猫狗识别

前言

整理的网上资源，方便大家学习，也不知道哪哪看到的了！

tensorflow

input_data.py:

import tensorflow as tf
import os
import numpy as np

#读取所有的训练集
def get_files(file_dir):
    cats = []
    label_cats = []
    dogs = []
    label_dogs = []
    for file in os.listdir(file_dir):
        name = file.split(sep='.')
        if 'cat' in name[0]:
            cats.append(file_dir + file)
            label_cats.append(0)
        elif 'dog' in name[0]:
            dogs.append(file_dir + file)
            label_dogs.append(1)
        image_list = np.hstack((cats, dogs))
        label_list = np.hstack((label_cats, label_dogs))
    # print('There are %d cats\nThere are %d dogs' %(len(cats), len(dogs)))
	#两行多列
    temp = np.array([image_list, label_list])
   # 转置矩阵，两列多行
    temp = temp.transpose()
    # 打乱顺序
    np.random.shuffle(temp)

    # 取出第一个元素为 image 第二个元素为 label
    image_list = list(temp[:, 0])
    label_list = list(temp[:, 1])
    label_list = [int(i) for i in label_list]
    return image_list, label_list

#自定义训练批次
# image_W ,image_H 指定图片大小，batch_size 每批读取的个数 ，capacity队列中 最多容纳元素的个数
def get_batch(image, label, image_W, image_H, batch_size, capacity):
    # 转换数据
    image = tf.cast(image, tf.string)
    label = tf.cast(label, tf.int32)

    # 将image 和 label 放倒队列里
    input_queue = tf.train.slice_input_producer([image, label])
    label = input_queue[1]
    # 读取图片的全部信息
    image_contents = tf.read_file(input_queue[0])
    # 把图片解码，3 为彩色图片
    image = tf.image.decode_jpeg(image_contents, channels=3)
    # 将图片以图片中心进行裁剪或者扩充为 指定的image_W，image_H
    image = tf.image.resize_image_with_crop_or_pad(image, image_W, image_H)
    # 对数据进行标准化,就是减去它的均值，除以他的方差
    image = tf.image.per_image_standardization(image)

    # 生成批次 
    image_batch, label_batch = tf.train.batch([image, label], batch_size=batch_size, num_threads=64, capacity=capacity)

    # 重新定义下 label_batch 的形状
    label_batch = tf.reshape(label_batch, [batch_size])
    # 转化图片
    image_batch = tf.cast(image_batch, tf.float32)
    return image_batch, label_batch

model.py:

import tensorflow as tf

# 结构
# conv1   卷积层 1
# pooling1_lrn  池化层 1
# conv2  卷积层 2
# pooling2_lrn 池化层 2
# local3 全连接层 1
# local4 全连接层 2
# softmax 全连接层 3
def inference(images, batch_size, n_classes):
    with tf.variable_scope('conv1') as scope:
        # 3*3 的卷积核，图片厚度是3，16个featuremap
        #即卷积后变细长
        weights = tf.get_variable('weights',
                                  shape=[3, 3, 3, 16],
                                  dtype=tf.float32,
                                  initializer=tf.truncated_normal_initializer(stddev=0.1, dtype=tf.float32))
        biases = tf.get_variable('biases',
                                 shape=[16],
                                 dtype=tf.float32,
                                 initializer=tf.constant_initializer(0.1))
        conv = tf.nn.conv2d(images, weights, strides=[1, 1, 1, 1], padding='SAME')
        pre_activation = tf.nn.bias_add(conv, biases)
        conv1 = tf.nn.relu(pre_activation, name=scope.name)

    with tf.variable_scope('pooling1_lrn') as scope:
        pool1 = tf.nn.max_pool(conv1, ksize=[1, 3, 3, 1], strides=[1, 2, 2, 1], padding='SAME', name='pooling1')
        norm1 = tf.nn.lrn(pool1, depth_radius=4, bias=1.0, alpha=0.001 / 9.0, beta=0.75, name='norm1')

