上传了人工智能导论三项作业决策树,svm；knn，以及pytorch图像分类

学习/人工智能导论/作业1-KNN/.ipynb_checkpoints/Untitled-checkpoint.ipynb

@@ -0,0 +1,195 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import random\n",
+    "import numpy as np\n",
+    "import matplotlib.pyplot as plt\n",
+    "from past.builtins import xrange\n",
+    "%matplotlib inline\n",
+    "plt.rcParams['figure.figsize'] = (15., 12.) # 设置默认大小\n",
+    "plt.rcParams['image.interpolation'] = 'nearest'\n",
+    "plt.rcParams['image.cmap'] = 'gray'\n",
+    "\n",
+    "%load_ext autoreload\n",
+    "%autoreload 2"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "(5000, 32, 32, 3)\n",
+      "(500, 32, 32, 3)\n",
+      "(500, 32, 32, 3)\n"
+     ]
+    }
+   ],
+   "source": [
+    "# 读取提供的cifar10-mini数据集，\n",
+    "data = np.load('cifar10-mini.npz')\n",
+    "\n",
+    "X_train= data['X_train']\n",
+    "X_val= data['X_val']\n",
+    "X_test= data['X_test']\n",
+    "y_train= data['y_train']\n",
+    "y_val= data['y_val']\n",
+    "y_test= data['y_test']\n",
+    "\n",
+    "# 打印数据shape\n",
+    "print(X_train.shape)\n",
+    "print(X_val.shape)\n",
+    "print(X_test.shape)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from features import *\n",
+    "\n",
+    "################################################################################\n",
+    "# TODO:                                                                        #\n",
+    "# 你需要使用 hog_feature, color_histogram_hsv 两个函数完成特征的提取           #\n",
+    "# 你可以在 features.py 中查看这两个函数的代码                                  #\n",
+    "################################################################################\n",
+    "\"\"\"你的代码\"\"\"\n",
+    "X_train_feats = extract_features(X_train,[hog_feature,color_histogram_hsv])\n",
+    "X_val_feats = extract_features(X_val,[hog_feature,color_histogram_hsv])\n",
+    "X_test_feats = extract_features(X_test,[hog_feature,color_histogram_hsv])\n",
+    "\n",
+    "################################################################################\n",
+    "#                                 END OF YOUR CODE                             #\n",
+    "################################################################################\n",
+    "\n",
+    "    \n",
+    "# 预处理: 减去均值\n",
+    "mean_feat = np.mean(X_train_feats, axis=0, keepdims=True)\n",
+    "X_train_feats -= mean_feat\n",
+    "\n",
+    "mean_feat = np.mean(X_val_feats, axis=0, keepdims=True)\n",
+    "X_val_feats -= mean_feat\n",
+    "\n",
+    "mean_feat = np.mean(X_test_feats, axis=0, keepdims=True)\n",
+    "X_test_feats -= mean_feat\n",
+    "\n",
+    "# 预处理: 除以标准差，这能保证所有的值在 0～1 之间\n",
+    "std_feat = np.std(X_train_feats, axis=0, keepdims=True)\n",
+    "X_train_feats /= std_feat\n",
+    "\n",
+    "std_feat = np.std(X_val_feats, axis=0, keepdims=True)\n",
+    "X_val_feats /= std_feat\n",
+    "\n",
+    "std_feat = np.std(X_test_feats, axis=0, keepdims=True)\n",
+    "X_test_feats /= std_feat\n",
+    "\n",
+    "# 预处理: 增加一个偏置值，在 K-NN 中，该步操作并无必要，但增加偏置值对其他分类器如 SVM 等有帮助。\n",
+    "X_train_feats = np.hstack([X_train_feats, np.ones((X_train_feats.shape[0], 1))])\n",
+    "X_val_feats = np.hstack([X_val_feats, np.ones((X_val_feats.shape[0], 1))])\n",
+    "X_test_feats = np.hstack([X_test_feats, np.ones((X_test_feats.shape[0], 1))])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "((500, 155), (500, 155), (500, 155))"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "X_test_feats.shape , X_val_feats.shape , X_test_feats.shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sklearn.neighbors import KNeighborsClassifier\n",
+    "from sklearn.metrics import accuracy_score"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "KNN准确率: 0.3180\n"
+     ]
+    }
+   ],
+   "source": [
+    "knn = KNeighborsClassifier() \n",
+    "knn.fit(X_train_feats , y_train ) \n",
+    "predict_y = knn.predict(X_test_feats) \n",
+    "print(\"KNN准确率: %.4lf\" % accuracy_score(y_test, predict_y))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "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": "3.8.3"
+  },
+  "toc": {
+   "base_numbering": 1,
+   "nav_menu": {},
+   "number_sections": true,
+   "sideBar": true,
+   "skip_h1_title": false,
+   "title_cell": "Table of Contents",
+   "title_sidebar": "Contents",
+   "toc_cell": false,
+   "toc_position": {},
+   "toc_section_display": true,
+   "toc_window_display": false
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}