(4, 2))\n", - "\n", - "print(\"矩阵 P:\")\n", - "print(P)\n", - "print(\"矩阵 Q:\")\n", - "print(Q)\n", - "\n", - "# 对矩阵Q进行转置操作，得到矩阵Q的转置Q^T\n", - "QT = Q.T\n", - "print(\"矩阵 QT:\")\n", - "print(QT)\n", - "\n", - "# 计算矩阵P和矩阵Q^T的矩阵相乘\n", - "result = torch.matmul(P, QT)\n", - "print(\"矩阵相乘的结果:\")\n", - "print(result)" - ] - }, - { - "cell_type": "markdown", - "id": "cea9cb6d-adde-4e08-b9f2-8c417abf4231", - "metadata": {}, - "source": [ - "## 题目2\n", - "**给定公式$ y_3=y_1+y_2=𝑥^2+𝑥^3$，且$x=1$。利用学习所得到的Tensor的相关知识，求$y_3$对$x$的梯度，即$\\frac{dy_3}{dx}$。**" - ] - }, - { - "cell_type": "code", - "execution_count": 4, - "id": "951512cd-d915-4d04-959f-eb99d1971e2d", - "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "仅通过y_1传递的梯度: 2.0\n", - "仅通过y_2传递的梯度: 3.0\n", - "dy_3/dx: 5.0\n" - ] - } - ], - "source": [ - "x = torch.tensor(1.0, requires_grad=True)\n", - "\n", - "y_1 = x ** 2\n", - "with torch.no_grad():\n", - " y_2 = x ** 3\n", - "y_3 = y_1 + y_2\n", - "y_3.backward()\n", - "print(\"仅通过y_1传递的梯度: \", x.grad.item())\n", - "\n", - "x.grad.data.zero_()\n", - "with torch.no_grad():\n", - " y_1 = x ** 2\n", - "y_2 = x ** 3\n", - "y_3 = y_1 + y_2\n", - "y_3.backward()\n", - "print(\"仅通过y_2传递的梯度: \", x.grad.item())\n", - "\n", - "x.grad.data.zero_()\n", - "y_1 = x ** 2\n", - "y_2 = x ** 3\n", - "y_3 = y_1 + y_2\n", - "y_3.backward()\n", - "\n", - "print(\"dy_3/dx: \", x.grad.item())" - ] - }, - { - "cell_type": "markdown", - "id": "3269dbf6-889a-49eb-8094-1e588e1a6c30", - "metadata": {}, - "source": [ - "# 二、动手实现logistic回归\n", - "## 题目1\n", - "**要求动手从0实现 logistic 回归（只借助Tensor和Numpy相关的库）在人工构造的数据集上进行训练和测试，并从loss以及训练集上的准确率等多个角度对结果进行分析（可借助nn.BCELoss或nn.BCEWithLogitsLoss作为损失函数，从零实现二元交叉熵为选作）**" - ] - }, - { - "cell_type": "markdown", - "id": "bcd12aa9-f187-4d88-8c59-af6d16107edb", - "metadata": {}, - "source": [ - "给定预测概率$ \\left( \\hat{y} \\right) $和目标标签$ \\left( y \\right)$（通常是0或1），BCELoss的计算公式如下：\n", - "$$\n", - " \\text{BCELoss}(\\hat{y}, y) = -\\frac{1}{N} \\sum_{i=1}^{N} \\left(y_i \\cdot \\log(\\hat{y}_i) + (1 - y_i) \\cdot \\log(1 - \\hat{y}_i)\\right) \n", - "$$\n", - "其中，$\\left( N \\right) $是样本数量，$\\left( \\hat{y}_i \\right) $表示模型的预测概率向量中的第$ \\left( i \\right) $个元素，$\\left( y_i \\right) $表示实际的目标标签中的第$ \\left( i \\right) $个元素。在二分类问题中，$\\left( y_i \\right) $通常是0或1。这个公式表示对所有样本的二分类交叉熵损失进行了求和并取平均。\n", - "\n", - "因此BCELoss的手动实现如下。" - ] - }, - { - "cell_type": "code", - "execution_count": 5, - "id": "e31b86ec-4114-48dd-8d73-fe4e0686419a", - "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "输入：\n", - "tensor([0.6900])\n", - "标签：\n", - "tensor([1.])\n", - "My_BCELoss损失值: 0.37110066413879395\n", - "nn.BCELoss损失值: 0.37110066413879395\n" - ] - } - ], - "source": [ - "class My_BCELoss:\n", - " def __call__(self, prediction: torch.Tensor, target: torch.Tensor):\n", - " loss = -torch.mean(target * torch.log(prediction) + (1 - target) * torch.log(1 - prediction))\n", - " return loss\n", - "\n", - "\n", - "# 测试\n", - "prediction = torch.sigmoid(torch.tensor([0.8]))\n", - "target = torch.tensor([1.0])\n", - "print(f\"输入：\\n{prediction}\")\n", - "print(f\"标签：\\n{target}\")\n", - "\n", - "my_bce_loss = My_BCELoss()\n", - "my_loss = my_bce_loss(prediction, target)\n", - "print(\"My_BCELoss损失值:\", my_loss.item())\n", - "\n", - "nn_bce_loss = nn.BCELoss()\n", - "nn_loss = nn_bce_loss(prediction, target)\n", - "print(\"nn.BCELoss损失值:\", nn_loss.item())" - ] - }, - { - "cell_type": "markdown", - "id": "345b0300-8808-4c43-9bf9-05a7e6e1f5af", - "metadata": {}, - "source": [ - "Optimizer的实现较为简单。\n", - "\n", - "主要实现：\n", - "- 传入参数：`__init__()`\n", - "- 对传入的参数进行更新：`step()`\n", - "- 清空传入参数存储的梯度：`zero_grad()`\n", - "\n", - "但是有一点需要注意，就是需要将传进来的`params`参数转化为`list`类型。