    with tf.variable_scope('conv2') as scope:
        weights = tf.get_variable('weights',
                                  shape=[3, 3, 16, 16],
                                  dtype=tf.float32,
                                  initializer=tf.truncated_normal_initializer(stddev=0.1, dtype=tf.float32))
        biases = tf.get_variable('biases',
                                 shape=[16],
                                 dtype=tf.float32,
                                 initializer=tf.constant_initializer(0.1))
        conv = tf.nn.conv2d(norm1, weights, strides=[1, 1, 1, 1], padding='SAME')
        pre_activation = tf.nn.bias_add(conv, biases)
        conv2 = tf.nn.relu(pre_activation, name='conv2')

        # pool2 and norm2
    with tf.variable_scope('pooling2_lrn') as scope:
        norm2 = tf.nn.lrn(conv2, depth_radius=4, bias=1.0, alpha=0.001 / 9.0, beta=0.75, name='norm2')
        pool2 = tf.nn.max_pool(norm2, ksize=[1, 3, 3, 1], strides=[1, 1, 1, 1], padding='SAME', name='pooling2')

    with tf.variable_scope('local3') as scope:
        reshape = tf.reshape(pool2, shape=[batch_size, -1])
        dim = reshape.get_shape()[1].value
        weights = tf.get_variable('weights',
                                  shape=[dim, 128],
                                  dtype=tf.float32,
                                  initializer=tf.truncated_normal_initializer(stddev=0.005, dtype=tf.float32))
        biases = tf.get_variable('biases',
                                 shape=[128],
                                 dtype=tf.float32,
                                 initializer=tf.constant_initializer(0.1))
    local3 = tf.nn.relu(tf.matmul(reshape, weights) + biases, name=scope.name)

    # local4
    with tf.variable_scope('local4') as scope:
        weights = tf.get_variable('weights',
                                  shape=[128, 128],
                                  dtype=tf.float32,
                                  initializer=tf.truncated_normal_initializer(stddev=0.005, dtype=tf.float32))
        biases = tf.get_variable('biases',
                                 shape=[128],
                                 dtype=tf.float32,
                                 initializer=tf.constant_initializer(0.1))
        local4 = tf.nn.relu(tf.matmul(local3, weights) + biases, name='local4')

        # softmax
    with tf.variable_scope('softmax_linear') as scope:
        weights = tf.get_variable('softmax_linear',
                                  shape=[128, n_classes],
                                  dtype=tf.float32,
                                  initializer=tf.truncated_normal_initializer(stddev=0.005, dtype=tf.float32))
        biases = tf.get_variable('biases',
                                 shape=[n_classes],
                                 dtype=tf.float32,
                                 initializer=tf.constant_initializer(0.1))
        softmax_linear = tf.add(tf.matmul(local4, weights), biases, name='softmax_linear')

    return softmax_linear


def losses(logits, labels):
    with tf.variable_scope('loss') as scope:
        cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits \
            (logits=logits, labels=labels, name='xentropy_per_example')
        loss = tf.reduce_mean(cross_entropy, name='loss')
        tf.summary.scalar(scope.name + '/loss', loss)
    return loss


def trainning(loss, learning_rate):
    with tf.name_scope('optimizer'):
        optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate)
        global_step = tf.Variable(0, name='global_step', trainable=False)
        train_op = optimizer.minimize(loss, global_step=global_step)
    return train_op


def evaluation(logits, labels):
    with tf.variable_scope('accuracy') as scope:
        correct = tf.nn.in_top_k(logits, labels, 1)
        correct = tf.cast(correct, tf.float16)
        accuracy = tf.reduce_mean(correct)
        tf.summary.scalar(scope.name + '/accuracy', accuracy)
    return accuracy

training.py:

import os
import numpy as np
import tensorflow as tf
import input_data
import model

