22、深度学习在图像处理中的应用：图像分类与目标检测

深度学习在图像处理中的应用：图像分类与目标检测

1. 用Keras的VGG - 16对猫狗图像进行分类

1.1 数据准备

首先，我们需要从Kaggle的Dogs vs. Cats竞赛中下载训练和测试图像数据集（https://www.kaggle.com/c/dogs-vs-cats ）。然后，我们将在训练图像上从头开始训练VGG - 16网络。

1.2 训练阶段

以下是在训练数据集上拟合模型的代码：

import cv2 # working with, mainly resizing, images
import numpy as np # dealing with arrays
import os # dealing with directories
from random import shuffle # mixing up or currently ordered data that might
lead our network astray in training.
from tqdm import tqdm # a nice pretty percentage bar for tasks.
from keras.utils import to_categorical

TRAIN_DIR = 'C:\Courses\My Book\Chapter10\\train' # point to the right path
for the training images
TEST_DIR = 'C:\Courses\My Book\Chapter10\\test'