{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from google.colab import drive\n",
    "\n",
    "drive.mount('/content/drive', force_remount=True)\n",
    "\n",
    "# 输入daseCV所在的路径\n",
    "# 'daseCV' 文件夹包括 '.py', 'classifiers' 和'datasets'文件夹\n",
    "# 例如 'CV/assignments/assignment1/daseCV/'\n",
    "FOLDERNAME = None\n",
    "\n",
    "assert FOLDERNAME is not None, \"[!] Enter the foldername.\"\n",
    "\n",
    "%cd drive/My\\ Drive\n",
    "%cp -r $FOLDERNAME ../../\n",
    "%cd ../../\n",
    "%cd daseCV/datasets/\n",
    "!bash get_datasets.sh\n",
    "%cd ../../"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "tags": [
     "pdf-title"
    ]
   },
   "source": [
    "# Softmax 练习\n",
    "\n",
    "*补充并完成本练习。*\n",
    "\n",
    "本练习类似于SVM练习，你要完成的事情包括:\n",
    "\n",
    "- 为Softmax分类器实现完全矢量化的**损失函数**\n",
    "- 实现其**解析梯度（analytic gradient）**的完全矢量化表达式\n",
    "- 用数值梯度**检查你的代码**\n",
    "- 使用验证集**调整学习率和正则化强度**\n",
    "- 使用**SGD优化**损失函数\n",
    "- **可视化**最终学习的权重\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "tags": [
     "pdf-ignore"
    ]
   },
   "outputs": [],
   "source": [
    "import random\n",
    "import numpy as np\n",
    "from daseCV.data_utils import load_CIFAR10\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "%matplotlib inline\n",
    "plt.rcParams['figure.figsize'] = (10.0, 8.0) # set default size of plots\n",
    "plt.rcParams['image.interpolation'] = 'nearest'\n",
    "plt.rcParams['image.cmap'] = 'gray'\n",
    "\n",
    "# for auto-reloading extenrnal modules\n",
    "# see http://stackoverflow.com/questions/1907993/autoreload-of-modules-in-ipython\n",
    "%load_ext autoreload\n",
    "%autoreload 2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "tags": [
     "pdf-ignore"
    ]
   },
   "outputs": [],
   "source": [
    "def get_CIFAR10_data(num_training=49000, num_validation=1000, num_test=1000, num_dev=500):\n",
    "    \"\"\"\n",
    "    Load the CIFAR-10 dataset from disk and perform preprocessing to prepare\n",
    "    it for the linear classifier. These are the same steps as we used for the\n",
    "    SVM, but condensed to a single function.  \n",
    "    \"\"\"\n",
    "    # Load the raw CIFAR-10 data\n",
    "    cifar10_dir = 'daseCV/datasets/cifar-10-batches-py'\n",
    "    \n",
    "    # Cleaning up variables to prevent loading data multiple times (which may cause memory issue)\n",
    "    try:\n",
    "       del X_train, y_train\n",
    "       del X_test, y_test\n",
    "       print('Clear previously loaded data.')\n",
    "    except:\n",
    "       pass\n",
    "\n",
    "    X_train, y_train, X_test, y_test = load_CIFAR10(cifar10_dir)\n",
    "    \n",
    "    # subsample the data\n",
    "    mask = list(range(num_training, num_training + num_validation))\n",
    "    X_val = X_train[mask]\n",
    "    y_val = y_train[mask]\n",
    "    mask = list(range(num_training))\n",
    "    X_train = X_train[mask]\n",
    "    y_train = y_train[mask]\n",
    "    mask = list(range(num_test))\n",
    "    X_test = X_test[mask]\n",
    "    y_test = y_test[mask]\n",
    "    mask = np.random.choice(num_training, num_dev, replace=False)\n",
    "    X_dev = X_train[mask]\n",
    "    y_dev = y_train[mask]\n",
    "    \n",
    "    # Preprocessing: reshape the image data into rows\n",
    "    X_train = np.reshape(X_train, (X_train.shape[0], -1))\n",
    "    X_val = np.reshape(X_val, (X_val.shape[0], -1))\n",
    "    X_test = np.reshape(X_test, (X_test.shape[0], -1))\n",
    "    X_dev = np.reshape(X_dev, (X_dev.shape[0], -1))\n",
    "    \n",
    "    # Normalize the data: subtract the mean image\n",
