官网实例详解4.7（cifar10_cnn_tfaugment2d.py）-keras学习笔记四

基于CIFAR10（小批量图片）数据集训练简单的深度卷积神经网络
本例比较扩大数据（样本）集的两种方法:ImageGenerator 和 AugmentLayer

Keras实例目录

代码注释

'''Train a simple deep CNN on the CIFAR10 small images dataset.
基于CIFAR10（小批量图片）数据集训练简单的深度卷积神经网络
本例使用的是AugmentLayer方法
本例比较增加数据集的两种方法:ImageGenerator 和 AugmentLayer

ImageGenerator：图像生成器（增加样本数量）
AugmentLayer：增强（扩展、增加，增加样本数量）层

Using Tensorflow internal augmentation APIs by replacing ImageGenerator with
an embedded AugmentLayer using LambdaLayer, which is faster on GPU.
使用Tensorflow内部增强API,它通过使用嵌入的使用Lambda层的增强层替换ImageGenerator，Lambda层在GPU上更快

# Benchmark of `ImageGenerator` vs `AugmentLayer` both using augmentation 2D:
` ImageGenerator `基准 VS 'AugmentLayer' 都基于扩展2D `：
(backend = Tensorflow-GPU, Nvidia Tesla P100-SXM2)
（基于 = Tensorflow-GPU,, Nvidia Tesla P100-SXM2 （显卡））


Settings: horizontal_flip = True
设置：水平翻转 = True
----------------------------------------------------------------------------
Epoch     | ImageGenerator | ImageGenerator | AugmentLayer  | Augment Layer
Number    | %Accuracy      | Performance    | %Accuracy     | Performance
----------------------------------------------------------------------------
1         | 44.84          | 15ms/step      | 45.54         | 358us/step
2         | 52.34          |  8ms/step      | 50.55         | 285us/step
8         | 65.45          |  8ms/step      | 65.59         | 281us/step
25        | 76.74          |  8ms/step      | 76.17         | 280us/step
100       | 78.81          |  8ms/step      | 78.70         | 285us/step
---------------------------------------------------------------------------

Settings: rotation = 30.0
设置：旋转 =  30.0
----------------------------------------------------------------------------
Epoch     | ImageGenerator | ImageGenerator | AugmentLayer  | Augment Layer
Number    | %Accuracy      | Performance    | %Accuracy     | Performance
----------------------------------------------------------------------------
1         | 43.46          | 15ms/step      | 42.21         | 334us/step
2         | 48.95          | 11ms/step      | 48.06         | 282us/step
8         | 63.59          | 11ms/step      | 61.35         | 290us/step
25        | 72.25          | 12ms/step      | 71.08         | 287us/step
100       | 76.35          | 11ms/step      | 74.62         | 286us/step
---------------------------------------------------------------------------
(Corner process and rotation precision by `ImageGenerator` and `AugmentLayer`
are slightly different.)
（“ImageGenerator”和“AugmentLayer”的拐角处理和旋转精度略有不同。）
'''

from __future__ import print_function
import keras
from keras.datasets import cifar10
from keras.models import Sequential
from keras.layers import Dense, Dropout, Activation, Flatten
from keras.layers import Conv2D, Lambda, MaxPooling2D
from keras import backend as K
import os

if K.backend() != 'tensorflow':
    raise RuntimeError('This example can only run with the '
                       'TensorFlow backend, '
                       'because it requires TF-native augmentation APIs')

import tensorflow as tf


def augment_2d(inputs, rotation=0, horizontal_flip=False, vertical_flip=False):
    """Apply additive augmentation on 2D data.
    在二维数据上应用添加增强
    # Arguments
    参数
      rotation: A float, the degree range for rotation (0 <= rotation < 180),
      旋转：浮点数，旋转角度范围(0 <= rotation < 180),
          e.g. 3 for random image rotation between (-3.0, 3.0).
            例如，随机图像旋转3，范围是(-3.0, 3.0).
      horizontal_flip: A boolean, whether to allow random horizontal flip,
      水平翻转：布尔型，是否允许随机水平翻转
          e.g. true for 50% possibility to flip image horizontally.
          例如：翻转水平翻转图像50%的可能
      vertical_flip: A boolean, whether to allow random vertical flip,
      垂直翻转：布尔型，是否允许随机垂直翻转
          e.g. true for 50% possibility to flip image vertically.
          例如：翻转垂直翻转图像50%的可能