因为`nn.Module`的`parameters()`方法会以``的类型返回模型的参数，但是该类型变量无法像`list`一样使用`for`循环遍历。" - ] - }, - { - "cell_type": "code", - "execution_count": 6, - "id": "0297066c-9fc1-448d-bdcb-29a6f1519117", - "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "x的初始值: 1.0\n", - "学习率: 0.1\n", - "y.backward()之后，x的梯度: 2.0\n", - "optimizer_test.step()之后，x的值: 0.800000011920929\n", - "optimizer_test.zero_grad()之后，x的梯度: 0.0\n" - ] - } - ], - "source": [ - "class My_Optimizer:\n", - " def __init__(self, params: list[torch.Tensor], lr: float):\n", - " self.params = list(params)\n", - " self.lr = lr\n", - "\n", - " def step(self):\n", - " for param in self.params:\n", - " param.data = param.data - self.lr * param.grad.data\n", - "\n", - " def zero_grad(self):\n", - " for param in self.params:\n", - " if param.grad is not None:\n", - " param.grad.data.zero_()\n", - "\n", - "\n", - "# 测试\n", - "x = torch.tensor(1.0, requires_grad=True)\n", - "print(\"x的初始值: \", x.item())\n", - "\n", - "optimizer_test = My_Optimizer([x], lr=0.1)\n", - "print(\"学习率: \", optimizer_test.lr)\n", - "\n", - "y = x ** 2\n", - "y.backward()\n", - "print(\"y.backward()之后，x的梯度: \", x.grad.item())\n", - "\n", - "optimizer_test.step()\n", - "print(\"optimizer_test.step()之后，x的值: \", x.item())\n", - "\n", - "optimizer_test.zero_grad()\n", - "print(\"optimizer_test.zero_grad()之后，x的梯度: \", x.grad.item())" - ] - }, - { - "cell_type": "markdown", - "id": "6ab83528-a88b-4d66-b0c9-b1315cf75c22", - "metadata": {}, - "source": [ - "线性层主要有一个权重（weight)和一个偏置（bias）。\n", - "线性层的数学公式如下：\n", - "$$\n", - "x:=x \\times weight^T+bias\n", - "$$\n", - "因此代码实现如下：" - ] - }, - { - "cell_type": "code", - "execution_count": 7, - "id": "8e18695a-d8c5-4f77-8b5c-de40d9240fb9", - "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "输入：\n", - "tensor([[1.],\n", - " [2.]], requires_grad=True)\n", - "权重：\n", - "tensor([[ 0.4240],\n", - " [-0.2577],\n", - " [ 0.4972]])\n", - "偏置：\n", - "tensor([0.6298, 0.6243, 0.8217])\n", - "My_Linear输出：\n", - "tensor([[1.0539, 0.3666, 1.3189],\n", - " [1.4779, 0.1089, 1.8161]], grad_fn=)\n", - "nn.Linear输出：\n", - "tensor([[1.0539, 0.3666, 1.3189],\n", - " [1.4779, 0.1089, 1.8161]], grad_fn=)\n" - ] - } - ], - "source": [ - "class My_Linear:\n", - " def __init__(self, input_feature: int, output_feature: int):\n", - " self.weight = torch.randn((output_feature, input_feature), requires_grad=True, dtype=torch.float32)\n", - " self.bias = torch.randn(1, requires_grad=True, dtype=torch.float32)\n", - " self.params = [self.weight, self.bias]\n", - "\n", - " def __call__(self, x: torch.Tensor):\n", - " return self.forward(x)\n", - "\n", - " def forward(self, x: torch.Tensor):\n", - " x = torch.matmul(x, self.weight.T) + self.bias\n", - " return x\n", - "\n", - " def to(self, device: str):\n", - " for param in self.params:\n", - " param.data = param.data.to(device=device)\n", - " return self\n", - "\n", - " def parameters(self):\n", - " return self.params\n", - "\n", - " \n", - "# 测试\n", - "my_linear = My_Linear(1, 3)\n", - "nn_linear = nn.Linear(1, 3)\n", - "my_linear.weight = nn_linear.weight.clone().requires_grad_()\n", - "my_linear.bias = nn_linear.bias.clone().requires_grad_()\n", - "x = torch.tensor([[1.], [2.]], requires_grad=True)\n", - "print(f\"输入：\\n{x}\")\n", - "print(f\"权重：\\n{my_linear.weight.data}\")\n", - "print(f\"偏置：\\n{my_linear.bias.data}\")\n", - "y_my_linear = my_linear(x)\n", - "print(f\"My_Linear输出：\\n{y_my_linear}\")\n", - "y_nn_linear = nn_linear(x)\n", - "print(f\"nn.Linear输出：\\n{y_nn_linear}\")" - ] - }, - { - "cell_type": "markdown", - "id": "5ff813cc-c1f0-4c73-a3e8-d6796ef5d366", - "metadata": {}, - "source": [ - "手动实现logistic回归模型。\n", - "\n", - "模型很简单，主要由一个线性层和一个sigmoid层组成。\n", - "\n", - "Sigmoid函数（又称为 Logistic函数）是一种常用的激活函数，通常用于神经网络的输出层或隐藏层，其作用是将输入的实数值压缩到一个范围在0和1之间的数值。" - ] - }, - { - "cell_type": "code", - "execution_count": 8, - "id": "e7de7e4b-a084-4793-812e-46e8550ecd8d", - "metadata": {}, - "outputs": [], - "source": [ - "class Model_2_1():\n", - " def __init__(self):\n", - " self.linear = My_Linear(1, 1)\n", - " self.params = self.linear.params\n", - "\n", - " def __call__(self, x):\n", - " return self.forward(x)\n", - "\n", - " def forward(self, x):\n", - " x = self.linear(x)\n", - " x = torch.sigmoid(x)\n", - " return x\n", - "\n", - " def to(self, device: str):\n", - " for param in self.params:\n", - " param.data = param.data.to(device=device)\n", - " return self\n", - "\n", - " def parameters(self):\n", - " return self.params" - ] - }, - { - "cell_type": "markdown", - "id": "e14acea9-e5ef-4c24-aea9-329647224ce1", - "metadata": {}, - "source": [ - "人工随机构造数据集。\n", - "\n", - "这里我遇到了比较大的问题。因为数据构建不合适，会导致后面的训练出现梯度爆炸。