    "    mean_image = np.mean(X_train, axis = 0)\n",
    "    X_train -= mean_image\n",
    "    X_val -= mean_image\n",
    "    X_test -= mean_image\n",
    "    X_dev -= mean_image\n",
    "    \n",
    "    # add bias dimension and transform into columns\n",
    "    X_train = np.hstack([X_train, np.ones((X_train.shape[0], 1))])\n",
    "    X_val = np.hstack([X_val, np.ones((X_val.shape[0], 1))])\n",
    "    X_test = np.hstack([X_test, np.ones((X_test.shape[0], 1))])\n",
    "    X_dev = np.hstack([X_dev, np.ones((X_dev.shape[0], 1))])\n",
    "    \n",
    "    return X_train, y_train, X_val, y_val, X_test, y_test, X_dev, y_dev\n",
    "\n",
    "\n",
    "# Invoke the above function to get our data.\n",
    "X_train, y_train, X_val, y_val, X_test, y_test, X_dev, y_dev = get_CIFAR10_data()\n",
    "print('Train data shape: ', X_train.shape)\n",
    "print('Train labels shape: ', y_train.shape)\n",
    "print('Validation data shape: ', X_val.shape)\n",
    "print('Validation labels shape: ', y_val.shape)\n",
    "print('Test data shape: ', X_test.shape)\n",
    "print('Test labels shape: ', y_test.shape)\n",
    "print('dev data shape: ', X_dev.shape)\n",
    "print('dev labels shape: ', y_dev.shape)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Softmax 分类器\n",
    "\n",
    "请在**daseCV/classifiers/softmax.py**中完成本节的代码。"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# 首先使用嵌套循环实现简单的softmax损失函数。\n",
    "# 打开文件 daseCV/classifiers/softmax.py 并补充完成\n",
    "# softmax_loss_naive 函数.\n",
    "\n",
    "from daseCV.classifiers.softmax import softmax_loss_naive\n",
    "import time\n",
    "\n",
    "# 生成一个随机的softmax权重矩阵，并使用它来计算损失。\n",
    "W = np.random.randn(3073, 10) * 0.0001\n",
    "loss, grad = softmax_loss_naive(W, X_dev, y_dev, 0.0)\n",
    "\n",
    "# As a rough sanity check, our loss should be something close to -log(0.1).\n",
    "print('loss: %f' % loss)\n",
    "print('sanity check: %f' % (-np.log(0.1)))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "tags": [
     "pdf-inline"
    ]
   },
   "source": [
    "**问题 1**\n",
    "\n",
    "\n",
    "为什么我们期望损失接近-log（0.1）？简要说明。\n",
    "\n",
    "$\\color{blue}{\\textit 答:}$ *在这里写上你的答案* \n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# 完成softmax_loss_naive，并实现使用嵌套循环的梯度的版本(naive)。\n",
    "loss, grad = softmax_loss_naive(W, X_dev, y_dev, 0.0)\n",
    "\n",
    "# 就像SVM那样，请使用数值梯度检查作为调试工具。\n",
    "# 数值梯度应接近分析梯度。\n",
    "from daseCV.gradient_check import grad_check_sparse\n",
    "f = lambda w: softmax_loss_naive(w, X_dev, y_dev, 0.0)[0]\n",
    "grad_numerical = grad_check_sparse(f, W, grad, 10)\n",
    "\n",
    "# 与SVM情况类似，使用正则化进行另一个梯度检查\n",
    "loss, grad = softmax_loss_naive(W, X_dev, y_dev, 5e1)\n",
    "f = lambda w: softmax_loss_naive(w, X_dev, y_dev, 5e1)[0]\n",
    "grad_numerical = grad_check_sparse(f, W, grad, 10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# 现在，我们有了softmax损失函数及其梯度的简单实现，\n",
    "# 接下来要在 softmax_loss_vectorized 中完成一个向量化版本.\n",
    "# 这两个版本应计算出相同的结果，但矢量化版本应更快。\n",
    "tic = time.time()\n",
    "loss_naive, grad_naive = softmax_loss_naive(W, X_dev, y_dev, 0.000005)\n",
    "toc = time.time()\n",
    "print('naive loss: %e computed in %fs' % (loss_naive, toc - tic))\n",
    "\n",
    "from daseCV.classifiers.softmax import softmax_loss_vectorized\n",
    "tic = time.time()\n",
    "loss_vectorized, grad_vectorized = softmax_loss_vectorized(W, X_dev, y_dev, 0.000005)\n",
    "toc = time.time()\n",
    "print('vectorized loss: %e computed in %fs' % (loss_vectorized, toc - tic))\n",
    "\n",
    "# 正如前面在SVM练习中所做的一样，我们使用Frobenius范数比较两个版本梯度。\n",