N_CLASSES = 2  #［1，0］ 或者 ［0，1］猫和狗的概率
IMG_W = 208  # 定义图片的大小
IMG_H = 208
BATCH_SIZE = 32  # 每批数据的大小
CAPACITY = 256
MAX_STEP = 1000  # 训练的步数
learning_rate = 0.0001  # 学习率，建议刚开始的 learning_rate <= 0.0001

def run_training():
    # 数据集
    train_dir = 'F:/dataset_kaggledogvscat/train/' 
    # 训练模型保存路径
    logs_train_dir = 'F:/dataset_kaggledogvscat/save/'

    # 获取图片和标签集
    train, train_label = input_data.get_files(train_dir)
    # 生成批次
    train_batch, train_label_batch = input_data.get_batch(train,
                                                          train_label,
                                                          IMG_W,
                                                          IMG_H,
                                                          BATCH_SIZE,
                                                          CAPACITY)
    # 进入模型
    train_logits = model.inference(train_batch, BATCH_SIZE, N_CLASSES)
    # 获取 loss
    train_loss = model.losses(train_logits, train_label_batch)
    # 训练
    train_op = model.trainning(train_loss, learning_rate)
    # 获取准确率
    train__acc = model.evaluation(train_logits, train_label_batch)
    # 合并 summary
    summary_op = tf.summary.merge_all()
    sess = tf.Session()
    # 保存summary
    train_writer = tf.summary.FileWriter(logs_train_dir, sess.graph)
    saver = tf.train.Saver()

    sess.run(tf.global_variables_initializer())
    coord = tf.train.Coordinator()
    threads = tf.train.start_queue_runners(sess=sess, coord=coord)

    try:
        for step in np.arange(MAX_STEP):
            if coord.should_stop():
                break
            _, tra_loss, tra_acc = sess.run([train_op, train_loss, train__acc])

            if step % 50 == 0:
                print('Step %d, train loss = %.2f, train accuracy = %.2f%%' % (step, tra_loss, tra_acc * 100.0))
                summary_str = sess.run(summary_op)
                train_writer.add_summary(summary_str, step)

            if step % 50 == 0 or (step + 1) == MAX_STEP:
                # 每隔X步保存一下模型
                checkpoint_path = os.path.join(logs_train_dir, 'model.ckpt')
                saver.save(sess, checkpoint_path, global_step=step)

    except tf.errors.OutOfRangeError:
        print('Done training -- epoch limit reached')
    finally:
        coord.request_stop()
    coord.join(threads)
    sess.close()


# train
run_training()

test.py:

# coding=utf-8
import tensorflow as tf
from PIL import Image
import matplotlib.pyplot as plt
import input_data
import numpy as np
import model
import os


# 选取一张图片
def get_one_image(train):
    files = os.listdir(train)
    n = len(files)
    ind = np.random.randint(0, n)
    img_dir = os.path.join(train, files[ind])
    image = Image.open(img_dir)
    plt.imshow(image)
    plt.show()
    image = image.resize([208, 208])
    image = np.array(image)
    return image


def evaluate_one_image():
    train = 'F:/dataset_kaggledogvscat/my/'
    image_array = get_one_image(train)

    with tf.Graph().as_default():
        BATCH_SIZE = 1  
        N_CLASSES = 2 
        # 转化图片格式
        image = tf.cast(image_array, tf.float32)
        # 图片标准化
        image = tf.image.per_image_standardization(image)
        # 图片->tensor
        image = tf.reshape(image, [1, 208, 208, 3])
        logit = model.inference(image, BATCH_SIZE, N_CLASSES)
        # 因为 inference 的返回没有用激活函数，所以在这里对结果用softmax 激活
        logit = tf.nn.softmax(logit)

        #占位符
        x = tf.placeholder(tf.float32, shape=[208, 208, 3])