\n", - "\n", - "我采用随机产生数据后归一化的方法，即\n", - "$$\n", - "\\hat{x} = \\frac{x - \\text{min}_x}{\\text{max}_x - \\text{min}_x} \n", - "$$\n", - "将数据控制在合适的区间。\n", - "\n", - "我的y设置为$4-3\\times x + noise$，noise为随机噪声。\n", - "\n", - "生成完x和y后进行归一化处理，并写好DataLoader访问数据集的接口`__getitem__()`。" - ] - }, - { - "cell_type": "code", - "execution_count": 9, - "id": "c39fbafb-62e4-4b8c-9d65-6718d25f2970", - "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "测试数据集大小：1000000\n", - "测试数据集第0对数据：\n", - "x_0 = 0.5488133381316141\n", - "y_0 = 0.45217091576438073\n" - ] - } - ], - "source": [ - "class My_Dataset(Dataset):\n", - " def __init__(self, data_size=1000000):\n", - " np.random.seed(0)\n", - " x = 2 * np.random.rand(data_size, 1)\n", - " noise = 0.2 * np.random.randn(data_size, 1)\n", - " y = 4 - 3 * x + noise\n", - " self.min_x, self.max_x = np.min(x), np.max(x)\n", - " min_y, max_y = np.min(y), np.max(y)\n", - " x = (x - self.min_x) / (self.max_x - self.min_x)\n", - " y = (y - min_y) / (max_y - min_y)\n", - " self.data = [[x[i][0], y[i][0]] for i in range(x.shape[0])]\n", - "\n", - " def __len__(self):\n", - " return len(self.data)\n", - "\n", - " def __getitem__(self, index):\n", - " x, y = self.data[index]\n", - " return x, y\n", - "\n", - "\n", - "# 测试，并后面的训练创建变量\n", - "dataset = My_Dataset()\n", - "dataset_size = len(dataset)\n", - "print(f\"测试数据集大小：{dataset_size}\")\n", - "x0, y0 = dataset[0]\n", - "print(f\"测试数据集第0对数据：\")\n", - "print(f\"x_0 = {x0}\")\n", - "print(f\"y_0 = {y0}\")" - ] - }, - { - "cell_type": "markdown", - "id": "957a76a2-b306-47a8-912e-8fbf00cdfd42", - "metadata": {}, - "source": [ - "训练Logistic回归模型。\n", - "进行如下步骤：\n", - "1. 初始化超参数\n", - "2. 获取数据集\n", - "3. 初始化模型\n", - "4. 定义损失函数和优化器\n", - "5. 训练\n", - " 1. 从训练dataloader中获取批量数据\n", - " 2. 传入模型\n", - " 3. 使用损失函数计算与ground_truth的损失\n", - " 4. 使用优化器进行反向传播\n", - " 5. 循环以上步骤\n", - "6. 测试\n", - " 1. 设置测试数据\n", - " 2. 传入模型\n", - " 3. 得到预测值" - ] - }, - { - "cell_type": "code", - "execution_count": 10, - "id": "5612661e-2809-4d46-96c2-33ee9f44116d", - "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 1/10, Loss: 688.6783249974251, Acc: 0.9766838179955138\n", - "Epoch 2/10, Loss: 679.506599009037, Acc: 0.992039453911494\n", - "Epoch 3/10, Loss: 677.644762635231, Acc: 0.9961844975781526\n", - "Epoch 4/10, Loss: 677.2690716981888, Acc: 0.998395304269398\n", - "Epoch 5/10, Loss: 677.1928514242172, Acc: 0.9993592246184307\n", - "Epoch 6/10, Loss: 677.1781670451164, Acc: 0.9996570376204033\n", - "Epoch 7/10, Loss: 677.1744618415833, Acc: 0.9998465339227576\n", - "Epoch 8/10, Loss: 677.1738814711571, Acc: 0.9998001679325041\n", - "Epoch 9/10, Loss: 677.1742851734161, Acc: 0.9998804348705138\n", - "Epoch 10/10, Loss: 677.1740592718124, Acc: 0.9999446971149187\n", - "Model weights: -0.0037125118542462587, bias: 0.017451055347919464\n", - "Prediction for test data: 0.5034345984458923\n" - ] - } - ], - "source": [ - "learning_rate = 5e-2\n", - "num_epochs = 10\n", - "batch_size = 1024\n", - "device = \"cuda:0\" if torch.cuda.is_available() else \"cpu\"\n", - "\n", - "dataloader = DataLoader(dataset=dataset, batch_size=batch_size, shuffle=True, num_workers=14, pin_memory=True)\n", - "\n", - "model = Model_2_1().to(device)\n", - "criterion = My_BCELoss()\n", - "optimizer = My_Optimizer(model.parameters(), lr=learning_rate)\n", - "\n", - "for epoch in range(num_epochs):\n", - " total_epoch_loss = 0\n", - " total_epoch_pred = 0\n", - " total_epoch_target = 0\n", - " for x, targets in dataloader:\n", - " optimizer.zero_grad()\n", - " \n", - " x = x.to(device).to(dtype=torch.float32)\n", - " targets = targets.to(device).to(dtype=torch.float32)\n", - " \n", - " x = x.unsqueeze(1)\n", - " y_pred = model(x)\n", - " loss = criterion(y_pred, targets)\n", - " total_epoch_loss += loss.item()\n", - " total_epoch_target += targets.sum().item()\n", - " total_epoch_pred += y_pred.sum().item()\n", - "\n", - " loss.backward()\n", - " optimizer.step()\n", - "\n", - " print(f\"Epoch {epoch + 1}/{num_epochs}, Loss: {total_epoch_loss}, \", end=\"\")\n", - " print(f\"Acc: {1 - abs(total_epoch_pred - total_epoch_target) / total_epoch_target}\")\n", - "\n", - "with torch.no_grad():\n", - " test_data = (np.array([[2]]) - dataset.min_x) / (dataset.max_x - dataset.min_x)\n", - " test_data = Variable(torch.tensor(test_data, dtype=torch.float32), requires_grad=False).to(device)\n", - " predicted = model(test_data).to(\"cpu\")\n", - " print(f\"Model weights: {model.linear.weight.item()}, bias: {model.linear.bias.item()}\")\n", - " print(f\"Prediction for test data: {predicted.item()}\")" - ] - }, - { - "cell_type": "markdown", - "id": "9e416582-a30d-4084-acc6-6e05f80a6aff", - "metadata": {}, - "source": [ - "## 题目2\n", - "**利用 torch.nn 实现 logistic 回归在人工构造的数据集上进行训练和测试，并对结果进行分析，并从loss以及训练集上的准确率等多个角度对结果进行分析**" - ] - }, - { - "cell_type": "markdown", - "id": "0460d125-7d03-44fe-845c-c4d13792e241", - "metadata": {}, - "source": [ - "使用torch.nn实现模型。\n", - "\n", - "将之前的Model_2_1中的手动实现函数改为torch.nn内置函数即可，再加上继承nn.Module以使用torch.nn内置模型模板特性。" - ] - }, - { - "cell_type": "code", - "execution_count": 11, - "id": "fa121afd-a1af-4193-9b54-68041e0ed068", - "metadata": {}, - "outputs": [], - "source": [ - "class Model_2_2(nn.Module):\n", - " def __init__(self):\n", - " super(Model_2_2, self).__init__()\n", - " self.linear = nn.Linear(1, 1, dtype=torch.float64)\n", - "\n", - " def forward(self, x):\n", - " x = self.linear(x)\n", - " x = torch.sigmoid(x)\n", - " return x" - ] - }, - { - "cell_type": "markdown", - "id": "176eee7e-4e3d-470e-8af2-8761bca039f8", - "metadata": {}, - "source": [ - "训练与测试过程与之前手动实现的几乎一致。仅有少量涉及数据类型（dtype）的代码需要更改以适应torch.nn的内置函数要求。" - ] - }, - { - "cell_type": "code", - "execution_count": 12, - "id": "93b0fdb6-be8b-4663-b59e-05ed19a9ea09", - "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 1/10, Loss: 660.2008021697803, Acc: 0.9355364605682331\n", - "Epoch 2/10, Loss: 589.2025169091534, Acc: 0.9769773185253259\n", - "Epoch 3/10, Loss: 572.7106042209589, Acc: 0.9881629137259633\n", - "Epoch 4/10, Loss: 568.0903503441508, Acc: 0.9935173218188225\n", - "Epoch 5/10, Loss: 566.6528526848851, Acc: 0.9962586560919562\n", - "Epoch 6/10, Loss: 566.1778871576632, Acc: 0.9978209774304773\n", - "Epoch 7/10, Loss: 566.0143385848835, Acc: 0.9987369762885633\n", - "Epoch 8/10, Loss: 565.9605239629793, Acc: 0.9992563563084009\n", - "Epoch 9/10, Loss: 565.9402079010808, Acc: 0.9995321069396558\n", - "Epoch 10/10, Loss: 565.9281422200424, Acc: 0.9997496312356398\n", - "Model weights: -3.6833968323036084, bias: 1.8628376037952126\n", - "Prediction for test data: 0.13936666014014443\n" - ] - } - ], - "source": [ - "learning_rate = 5e-2\n", - "num_epochs = 10\n", - "batch_size = 1024\n", - "device = \"cuda:0\" if torch.cuda.is_available() else \"cpu\"\n", - "\n", - "dataloader = DataLoader(dataset=dataset, batch_size=batch_size, shuffle=True, num_workers=14, pin_memory=True)\n", - "\n", - "model = Model_2_2().to(device)\n", - "criterion = nn.BCELoss()\n", - "optimizer = torch.optim.SGD(model.parameters(), lr=learning_rate)\n", - "\n", - "for epoch in range(num_epochs):\n", - " total_epoch_loss = 0\n", - " total_epoch_pred = 0\n", - " total_epoch_target = 0\n", - " for x, targets in dataloader:\n", - " optimizer.zero_grad()\n", - "\n", - " x = x.to(device)\n", - " targets = targets.to(device)\n", - "\n", - " x = x.unsqueeze(1)\n", - " targets = targets.unsqueeze(1)\n", - " y_pred = model(x)\n", - " loss = criterion(y_pred, targets)\n", - " total_epoch_loss += loss.item()\n", - " total_epoch_target += targets.sum().item()\n", - " total_epoch_pred += y_pred.sum().item()\n", - "\n", - " loss.backward()\n", - " optimizer.step()\n", - "\n", - " print(f\"Epoch {epoch + 1}/{num_epochs}, Loss: {total_epoch_loss}, \", end=\"\")\n", - " print(f\"Acc: {1 - abs(total_epoch_pred - total_epoch_target) / total_epoch_target}\")\n", - "\n", - "with torch.no_grad():\n", - " test_data = (np.array([[2]]) - dataset.min_x) / (dataset.max_x - dataset.min_x)\n", - " test_data = Variable(torch.tensor(test_data, dtype=torch.float64), requires_grad=False).to(device)\n", - " predicted = model(test_data).to(\"cpu\")\n", - " print(f\"Model weights: {model.linear.weight.item()}, bias: {model.linear.bias.item()}\")\n", - " print(f\"Prediction for test data: {predicted.item()}\")" - ] - }, - { - "cell_type": "markdown", - "id": "e6bff679-f8d2-46cc-bdcb-82af7dab38b3", - "metadata": {}, - "source": [ - "对比发现，手动实现的损失函数和优化器与torch.nn的内置损失函数和优化器相比，表现差不多。