    # Returns
    返回
      input data after augmentation, whose shape is the same as its original.
      增强后的输入数据，其形状（对于二维图像指宽高）与原始数据（宽高）相同
    """
    if inputs.dtype != tf.float32:
        inputs = tf.image.convert_image_dtype(inputs, dtype=tf.float32)

    with tf.name_scope('augmentation'):
        shp = tf.shape(inputs)
        batch_size, height, width = shp[0], shp[1], shp[2]
        width = tf.cast(width, tf.float32)
        height = tf.cast(height, tf.float32)

        transforms = []
        identity = tf.constant([1, 0, 0, 0, 1, 0, 0, 0], dtype=tf.float32)

        if rotation > 0:
            angle_rad = rotation * 3.141592653589793 / 180.0
            angles = tf.random_uniform([batch_size], -angle_rad, angle_rad)
            f = tf.contrib.image.angles_to_projective_transforms(angles,
                                                                 height, width)
            transforms.append(f)

        if horizontal_flip:
            coin = tf.less(tf.random_uniform([batch_size], 0, 1.0), 0.5)
            shape = [-1., 0., width, 0., 1., 0., 0., 0.]
            flip_transform = tf.convert_to_tensor(shape, dtype=tf.float32)
            flip = tf.tile(tf.expand_dims(flip_transform, 0), [batch_size, 1])
            noflip = tf.tile(tf.expand_dims(identity, 0), [batch_size, 1])
            transforms.append(tf.where(coin, flip, noflip))

        if vertical_flip:
            coin = tf.less(tf.random_uniform([batch_size], 0, 1.0), 0.5)
            shape = [1., 0., 0., 0., -1., height, 0., 0.]
            flip_transform = tf.convert_to_tensor(shape, dtype=tf.float32)
            flip = tf.tile(tf.expand_dims(flip_transform, 0), [batch_size, 1])
            noflip = tf.tile(tf.expand_dims(identity, 0), [batch_size, 1])
            transforms.append(tf.where(coin, flip, noflip))

    if transforms:
        f = tf.contrib.image.compose_transforms(*transforms)
        inputs = tf.contrib.image.transform(inputs, f, interpolation='BILINEAR')
    return inputs


batch_size = 32
num_classes = 10
epochs = 100
num_predictions = 20
save_dir = '/tmp/saved_models'
model_name = 'keras_cifar10_trained_model.h5'

# The data, shuffled and split between train and test sets:
# 筛选（数据顺序打乱）、划分训练集和测试集
(x_train, y_train), (x_test, y_test) = cifar10.load_data()
print('x_train shape:', x_train.shape)
print(x_train.shape[0], 'train samples')
print(x_test.shape[0], 'test samples')

# Convert class vectors to binary class matrices.
# 类别向量转为多分类（num_classes = 10）矩阵
y_train = keras.utils.to_categorical(y_train, num_classes)
y_test = keras.utils.to_categorical(y_test, num_classes)

model = Sequential()
model.add(Lambda(augment_2d,
                 input_shape=x_train.shape[1:],
                 arguments={'rotation': 8.0, 'horizontal_flip': True}))
model.add(Conv2D(32, (3, 3), padding='same'))
model.add(Activation('relu'))
model.add(Conv2D(32, (3, 3)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))

model.add(Conv2D(64, (3, 3), padding='same'))
model.add(Activation('relu'))
model.add(Conv2D(64, (3, 3)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))

model.add(Flatten())
model.add(Dense(512))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(num_classes))
model.add(Activation('softmax'))

# initiate RMSprop optimizer
# 均方根反向传播（RMSprop，root mean square prop）优化
opt = keras.optimizers.rmsprop(lr=0.0001, decay=1e-6)

# Let's train the model using RMSprop
# 使用均方根反向传播（RMSprop）训练模型
model.compile(loss='categorical_crossentropy',
              optimizer=opt,
              metrics=['accuracy'])

x_train = x_train.astype('float32')
x_test = x_test.astype('float32')
x_train /= 255
x_test /= 255

model.fit(x_train, y_train,
          batch_size=batch_size,
          epochs=epochs,
          validation_data=(x_test, y_test),
          shuffle=True)

# Save model and weights
# 保存模型和权重（数据）
if not os.path.isdir(save_dir):
    os.makedirs(save_dir)
model_path = os.path.join(save_dir, model_name)
model.save(model_path)
print('Saved trained model at %s ' % model_path)

# Score trained model.
# 评估训练的模型
scores = model.evaluate(x_test, y_test, verbose=1)
print('Test loss:', scores[0])
print('Test accuracy:', scores[1])

代码执行

Keras详细介绍

英文：https://keras.io/

中文：http://keras-cn.readthedocs.io/en/latest/

实例下载

https://github.com/keras-team/keras

https://github.com/keras-team/keras/tree/master/examples

完整项目下载

方便没积分童鞋，请加企鹅452205574，共享文件夹。

包括：代码、数据集合（图片）、已生成model、安装库文件等。