    "grad_difference = np.linalg.norm(grad_naive - grad_vectorized, ord='fro')\n",
    "print('Loss difference: %f' % np.abs(loss_naive - loss_vectorized))\n",
    "print('Gradient difference: %f' % grad_difference)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "tags": [
     "code"
    ]
   },
   "outputs": [],
   "source": [
    "# 使用验证集调整超参数（正则化强度和学习率）。您应该尝试不同的学习率和正则化强度范围; \n",
    "# 如果您小心的话，您应该能够在验证集上获得超过0.35的精度。\n",
    "from daseCV.classifiers import Softmax\n",
    "results = {}\n",
    "best_val = -1\n",
    "best_softmax = None\n",
    "learning_rates = [1e-7, 5e-7]\n",
    "regularization_strengths = [2.5e4, 5e4]\n",
    "\n",
    "################################################################################\n",
    "# 需要完成的事:                                                                        \n",
    "# 对验证集设置学习率和正则化强度。\n",
    "# 这与之前SVM中做的类似；\n",
    "# 保存训练效果最好的softmax分类器到best_softmax中。\n",
    "################################################################################\n",
    "# *****START OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****\n",
    "\n",
    "pass\n",
    "\n",
    "# *****END OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****\n",
    "    \n",
    "# Print out results.\n",
    "for lr, reg in sorted(results):\n",
    "    train_accuracy, val_accuracy = results[(lr, reg)]\n",
    "    print('lr %e reg %e train accuracy: %f val accuracy: %f' % (\n",
    "                lr, reg, train_accuracy, val_accuracy))\n",
    "    \n",
    "print('best validation accuracy achieved during cross-validation: %f' % best_val)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# 在测试集上评估\n",
    "# 在测试集上评估最好的softmax\n",
    "y_test_pred = best_softmax.predict(X_test)\n",
    "test_accuracy = np.mean(y_test == y_test_pred)\n",
    "print('softmax on raw pixels final test set accuracy: %f' % (test_accuracy, ))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "tags": [
     "pdf-inline"
    ]
   },
   "source": [
    "**问题 2** - *对或错*\n",
    "\n",
    "假设总训练损失定义为所有训练样本中每个数据点损失的总和。可能会有新的数据点添加到训练集中，同时SVM损失保持不变，但是对于Softmax分类器的损失而言，情况并非如此。\n",
    "\n",
    "$\\color{blue}{\\textit 你的回答:}$\n",
    "\n",
    "\n",
    "$\\color{blue}{\\textit 你的解释:}$\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# 可视化每个类别的学习到的权重\n",
    "w = best_softmax.W[:-1,:] # strip out the bias\n",
    "w = w.reshape(32, 32, 3, 10)\n",
    "\n",
    "w_min, w_max = np.min(w), np.max(w)\n",
    "\n",
    "classes = ['plane', 'car', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship', 'truck']\n",
    "for i in range(10):\n",
    "    plt.subplot(2, 5, i + 1)\n",
    "    \n",
    "    # Rescale the weights to be between 0 and 255\n",
    "    wimg = 255.0 * (w[:, :, :, i].squeeze() - w_min) / (w_max - w_min)\n",
    "    plt.imshow(wimg.astype('uint8'))\n",
    "    plt.axis('off')\n",
    "    plt.title(classes[i])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "---\n",
    "# 重要\n",
    "\n",
    "这里是作业的结尾处，请执行以下步骤:\n",
    "\n",
    "1. 点击`File -> Save`或者用`control+s`组合键，确保你最新的的notebook的作业已经保存到谷歌云。\n",
    "2. 执行以下代码确保 `.py` 文件保存回你的谷歌云。"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "\n",
    "FOLDER_TO_SAVE = os.path.join('drive/My Drive/', FOLDERNAME)\n",
    "FILES_TO_SAVE = ['daseCV/classifiers/softmax.py']\n",
    "\n",
    "for files in FILES_TO_SAVE:\n",
    "  with open(os.path.join(FOLDER_TO_SAVE, '/'.join(files.split('/')[1:])), 'w') as f:\n",
    "    f.write(''.join(open(files).readlines()))"
   ]
  }
 ],
 "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": "3.7.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}