\n", - "\n", - "但是为什么相同分布的数据集训练出的权重和偏置，以及预测结果存在较大差别，这个问题的原因还有待我探究。" - ] - }, - { - "cell_type": "markdown", - "id": "ef41d7fa-c2bf-4024-833b-60af0a87043a", - "metadata": {}, - "source": [ - "# 三、动手实现softmax回归\n", - "\n", - "## 问题1\n", - "\n", - "**要求动手从0实现softmax回归（只借助Tensor和Numpy相关的库）在Fashion-MNIST数据集上进行训练和测试，并从loss、训练集以及测试集上的准确率等多个角度对结果进行分析（要求从零实现交叉熵损失函数）**" - ] - }, - { - "cell_type": "markdown", - "id": "3c356760-75a8-4814-ba69-73b270396a4e", - "metadata": {}, - "source": [ - "手动实现nn.one_hot()。\n", - "\n", - "one-hot向量用于消除线性标签值所映射的类别的非线性。\n", - "\n", - "one-hot向量是使用一个长度为分类数量的数组表示标签值，其中有且仅有1个值为为1，该值的下标为标签值；其余为0。\n", - "\n", - "原理很简单，步骤如下：\n", - "1. 初始化全零的张量，大小为（标签数量，分类数量）；\n", - "2. 将标签值映射到全零张量的\\[下标，标签值\\]中，将该位置为1；\n", - "3. 返回修改后的张量，即是ont-hot向量。" - ] - }, - { - "cell_type": "code", - "execution_count": 13, - "id": "e605f1b0-1d32-410f-bddf-402a85ccc9ff", - "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "输入：\n", - "tensor([2, 1, 0])\n", - "my_one_hot输出：\n", - "tensor([[0, 0, 1, 0, 0],\n", - " [0, 1, 0, 0, 0],\n", - " [1, 0, 0, 0, 0]])\n", - "nn.functional.one_hot输出：\n", - "tensor([[0, 0, 1, 0, 0],\n", - " [0, 1, 0, 0, 0],\n", - " [1, 0, 0, 0, 0]])\n" - ] - } - ], - "source": [ - "def my_one_hot(indices: torch.Tensor, num_classes: int):\n", - " one_hot_tensor = torch.zeros(len(indices), num_classes).to(indices.device).to(dtype=torch.int64)\n", - " one_hot_tensor.scatter_(1, indices.view(-1, 1), 1)\n", - " return one_hot_tensor\n", - "\n", - "\n", - "# 测试\n", - "x = torch.tensor([2, 1, 0], dtype=torch.int64)\n", - "print(f\"输入：\\n{x}\")\n", - "\n", - "x_my_onehot = my_one_hot(x, 5)\n", - "print(f\"my_one_hot输出：\\n{x_my_onehot}\")\n", - "\n", - "x_nn_F_onehot = nn.functional.one_hot(x, 5)\n", - "print(f\"nn.functional.one_hot输出：\\n{x_nn_F_onehot}\")" - ] - }, - { - "cell_type": "markdown", - "id": "902603a6-bfb9-4ce3-bd0d-b00cebb1d3cb", - "metadata": {}, - "source": [ - "手动实现CrossEntropyLoss。\n", - "\n", - "CrossEntropyLoss由一个log_softmax和一个nll_loss组成。\n", - "\n", - "softmax的数学表达式如下：\n", - "$$\n", - "\\text{softmax}(y_i) = \\frac{e^{y_i - \\text{max}(y)}}{\\sum_{j=1}^{N} e^{y_j - \\text{max}(y)}} \n", - "$$\n", - "log_softmax即为$\\log\\left(softmax\\left(y\\right)\\right)$。\n", - "\n", - "CrossEntropyLoss的数学表达式如下：\n", - "$$\n", - "\\text{CrossEntropyLoss}(y, \\hat{y}) = -\\frac{1}{N} \\sum_{i=1}^{N} \\hat{y}_i \\cdot \\log(\\text{softmax}(y_i)) \n", - "$$\n", - "\n", - "故代码如下：" - ] - }, - { - "cell_type": "code", - "execution_count": 14, - "id": "759a3bb2-b5f4-4ea5-a2d7-15f0c4cdd14b", - "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "输入：\n", - "tensor([[ 0.7600, 0.4269, 0.7948, -0.6086, 1.2527],\n", - " [-0.4749, 0.5720, -0.0164, -0.2126, -0.0410],\n", - " [ 1.3269, 1.8524, -0.9815, 0.0156, 1.6971]], requires_grad=True)\n", - "标签：\n", - "tensor([[0., 1., 0., 0., 0.],\n", - " [0., 0., 0., 1., 0.],\n", - " [1., 0., 0., 0., 0.]])\n", - "My_CrossEntropyLoss损失值: 1.7417106628417969\n", - "nn.CrossEntropyLoss损失值: 1.7417105436325073\n" - ] - } - ], - "source": [ - "class My_CrossEntropyLoss:\n", - " def __call__(self, predictions: torch.Tensor, targets: torch.Tensor):\n", - " max_values = torch.max(predictions, dim=1, keepdim=True).values\n", - " exp_values = torch.exp(predictions - max_values)\n", - " softmax_output = exp_values / torch.sum(exp_values, dim=1, keepdim=True)\n", - " log_probs = torch.log(softmax_output)\n", - " \n", - " nll_loss = -torch.sum(targets * log_probs, dim=1)\n", - " average_loss = torch.mean(nll_loss)\n", - " return average_loss\n", - "\n", - " \n", - "# 测试\n", - "input = torch.randn(3, 5, requires_grad=True)\n", - "target = torch.randn(3, 5).softmax(dim=1).argmax(1)\n", - "target = torch.nn.functional.one_hot(target, num_classes=5).to(dtype=torch.float32)\n", - "print(f\"输入：\\n{input}\")\n", - "print(f\"标签：\\n{target}\")\n", - "\n", - "my_crossentropyloss = My_CrossEntropyLoss()\n", - "my_loss = my_crossentropyloss(input, target)\n", - "print(\"My_CrossEntropyLoss损失值:\", my_loss.item())\n", - "\n", - "nn_crossentropyloss = nn.CrossEntropyLoss()\n", - "nn_loss = nn_crossentropyloss(input, target)\n", - "print(\"nn.CrossEntropyLoss损失值:\", nn_loss.item())" - ] - }, - { - "cell_type": "markdown", - "id": "dbf78501-f5be-4008-986c-d331d531491f", - "metadata": {}, - "source": [ - "手动实现Flatten。