machinelearning_notebook/7_deep_learning/1_CNN/02-LeNet5.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# LeNet5\n",
    "\n",
    "LeNet 诞生于 1994 年，是最早的卷积神经网络之一，并且推动了深度学习领域的发展。自从 1988 年开始，在多次迭代后这个开拓性成果被命名为 LeNet5。LeNet5 的架构的提出是基于如下的观点：图像的特征分布在整张图像上，通过带有可学习参数的卷积，从而有效的减少了参数数量，能够在多个位置上提取相似特征。\n",
    "\n",
    "在LeNet5提出的时候，没有 GPU 帮助训练，甚至 CPU 的速度也很慢，因此，LeNet5的规模并不大。其包含七个处理层，每一层都包含可训练参数（权重），当时使用的输入数据是 $32 \\times 32$ 像素的图像。LeNet-5 这个网络虽然很小，但是它包含了深度学习的基本模块：卷积层，池化层，全连接层。它是其他深度学习模型的基础，这里对LeNet5进行深入分析和讲解，通过实例分析，加深对与卷积层和池化层的理解。"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "import sys\n",
    "sys.path.append('..')\n",
    "\n",
    "import numpy as np\n",
    "import torch\n",
    "from torch import nn\n",
    "from torch.autograd import Variable\n",
    "from torchvision.datasets import CIFAR10\n",
    "from torchvision import transforms as tfs"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "import torch\n",
    "from torch import nn\n",
    "\n",
    "lenet5 = nn.Sequential(\n",
    "    nn.Conv2d(1, 6, kernel_size=5, padding=2), nn.Sigmoid(),\n",
    "    nn.AvgPool2d(kernel_size=2, stride=2),\n",
    "    nn.Conv2d(6, 16, kernel_size=5), nn.Sigmoid(),\n",
    "    nn.AvgPool2d(kernel_size=2, stride=2),\n",
    "    nn.Flatten(),\n",
    "    nn.Linear(16 * 5 * 5, 120), nn.Sigmoid(),\n",
    "    nn.Linear(120, 84), nn.Sigmoid(),\n",
    "    nn.Linear(84, 10) )"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "from utils import train\n",
    "\n",
    "# 使用数据增强\n",
    "def train_tf(x):\n",
    "    im_aug = tfs.Compose([\n",
    "        tfs.Resize(224),\n",
    "        tfs.ToTensor(),\n",
    "        tfs.Normalize([0.5, 0.5, 0.5], [0.5, 0.5, 0.5])\n",
    "    ])\n",
    "    x = im_aug(x)\n",
    "    return x\n",
    "\n",
    "def test_tf(x):\n",
    "    im_aug = tfs.Compose([\n",
    "        tfs.Resize(224),\n",
    "        tfs.ToTensor(),\n",
    "        tfs.Normalize([0.5, 0.5, 0.5], [0.5, 0.5, 0.5])\n",
    "    ])\n",
    "    x = im_aug(x)\n",
    "    return x\n",
    "     \n",
    "train_set = CIFAR10('../../data', train=True, transform=train_tf)\n",
    "train_data = torch.utils.data.DataLoader(train_set, batch_size=64, shuffle=True)\n",
    "test_set  = CIFAR10('../../data', train=False, transform=test_tf)\n",
    "test_data = torch.utils.data.DataLoader(test_set, batch_size=128, shuffle=False)\n",
    "\n",
    "net = lenet5\n",
    "optimizer = torch.optim.SGD(net.parameters(), lr=1e-1)\n",
    "criterion = nn.CrossEntropyLoss()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "(l_train_loss, l_train_acc, l_valid_loss, l_valid_acc) = train(net, \n",
    "                                                               train_data, test_data, \n",
    "                                                               20, \n",
    "                                                               optimizer, criterion,\n",
    "                                                               use_cuda=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "import matplotlib.pyplot as plt\n",
    "%matplotlib inline\n",
    "\n",
    "plt.plot(l_train_loss, label='train')\n",
    "plt.plot(l_valid_loss, label='valid')\n",
    "plt.xlabel('epoch')\n",
    "plt.legend(loc='best')\n",
    "plt.savefig('fig-res-lenet5-train-validate-loss.pdf')\n",
    "plt.show()\n",
    "\n",
    "plt.plot(l_train_acc, label='train')\n",
    "plt.plot(l_valid_acc, label='valid')\n",
    "plt.xlabel('epoch')\n",
    "plt.legend(loc='best')\n",
    "plt.savefig('fig-res-lenet5-train-validate-acc.pdf')\n",
    "plt.show()"
   ]
  }
 ],
 "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": "3.5.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}