        # 我门存放模型的路径
        logs_train_dir = 'F:/dataset_kaggledogvscat/save/'
     
        saver = tf.train.Saver()

        with tf.Session() as sess:

            print("从指定的路径中加载模型。。。。")
            ckpt = tf.train.get_checkpoint_state(logs_train_dir)
            if ckpt and ckpt.model_checkpoint_path:
                global_step = ckpt.model_checkpoint_path.split('/')[-1].split('-')[-1]
                saver.restore(sess, ckpt.model_checkpoint_path)
                print('模型加载成功, 训练的步数为 %s' % global_step)
            else:
                print('模型加载失败，，，文件没有找到')
                # 将图片输入到模型计算
            prediction = sess.run(logit, feed_dict={x: image_array})
            # 获取输出结果中最大概率的索引
            max_index = np.argmax(prediction)
            if max_index == 0:
                print('猫的概率 %.6f' % prediction[:, 0])
            else:
                print('狗的概率 %.6f' % prediction[:, 1]) 
# 测试
evaluate_one_image()

效果

插入：
通俗理解tf.name_scope()、tf.variable_scope()
下面是测试代码：

import tensorflow as tf
'''
get_variable函数共有十一个参数，常用的有：名称name、变量规格shape、变量类型dtype、变量初始化方式initializer。该函数的作用是创建新的tensorflow变量，常见的initializer有：常量初始化器tf.constant_initializer、正太分布初始化器tf.random_normal_initializer、截断正态分布初始化器tf.truncated_normal_initializer、均匀分布初始化器tf.random_uniform_initializer。
'''

with tf.variable_scope('V1', reuse=None):
    a1 = tf.get_variable(name='a1', shape=[1], initializer=tf.constant_initializer(1))
    a2 = tf.Variable(tf.random_normal(shape=[2, 3], mean=0, stddev=1), name='a2')
with tf.variable_scope('V1', reuse=True):
    a3 = tf.get_variable(name='a1', shape=[1], initializer=tf.constant_initializer(1))
    a4 = tf.Variable(tf.random_normal(shape=[2, 3], mean=0, stddev=1), name='a2')

with tf.Session() as sess:
    sess.run(tf.initialize_all_variables())
    print(a1.name)
    print(a2.name)
    print(a3.name)
    print(a4.name)

with tf.name_scope("my_name_scope"):
    v1 = tf.get_variable("var1", [1], dtype=tf.float32)
    v2 = tf.Variable(1, name="var2", dtype=tf.float32)
    a = tf.add(v1, v2)
    print(v1.name)
    print(v2.name)
    print(a.name)

with tf.variable_scope("my_variable_scope"):
    v1 = tf.get_variable("var1", [1], dtype=tf.float32)
    v2 = tf.Variable(1, name="var2", dtype=tf.float32)
    a = tf.add(v1, v2)
    print(v1.name)
    print(v2.name)
    print(a.name)

数据集

数据集分享

keras

文档十分详细

from keras import layers
from keras import models
import os
#设置文件目录
base_dir = 'F:/kaggle-cats-and-dogs/cats_and_dogs_small/'
trainDir = os.path.join(base_dir , 'train/')
valDir = os.path.join(base_dir , 'validation/')
testDir = os.path.join(base_dir , 'test/')
#训练集
trainCatDir = os.path.join(trainDir, 'cats')
trainDogDir = os.path.join(trainDir, 'dogs')
#验证集
valCatDir = os.path.join(valDir , 'cats')
valDogDir = os.path.join(valDir , 'dogs')
#测试集
testCatDir = os.path.join(trainDir , 'cats')
testDogDir = os.path.join(trainDir , 'dogs')