\n", - "\n", - "原理很简单，就是把多维的张量拉直成一个向量。" - ] - }, - { - "cell_type": "code", - "execution_count": 15, - "id": "74322629-8325-4823-b80f-f28182d577c1", - "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Flatten之前的x：\n", - "tensor([[[1., 2.],\n", - " [3., 4.]],\n", - "\n", - " [[5., 6.],\n", - " [7., 8.]]])\n", - "My_Flatten之后的x：\n", - "tensor([[1., 2., 3., 4.],\n", - " [5., 6., 7., 8.]])\n", - "nn.Flatten之后的x：\n", - "tensor([[1., 2., 3., 4.],\n", - " [5., 6., 7., 8.]])\n" - ] - } - ], - "source": [ - "class My_Flatten:\n", - " def __call__(self, x: torch.Tensor):\n", - " return self.forward(x)\n", - "\n", - " def forward(self, x: torch.Tensor):\n", - " x = x.view(x.shape[0], -1)\n", - " return x\n", - "\n", - "\n", - "# 测试\n", - "my_flatten = My_Flatten()\n", - "nn_flatten = nn.Flatten()\n", - "x = torch.tensor([[[1., 2.],\n", - " [3., 4.]],\n", - " [[5., 6.],\n", - " [7., 8.]]])\n", - "print(f\"Flatten之前的x：\\n{x}\")\n", - "x_my_flatten = my_flatten(x)\n", - "print(f\"My_Flatten之后的x：\\n{x_my_flatten}\")\n", - "x_nn_flatten = nn_flatten(x)\n", - "print(f\"nn.Flatten之后的x：\\n{x_nn_flatten}\")" - ] - }, - { - "cell_type": "markdown", - "id": "35aee905-ae37-4faa-a7f1-a04cd8579f78", - "metadata": {}, - "source": [ - "手动实现softmax回归模型。\n", - "\n", - "模型很简单，主要由一个Flatten层和一个线性层组成。\n", - "\n", - "Flatten层主要用于将2维的图像展开，直接作为1维的特征量输入网络。" - ] - }, - { - "cell_type": "code", - "execution_count": 16, - "id": "bb31a75e-464c-4b94-b927-b219a765e35d", - "metadata": {}, - "outputs": [], - "source": [ - "class Model_3_1:\n", - " def __init__(self, num_classes):\n", - " self.flatten = My_Flatten()\n", - " self.linear = My_Linear(28 * 28, num_classes)\n", - " self.params = self.linear.params\n", - "\n", - " def __call__(self, x: torch.Tensor):\n", - " return self.forward(x)\n", - "\n", - " def forward(self, x: torch.Tensor):\n", - " x = self.flatten(x)\n", - " x = self.linear(x)\n", - " return x\n", - "\n", - " def to(self, device: str):\n", - " for param in self.params:\n", - " param.data = param.data.to(device=device)\n", - " return self\n", - "\n", - " def parameters(self):\n", - " return self.params" - ] - }, - { - "cell_type": "markdown", - "id": "17e686d1-9c9a-4727-8fdc-9990d348c523", - "metadata": {}, - "source": [ - "训练与测试过程与之前手动实现的几乎一致。由于数据集的变化，对应超参数也进行了调整。\n", - "\n", - "数据集也使用了现成的FashionMNIST数据集，且划分了训练集和测试集。\n", - "\n", - "FashionMNIST数据集直接调用API获取。数据集的image为28*28的单通道灰白图片，label为单个数值标签。\n", - "\n", - "训练softmax回归模型。\n", - "进行如下步骤：\n", - "1. 初始化超参数\n", - "2. 获取数据集\n", - "3. 初始化模型\n", - "4. 定义损失函数和优化器\n", - "5. 训练\n", - " 1. 从训练dataloader中获取批量数据\n", - " 2. 传入模型\n", - " 3. 使用损失函数计算与ground_truth的损失\n", - " 4. 使用优化器进行反向传播\n", - " 5. 循环以上步骤\n", - "6. 测试\n", - " 1. 从测试dataloader中获取批量数据\n", - " 2. 传入模型\n", - " 3. 将预测值与ground_truth进行比较，得出正确率\n", - " 4. 对整个训练集统计正确率，从而分析训练效果" - ] - }, - { - "cell_type": "code", - "execution_count": 17, - "id": "d816dae1-5fbe-4c29-9597-19d66b5eb6b4", - "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 1/10, Loss: 87.64246368408203, Acc: 0.45329999923706055\n", - "Epoch 2/10, Loss: 42.025726318359375, Acc: 0.5523999929428101\n", - "Epoch 3/10, Loss: 34.06425094604492, Acc: 0.5947999954223633\n", - "Epoch 4/10, Loss: 30.135021209716797, Acc: 0.620199978351593\n", - "Epoch 5/10, Loss: 27.43822479248047, Acc: 0.6401000022888184\n", - "Epoch 6/10, Loss: 25.72039031982422, Acc: 0.6525999903678894\n", - "Epoch 7/10, Loss: 24.28335952758789, Acc: 0.6638999581336975\n", - "Epoch 8/10, Loss: 23.18214988708496, Acc: 0.671999990940094\n", - "Epoch 9/10, Loss: 22.18520164489746, Acc: 0.680899977684021\n", - "Epoch 10/10, Loss: 21.393451690673828, Acc: 0.6875999569892883\n" - ] - } - ], - "source": [ - "learning_rate = 5e-1\n", - "num_epochs = 10\n", - "batch_size = 4096\n", - "num_classes = 10\n", - "device = \"cuda:0\" if torch.cuda.is_available() else \"cpu\"\n", - "\n", - "transform = transforms.Compose(\n", - " [\n", - " transforms.ToTensor(),\n", - " transforms.Normalize((0.5,), (1.0,)),\n", - " ]\n", - ")\n", - "train_dataset = datasets.FashionMNIST(root=\"./dataset\", train=True, transform=transform, download=True)\n", - "test_dataset = datasets.FashionMNIST(root=\"./dataset\", train=False, transform=transform, download=True)\n", - "train_loader = DataLoader(dataset=train_dataset, batch_size=batch_size,shuffle=True, num_workers=14, pin_memory=True)\n", - "test_loader = DataLoader(dataset=test_dataset, batch_size=batch_size,shuffle=True, num_workers=14, pin_memory=True)\n", - "\n", - "model = Model_3_1(num_classes).to(device)\n", - "criterion = My_CrossEntropyLoss()\n", - "optimizer = My_Optimizer(model.parameters(), lr=learning_rate)\n", - "\n", - "for epoch in range(num_epochs):\n", - " total_epoch_loss = 0\n", - " for images, targets in train_loader:\n", - " optimizer.zero_grad()\n", - "\n", - " images = images.to(device)\n", - " targets = targets.to(device).to(dtype=torch.long)\n", - "\n", - " one_hot_targets = my_one_hot(targets, num_classes=num_classes).to(device).to(dtype=torch.long)\n", - "\n", - " outputs = model(images)\n", - " loss = criterion(outputs, one_hot_targets)\n", - " total_epoch_loss += loss\n", - "\n", - " loss.backward()\n", - " optimizer.step()\n", - "\n", - " total_acc = 0\n", - " with torch.no_grad():\n", - " for image, targets in test_loader:\n", - " image = image.to(device)\n", - " targets = targets.to(device)\n", - " outputs = model(image)\n", - " total_acc += (outputs.argmax(1) == targets).sum()\n", - " print(f\"Epoch {epoch + 1}/{num_epochs}, Loss: {total_epoch_loss}, Acc: {total_acc / len(test_dataset)}\")" - ] - }, - { - "cell_type": "markdown", - "id": "a49d0165-aeb7-48c0-9b67-956bb08cb356", - "metadata": {}, - "source": [ - "在这里我遇到了梯度爆炸的问题。\n", - "\n", - "原来我在数据预处理中使用`transforms.Normalize((0.5,), (0.5,))`进行归一化，但是这样导致了梯度爆炸。\n", - "\n", - "将第二个参数方差改为1.0后，成功解决了梯度爆炸的问题。" - ] - }, - { - "cell_type": "markdown", - "id": "3ef5240f-8a11-4678-bfce-f1cbc7e71b77", - "metadata": {}, - "source": [ - "## 问题2\n", - "\n", - "**利用torch.nn实现softmax回归在Fashion-MNIST数据集上进行训练和测试，并从loss，训练集以及测试集上的准确率等多个角度对结果进行分析**" - ] - }, - { - "cell_type": "markdown", - "id": "5c4a88c6-637e-4af5-bed5-f644685dcabc", - "metadata": {}, - "source": [ - "使用torch.nn实现模型。\n", - "\n", - "将之前的Model_3_1中的手动实现函数改为torch.nn内置函数即可，再加上继承nn.Module以使用torch.nn内置模型模板特性。" - ] - }, - { - "cell_type": "code", - "execution_count": 18, - "id": "0163b9f7-1019-429c-8c29-06436d0a4c98", - "metadata": {}, - "outputs": [], - "source": [ - "class Model_3_2(nn.Module):\n", - " def __init__(self, num_classes):\n", - " super(Model_3_2, self).__init__()\n", - " self.flatten = nn.Flatten()\n", - " self.linear = nn.Linear(28 * 28, num_classes)\n", - "\n", - " def forward(self, x: torch.Tensor):\n", - " x = self.flatten(x)\n", - " x = self.linear(x)\n", - " return x" - ] - }, - { - "cell_type": "markdown", - "id": "6e765ad7-c1c6-4166-bd7f-361666bd4016", - "metadata": {}, - "source": [ - "训练与测试过程与之前手动实现的几乎一致。" - ] - }, - { - "cell_type": "code", - "execution_count": 19, - "id": "6d241c05-b153-4f56-a845-0f2362f6459b", - "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 1/10, Loss: 19.15451431274414, Acc: 0.7202000021934509\n", - "Epoch 2/10, Loss: 12.260371208190918, Acc: 0.7486000061035156\n", - "Epoch 3/10, Loss: 10.835549354553223, Acc: 0.7615999579429626\n", - "Epoch 4/10, Loss: 10.09542179107666, Acc: 0.7701999545097351\n", - "Epoch 5/10, Loss: 9.626176834106445, Acc: 0.777899980545044\n", - "Epoch 6/10, Loss: 9.264442443847656, Acc: 0.7854999899864197\n", - "Epoch 7/10, Loss: 9.017412185668945, Acc: 0.7879999876022339\n", - "Epoch 8/10, Loss: 8.786051750183105, Acc: 0.7915999889373779\n", - "Epoch 9/10, Loss: 8.613431930541992, Acc: 0.79749995470047\n", - "Epoch 10/10, Loss: 8.462657928466797, Acc: 0.7996999621391296\n" - ] - } - ], - "source": [ - "learning_rate = 5e-2\n", - "num_epochs = 10\n", - "batch_size = 4096\n", - "num_classes = 10\n", - "device = \"cuda:0\" if torch.cuda.is_available() else \"cpu\"\n", - "\n", - "transform = transforms.Compose(\n", - " [\n", - " transforms.ToTensor(),\n", - " transforms.Normalize((0.5,), (0.5,)),\n", - " ]\n", - ")\n", - "train_dataset = datasets.FashionMNIST(root=\"./dataset\", train=True, transform=transform, download=True)\n", - "test_dataset = datasets.FashionMNIST(root=\"./dataset\", train=False, transform=transform, download=True)\n", - "train_loader = DataLoader(dataset=train_dataset, batch_size=batch_size, shuffle=True, num_workers=14, pin_memory=True)\n", - "test_loader = DataLoader(dataset=test_dataset, batch_size=batch_size, shuffle=True, num_workers=14, pin_memory=True)\n", - "\n", - "model = Model_3_2(num_classes).to(device)\n", - "criterion = nn.CrossEntropyLoss()\n", - "optimizer = torch.optim.SGD(model.parameters(), lr=learning_rate)\n", - "\n", - "for epoch in range(num_epochs):\n", - " total_epoch_loss = 0\n", - " model.train()\n", - " for images, targets in train_loader:\n", - " optimizer.zero_grad()\n", - "\n", - " images = images.to(device)\n", - " targets = targets.to(device)\n", - "\n", - " one_hot_targets = nn.functional.one_hot(targets, num_classes=num_classes).to(device).to(dtype=torch.float32)\n", - "\n", - " outputs = model(images)\n", - " loss = criterion(outputs, one_hot_targets)\n", - " total_epoch_loss += loss\n", - "\n", - " loss.backward()\n", - " optimizer.step()\n", - "\n", - " model.eval()\n", - " total_acc = 0\n", - " with torch.no_grad():\n", - " for image, targets in test_loader:\n", - " image = image.to(device)\n", - " targets = targets.to(device)\n", - " outputs = model(image)\n", - " total_acc += (outputs.argmax(1) == targets).sum()\n", - " print(f\"Epoch {epoch + 1}/{num_epochs}, Loss: {total_epoch_loss}, Acc: {total_acc / len(test_dataset)}\")" - ] - }, - { - "cell_type": "markdown", - "id": "59555b67-1650-4e1a-a98e-7906878bf3d0", - "metadata": {}, - "source": [ - "与手动实现的softmax回归相比较，nn.CrossEntropyLoss比手动实现的My_CrossEntropyLoss更加稳定，对输入数据的兼容性更强，没有出现梯度爆炸的情况。\n", - "\n", - "总体表现上，torch.nn的内置功能相对手动实现的功能，正确率提升更快，最终正确率更高。" - ] - }, - { - "cell_type": "markdown", - "id": "f40431f2-e77b-4ead-81a3-ff6451a8e452", - "metadata": {}, - "source": [ - "# 实验心得体会\n", - "\n", - "通过完成本次Pytorch基本操作实验，让我对Pytorch框架有了更加深入的理解。我接触深度学习主要是在大语言模型领域，比较熟悉微调大模型，但是涉及到底层的深度学习知识，我还有很多短板和不足。这次实验对我这方面的锻炼让我收获良多。\n", - "\n", - "首先是数据集的设置。如果数据没有合理进行归一化，很容易出现梯度爆炸。这是在我以前直接使用图片数据集的经历中没有遇到过的问题。\n", - "\n", - "在实现logistic回归模型时，通过手动实现各个组件如优化器、线性层等，让我对这些模块的工作原理有了更清晰的认识。尤其是在实现广播机制时，需要充分理解张量操作的维度变换规律。而使用Pytorch内置模块进行实现时，通过继承nn.Module可以自动获得许多功能，使代码更加简洁。\n", - "\n", - "在实现softmax回归时，则遇到了更大的困难。手动实现的模型很容易出现梯度爆炸的问题，而使用Pytorch内置的损失函数和优化器则可以稳定训练。这让我意识到了选择合适的优化方法的重要性。另外，Pytorch强大的自动微分机制也是构建深度神经网络的重要基础。\n", - "\n", - "通过这个实验，让我对Pytorch框架有了更加直观的感受，也让我看到了仅靠基础模块搭建复杂模型的难点所在。这些经验对我后续使用Pytorch构建数据集模型会很有帮助。" - ] - } - ], - "metadata": { - "kernelspec": { - "display_name": "Python 3 (ipykernel)", - "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": "3.10.13" - } - }, - "nbformat": 4, - "nbformat_minor": 5 -} diff --git a/Lab1/Pytorch基本操作实验报告.ipynb b/Lab1/Pytorch基本操作实验报告.ipynb index ac0b0e3..952c0a6 100644 --- a/Lab1/Pytorch基本操作实验报告.ipynb +++ b/Lab1/Pytorch基本操作实验报告.ipynb @@ -393,7 +393,7 @@ "id": "6ab83528-a88b-4d66-b0c9-b1315cf75c22", "metadata": {}, "source": [ - "线性层主要有一个权重（weight)和一个偏置（bias）。\n", + "线性层主要有一个权重（weight）和一个偏置（bias）。\n", "线性层的数学公式如下：\n", "$$\n", "x:=x \\times weight^T+bias\n", diff --git a/Lab1/code/.ipynb_checkpoints/1.1-checkpoint.py b/Lab1/code/.ipynb_checkpoints/1.1-checkpoint.py deleted file mode 100644 index 0720510..0000000 --- a/Lab1/code/.ipynb_checkpoints/1.1-checkpoint.py +++ /dev/null @@ -1,39 +0,0 @@ -import torch - -A = torch.tensor([[1, 2, 3]]) - -B = torch.tensor([[4], - [5]]) - -# 方法1: 使用PyTorch的减法操作符 -result1 = A - B - -# 方法2: 使用PyTorch的sub函数 -result2 = torch.sub(A, B) - -# 方法3: 手动实现广播机制并作差 -def my_sub(a:torch.Tensor, b:torch.Tensor): - if not ( - (a.size(0) == 1 and b.size(1) == 1) - or - (a.size(1) == 1 and b.size(0) == 1) - ): - raise ValueError("输入的张量大小无法满足广播机制的条件。") - else: - target_shape = torch.Size([max(A.size(0), B.size(0)), max(A.size(1), B.size(1))]) - A_broadcasted = A.expand(target_shape) - B_broadcasted = B.expand(target_shape) - result = torch.zeros(target_shape, dtype=torch.int64).to(device=A_broadcasted.device) - for i in range(target_shape[0]): - for j in range(target_shape[1]): - result[i, j] = A_broadcasted[i, j] - B_broadcasted[i, j] - return result - -result3 = my_sub(A, B) - -print("方法1的结果:") -print(result1) -print("方法2的结果:") -print(result2) -print("方法3的结果:") -print(result3)