Python深度学习基于Tensorflow（4）Tensorflow 数据处理和数据可视化

链接：https://pan.baidu.com/s/1e9skHjPAzy9Bfd5Z7Xl70A?pwd=zynb 
提取码：zynb

import tensorflow as tf
import os
## 设置文件位置以及标签
data_dir = "./data/cat-dog"
train_cat_dir = data_dir + '/train/cats/'
train_dog_dir = data_dir + "/train/dogs/"
test_cat_dir = data_dir + "/test/cats/"
test_dog_dir = data_dir + "/test/dogs/"
train_cat_filenames = [train_cat_dir + filename for filename in os.listdir(train_cat_dir)]
train_dog_filenames = [train_dog_dir + filename for filename in os.listdir(train_dog_dir)]
train_filenames = train_cat_filenames + train_dog_filenames
train_labels = [0]*len(train_cat_filenames) + [1]*len(train_dog_filenames)
test_cat_filenames = [test_cat_dir + filename for filename in os.listdir(test_cat_dir)]
test_dog_filenames = [test_dog_dir + filename for filename in os.listdir(test_dog_dir)]
test_filenames = test_cat_filenames + test_dog_filenames
test_labels = [0]*len(test_cat_filenames) + [1]*len(test_dog_filenames)
## 创建生成TFRecord数据集函数
def encoder(filenames, labels, tfrecord_file):
    with tf.io.TFRecordWriter(tfrecord_file) as writer:
        for filename, label in zip(filenames, labels):
            with open(filename, 'rb') as f:
                image = f.read()
                ## 将img，label转化为向量的形式  这里只能是普通的形式，不能np和tf，所以读取图片最好是直接读取字节，虽然np.array(Image.open(filename)) 很快，但是array.tolist() 很慢，这就导致效果很慢，所以这里还是读字节最后再在读取tfrecord数据的时候，使用tf.io.decode_jpeg对图片进行解码。
                image_feature = tf.train.Feature(bytes_list=tf.train.BytesList(value=[image]))
                label_feature = tf.train.Feature(int64_list=tf.train.Int64List(value=[label]))
                
                ## 建立feature字典
                feature = {
                    'image': image_feature,
                    'label': label_feature
                }
                # 通过字典创建example，example对象对label和image数据进行封装
                example = tf.train.Example(features=tf.train.Features(feature=feature))
                # 将example序列化并写入字典
                writer.write(example.SerializeToString())
## 创建TFRecord
encoder(train_filenames, train_labels, 'train.tfrecords')
encoder(test_filenames, test_labels, 'test.tfrecords')

tf.train.Feature(bytes_list=tf.train.BytesList(value=[*]))
tf.train.Feature(int64_list=tf.train.Int64List(value=[*]))
tf.train.Feature(float_list=tf.train.FloatList(value=[*]))

def decoder(tfrecord_file, is_train_dataset=None):
    #构建dataset
    dataset = tf.data.TFRecordDataset(tfrecord_file)
    #说明特征的描述属性，为解吗每个example使用
    feature_discription = {
        'image': tf.io.FixedLenFeature([], tf.string),
        'label': tf.io.FixedLenFeature([], tf.int64)
    }
    def _parse_example(example_string): # 解码每一个example
        #将文件读入到队列中
        feature_dic = tf.io.parse_single_example(example_string, feature_discription)
        feature_dic['image'] = tf.io.decode_jpeg(feature_dic['image'])
        #对图片进行resize，属于数据处理的操作
        feature_dic['image'] = tf.image.resize(feature_dic['image'], [256, 256])/255.0
        return feature_dic['image'], feature_dic['label']
    batch_size = 4
    if is_train_dataset is not None:
        #tf.data.experimental.AUTOTUNE#根据计算机性能进行运算速度的调整
        dataset = dataset.map(_parse_example).shuffle(buffer_size=2000).batch(batch_size).prefetch(tf.data.experimental.AUTOTUNE)
    else:
        dataset = dataset.map(_parse_example)
        dataset = dataset.batch(batch_size)
    return dataset
train_data = decoder('train.tfrecords', is_train_dataset=True)
test_data = decoder('test.tfrecords')

import matplotlib.pyplot as plt
def plot_img_label(elemtents):
    imgs, labels = elemtents
    num_imgs = labels.shape[0]
    for i in range(num_imgs):
        plt.subplot(1,num_imgs,i+1)
        plt.axis('off')
        plt.title(labels[i].numpy())
        plt.imshow(imgs[i].numpy())
    plt.show()
plot_img_label(train_data.take(1).get_single_element())

# 解码图片 转换图片数据类型 调整图片尺寸
image = tf.image.decode_jpeg(image, channels=3)
image = tf.image.convert_image_dtype(image, dtype=tf.float32)
image = tf.image.resize(image, (156, 156))
# 对图片进行上下左右随机的翻转,调整明亮度最后旋转90度
images = tf.image.random_flip_left_right(images)
images = tf.image.random_flip_up_down(images)
images = tf.image.random_brightness(images, 1)
images = tf.image.rot90(images, 1)

# windows
plt.rcParams['font.sans-serif']=['SimHei']
plt.rcParams['axes.unicode_minus'] = False 
# mac
plt.rcParams['font.sans-serif'] = ['Arial Unicode MS']
plt.rcParams['axes.unicode_minus'] = False

logdir = os.path.join("logs", datetime.datetime.now().strftime("%Y%m%d-%H%M%S"))
tensorboard_callback = tf.keras.callbacks.TensorBoard(logdir, histogram_freq=1)
model.fit(x=x_train, 
    y=y_train, 
    epochs=5, 
    validation_data=(x_test, y_test), 
    callbacks=[tensorboard_callback])

%load_ext tensorboard
%tensorboard --logdir logs
from tensorboard import notebook
notebook.list() # View open TensorBoard instances