#创建模型
model = models.Sequential()
#卷积层，输出特征图的深度为32，提取信息的窗口大小(3,3),卷积核的大小也为(3,3),激活函数relu,输入图片大小(150,150,3)
model.add(layers.Conv2D(32, (3, 3), activation='relu',input_shape=(150, 150, 3)))
#池化层，窗口大小为(2,2)，缩小特征图的尺寸
model.add(layers.MaxPooling2D((2, 2)))

model.add(layers.Conv2D(64, (3, 3), activation='relu'))
model.add(layers.MaxPooling2D((2, 2)))

model.add(layers.Conv2D(128, (3, 3), activation='relu'))
model.add(layers.MaxPooling2D((2, 2)))

model.add(layers.Conv2D(128, (3, 3), activation='relu'))
model.add(layers.MaxPooling2D((2, 2)))

model.add(layers.Flatten())
model.add(layers.Dropout(rate=0.5))
#扁平层,将多维的输入转化为一维的输出
model.add(layers.Dense(512, activation='relu'))
#全连接层，将提取的特征组合，得出结果
model.add(layers.Dense(1, activation='sigmoid'))

#设置损失函数，优化器，模型在训练和测试时的性能指标
from keras import optimizers

model.compile(loss='binary_crossentropy',
  optimizer=optimizers.RMSprop(lr=1e-4),
  metrics=['acc'])

#配置图片生成器
from keras.preprocessing.image import ImageDataGenerator
#将图片像素缩小为[0,1]之间的浮点数
train_datagen = ImageDataGenerator(
            rescale=1./255,
            rotation_range=40,          #图像随机旋转的最大角度
            width_shift_range=0.2,      #图片在水平位置上偏移的最大百分比值
            height_shift_range=0.2,     #数值位置上
            shear_range=0.2,            #随机错位切换的角度
            zoom_range=0.2,             #图片随机缩放的范围
            horizontal_flip=True        #随机将一半的图片进行水平翻转
)
#验证集的数据不能增强
test_datagen = ImageDataGenerator(rescale=1./255)

#创建图片生成器
train_generator = train_datagen.flow_from_directory(
         trainDir,                  #图片地址
         target_size=(150, 150),    #将图片调整为(150,150)大小
         batch_size=32,             #设置批量数据的大小为32
         class_mode='binary'        #设置返回标签的类型
)

val_generator = test_datagen.flow_from_directory(
         valDir,
         target_size=(150, 150),
         batch_size=32,
         class_mode='binary'
)

#拟合模型
history = model.fit_generator(
      train_generator,
      steps_per_epoch=100,  #迭代进入下一轮次需要抽取的批次
      epochs=100,           #数据迭代的轮数
      validation_data=val_generator,
      validation_steps=50   #验证集用于评估的批次
)

#保存模型
model.save('cats_and_dogs_small_1.h5')

#画出结果
import matplotlib.pyplot as plt

#查看变量，发现history.history中就只有这四个值，分别是准确度，验证集准确度，损失，验证集损失
acc = history.history['acc']
val_acc = history.history['val_acc']
loss = history.history['loss']
val_loss = history.history['val_loss']
epochs = range(1, len(acc) + 1)

#正确率
plt.figure(1)
plt.plot(epochs, acc, 'bo', label='Training acc')
plt.plot(epochs, val_acc, 'b', label='Validation acc')
plt.title('Training and validation accuracy')
plt.legend()
plt.show()

加载模型：

import cv2
import numpy as np
from keras.models import load_model

model = load_model('cats_and_dogs_small_1.h5')  #选取自己的.h模型名称
#path = r'cats_and_dogs_small\test\dogs\dog.1501.jpg'
path = r'F:\dataset_kaggledogvscat\my\1 (7).jpg'
img = cv2.imread(path)

def format_pucture(file_path, shape):
    from keras.preprocessing import image
    img = image.load_img(file_path, target_size=shape)
    array = image.img_to_array(img)
    array = array.reshape((1,) + shape) / 255
    return array

pucture = format_pucture(path, (150, 150, 3))
predict = model.predict(pucture)
res = predict[0][0]
print(res)
if res < 0.5:
    print("this is a cat")
else:
    if res > 0.5:
        print("this is a dog")

cv2.imshow("Image1", img)
cv2.waitKey(0)

效果

数据集

数据集分享