经典的10-monkeys和cifa10数据集进行分类

第一步先在kaggle注册账号密码（接受验证码需要翻墙！）
搜索10monkeys,下载数据集，数据集是已经分好类的文件夹。

注意目录：两个training

所以我们在调用训练集文件夹时候一定要打两次地址

train_dir = "input-monkeys/training/training"
valid_dir = "input-monkeys/validation/validation"
label_file = "input-monkeys/monkey_labels.txt"

然后用os这个包判断是否存在

#用os来判断路径是否存在
print(os.path.exists(train_dir))
print(os.path.exists(valid_dir))
print(os.path.exists(label_file))

编写读取数据的代码
用pd.read_csv API读取
labels是子文件夹到真正文件夹的映射

#指定哪一行作为表头。默认设置为0（即第一行作为表头），如果没有表头的话，要修改参数，设置header=None
labels = pd.read_csv(label_file,header = 0)
print(labels)

设置输入相同尺寸大小的图片：

#定义缩放后图片参数
height = 128
width = 128
channels = 3
batch_size = 64
num_classes = 10

tf.dataset用来读取数据，ImageDataGenerator用来读取图片数据

#ImageDataGenerator 帮助处理图片,rescale1/255,每个像素点/255-->(0,1)
#rotation_range:将图片随机旋转正负40度角度
#width_shift_range代表位移，增加位移鲁棒性，水平，height:竖直,小于1代表随机比例范围，大于1代表像素值
#shear_range:剪切强度,zoom_range:缩放强度
#horizonetal_flip:是否做水平翻转，fill_mode:是否操作后填充像素，“nearest"用附近的真实像素值填充。
train_datagen = keras.preprocessing.image.ImageDataGenerator(
    rescale = 1./255,
    rotation_range=40,
    width_shift_range = 0.2,
    height_shift_range = 0.2,
    shear_range = 0.2,
    zoom_range = 0.2,
    horizontal_flip = True,
    fill_mode = 'nearest',
)

如果targets函数是one-hot编码，用 categorical_crossentropy，one-hot 编码：[0, 0, 1], [1, 0, 0], [0, 1, 0]
如果tagets函数是数字编码 ，用 sparse_categorical_crossentropy，数字编码：2, 0, 1

#调取图片，并且按上方法处理(seed:随机数,shuffle:是否混排,class_mode:label的编码格式)
train_generator = train_datagen.flow_from_directory(train_dir,
                                                   target_size = (height,width),
                                                   batch_size =batch_size,
                                                   seed = 7,
                                                   shuffle =True,
                                                   class_mode = "categorical"
                                                  )
#在验证集很多操作不用毕竟只是做验证，但是缩放还是得做,做验证，没有必要混排
valid_datagen = keras.preprocessing.image.ImageDataGenerator(rescale = 1./255)
valid_generator = valid_datagen.flow_from_directory(valid_dir,
                                                   target_size = (height,width),
                                                   batch_size =batch_size,
                                                   seed = 7,
                                                   shuffle =False,
                                                   class_mode = "categorical"
                                                  )

看一下都有多少数据

train_num = train_generator.samples
valid_num = valid_generator.samples
print(train_num,valid_num)

下面从generator中取数据：
.next可以获得下一组数据

for i in range(2):
    x,y = train_generator.next()
    print(x.shape, y.shape)
    print(y)

来定义模型:

# 类似，两个卷积加一个pooling
# !!!!!selu在全连接情况一般会起到一个很好的效果，但是卷积一般还是relu好一点
model = keras.models.Sequential([
    keras.layers.Conv2D(filters=32, kernel_size=3, padding='same',
                        activation='relu', input_shape=[width, height, channels]),
    keras.layers.Conv2D(filters=32, kernel_size=3, padding='same',
                        activation='relu'),
    keras.layers.MaxPool2D(pool_size=2),

    keras.layers.Conv2D(filters=64, kernel_size=3, padding='same',
                        activation='relu'),
    keras.layers.Conv2D(filters=64, kernel_size=3, padding='same',
                        activation='relu'),
    keras.layers.MaxPool2D(pool_size=2),

    keras.layers.Conv2D(filters=128, kernel_size=3, padding='same',
                        activation='relu'),
    keras.layers.Conv2D(filters=128, kernel_size=3, padding='same',
                        activation='relu'),
    keras.layers.MaxPool2D(pool_size=2),
    keras.layers.Flatten(),
    keras.layers.Dense(128, activation='relu'),
    keras.layers.Dense(num_classes, activation='softmax'),
])
model.compile(loss="categorical_crossentropy",
              optimizer="adam", metrics=['accuracy'])
print(model.summary())

#epoch数目代表完整训练样本得数目，steps_per_epoch代表训练批次
epochs = 10
history = model.fit_generator(train_generator,
                             steps_per_epoch= train_num//batch_size,
                             epochs= epochs,
                             validation_data = valid_generator,
                             validation_steps = valid_num //batch_size
                             )
print(history.history.keys())

分开打印曲线

def plot_learning_curves(history,label,epochs,min_value,max_value):
    data = {}
    data[label] = history.history[label]
    data['val_'+label] = history.history['val_'+label]
    pd.DataFrame(data).plot(figsize = (8,5))
    plt.grid(True)
    plt.axis([0,epochs,min_value,max_value])
    plt.show()

plot_learning_curves(history,'acc',epochs,0,1)
plot_learning_curves(history,'loss',epochs,1.5,2.5)