5.3.1.2卷积神经网络-猫狗分类-使用数据增强的快速特征提取.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": true
   },
   "source": [
    "## 使用数据增强的特征提取\n",
    "\n",
    "扩展 conv_base 模型，然后在输入数据上端到端地运行模型。\n",
    "\n",
    "注意：只在有 GPU 的情况下才能尝试运行。它在 CPU 上是绝对难以运行的。"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Using TensorFlow backend.\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "WARNING:tensorflow:From /home/fc/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py:263: colocate_with (from tensorflow.python.framework.ops) is deprecated and will be removed in a future version.\n",
      "Instructions for updating:\n",
      "Colocations handled automatically by placer.\n"
     ]
    }
   ],
   "source": [
    "from keras.applications import VGG16\n",
    "conv_base = VGG16(weights='imagenet',\n",
    "                  include_top=False,\n",
    "                  input_shape=(150, 150, 3))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# 在卷积基上添加一个密集连接分类器\n",
    "from keras import models\n",
    "from keras import layers\n",
    "model = models.Sequential()\n",
    "model.add(conv_base)\n",
    "model.add(layers.Flatten())\n",
    "model.add(layers.Dense(256, activation='relu'))\n",
    "model.add(layers.Dense(1, activation='sigmoid'))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "#冻结网络\n",
    "conv_base.trainable = False"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Found 2000 images belonging to 2 classes.\n",
      "Found 1000 images belonging to 2 classes.\n",
      "WARNING:tensorflow:From /home/fc/anaconda3/lib/python3.6/site-packages/tensorflow/python/ops/math_ops.py:3066: to_int32 (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version.\n",
      "Instructions for updating:\n",
      "Use tf.cast instead.\n",
      "Epoch 1/30\n",
      "100/100 [==============================] - 681s 7s/step - loss: 0.5919 - acc: 0.7085 - val_loss: 0.4407 - val_acc: 0.8380\n",
      "Epoch 2/30\n",
      "100/100 [==============================] - 662s 7s/step - loss: 0.4891 - acc: 0.7870 - val_loss: 0.3777 - val_acc: 0.8540\n",
      "Epoch 3/30\n",
      "100/100 [==============================] - 658s 7s/step - loss: 0.4285 - acc: 0.8190 - val_loss: 0.3297 - val_acc: 0.8680\n",
      "Epoch 4/30\n",
      "100/100 [==============================] - 846s 8s/step - loss: 0.4086 - acc: 0.8195 - val_loss: 0.3101 - val_acc: 0.8750\n",
      "Epoch 5/30\n",
      "100/100 [==============================] - 1317s 13s/step - loss: 0.3943 - acc: 0.8220 - val_loss: 0.3117 - val_acc: 0.8710\n",
      "Epoch 6/30\n",
      " 99/100 [============================>.] - ETA: 5s - loss: 0.3703 - acc: 0.8449 "
     ]
    }
   ],
   "source": [
    "# 利用冻结的卷积基端到端地训练模型\n",
    "from keras.preprocessing.image import ImageDataGenerator\n",
    "from keras import optimizers\n",
    "import os\n",
    "base_dir = './data/cats_and_dogs_small'\n",
    "train_dir = os.path.join(base_dir, 'train')\n",
    "validation_dir = os.path.join(base_dir, 'validation')\n",
    "test_dir = os.path.join(base_dir, 'test')\n",
    "\n",
    "train_datagen = ImageDataGenerator(\n",
    "        rescale=1./255,\n",
    "        rotation_range=40,\n",
    "        width_shift_range=0.2,\n",
    "        height_shift_range=0.2,\n",
    "        shear_range=0.2,\n",
    "        zoom_range=0.2,\n",
    "        horizontal_flip=True,\n",
    "        fill_mode='nearest')\n",
    "\n",
    "test_datagen = ImageDataGenerator(rescale=1./255)\n",
    "\n",
    "train_generator = train_datagen.flow_from_directory(\n",
    "        train_dir,\n",
    "        target_size=(150, 150),\n",
    "        batch_size=20,\n",
    "        class_mode='binary')\n",
    "\n",
    "validation_generator = test_datagen.flow_from_directory(\n",
    "        validation_dir,\n",
    "        target_size=(150, 150),\n",
    "        batch_size=20,\n",
    "        class_mode='binary')\n",
    "\n",
    "model.compile(loss='binary_crossentropy',\n",
    "              optimizer=optimizers.RMSprop(lr=2e-5),\n",
    "              metrics=['acc'])\n",
    "\n",
    "history = model.fit_generator(\n",
    "        train_generator,\n",
    "        steps_per_epoch=100,\n",
    "        epochs=30,\n",
    "        validation_data=validation_generator,\n",
    "        validation_steps=50)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# 绘制训练过程中的损失曲线和精度曲线\n",
    "import matplotlib.pyplot as plt \n",
    "%matplotlib inline\n",
    "\n",
    "acc = history.history['acc'] \n",
    "val_acc = history.history['val_acc'] \n",
    "loss = history.history['loss'] \n",
    "val_loss = history.history['val_loss'] \n",
    "\n",
    "epochs = range(1, len(acc) + 1) \n",
    "\n",
    "plt.plot(epochs, acc, 'bo', label='Training acc') \n",
    "plt.plot(epochs, val_acc, 'b', label='Validation acc')\n",
    "plt.title('Training and validation accuracy') \n",
    "plt.legend() \n",
    "\n",
    "plt.figure() \n",
    "\n",
    "plt.plot(epochs, loss, 'bo', label='Training loss') \n",
    "plt.plot(epochs, val_loss, 'b', label='Validation loss')\n",
    "plt.title('Training and validation loss') \n",
    "plt.legend() \n",
    "\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": "3.6.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}