拓展神经网络八股（入门级）

自制数据集

minst等数据集是别人打包好的，如果是本领域的数据集。自制数据集。

替换

把图片路径和标签文件输入到函数里，并返回输入特征和标签

要生成.npy格式的数据集，在进行读入训练集。

只需要把图片灰度值数据拼接到特征列表，标签添加到标签列表,提取操作函数如下：

def generateds(path, txt):
    f = open(txt, 'r')
    contents = f.readlines() #读取所有行
    f.close()
    x, y_ = [], []
    for content in contents:
        value = content.split()
        img_path = path + value[0]#找到图片索引路径
        img = Image.open(img_path) #图片打开
        img = np.array(img.convert('L')) # 图片变为8位灰度的npy格式的数据集                    
        img = img / 255.
        x.append(img)
        y_.append(value[1])
        print('loading:' + content) # 打印状态提示
    x = np.array(x)
    y_ = np.array(y_)
    y_ = y_astype(np.int64)
    return x, y_

完整代码

import tensorflow as tf
from PIL import Image
import numpy as np
import os

train_path = './fashion_image_label/fashion_train_jpg_60000/'
train_txt = './fashion_image_label/fashion_train_jpg_60000.txt'
x_train_savepath = './fashion_image_label/fashion_x_train.npy'
y_train_savepath = './fashion_image_label/fahion_y_train.npy'

test_path = './fashion_image_label/fashion_test_jpg_10000/'
test_txt = './fashion_image_label/fashion_test_jpg_10000.txt'
x_test_savepath = './fashion_image_label/fashion_x_test.npy'
y_test_savepath = './fashion_image_label/fashion_y_test.npy'


def generateds(path, txt):
    f = open(txt, 'r')
    contents = f.readlines()  # 按行读取
    f.close()
    x, y_ = [], []
    for content in contents:
        value = content.split()  # 以空格分开，存入数组
        img_path = path + value[0]
        img = Image.open(img_path)
        img = np.array(img.convert('L'))
        img = img / 255.
        x.append(img)
        y_.append(value[1])
        print('loading : ' + content)

    x = np.array(x)
    y_ = np.array(y_)
    y_ = y_.astype(np.int64)
    return x, y_


if os.path.exists(x_train_savepath) and os.path.exists(y_train_savepath) and os.path.exists(
        x_test_savepath) and os.path.exists(y_test_savepath):
    print('-------------Load Datasets-----------------')
    x_train_save = np.load(x_train_savepath)
    y_train = np.load(y_train_savepath)
    x_test_save = np.load(x_test_savepath)
    y_test = np.load(y_test_savepath)
    x_train = np.reshape(x_train_save, (len(x_train_save), 28, 28))
    x_test = np.reshape(x_test_save, (len(x_test_save), 28, 28))
else:
    print('-------------Generate Datasets-----------------')
    x_train, y_train = generateds(train_path, train_txt)
    x_test, y_test = generateds(test_path, test_txt)

    print('-------------Save Datasets-----------------')
    x_train_save = np.reshape(x_train, (len(x_train), -1))
    x_test_save = np.reshape(x_test, (len(x_test), -1))
    np.save(x_train_savepath, x_train_save)
    np.save(y_train_savepath, y_train)
    np.save(x_test_savepath, x_test_save)
    np.save(y_test_savepath, y_test)

model = tf.keras.models.Sequential([
    tf.keras.layers.Flatten(),
    tf.keras.layers.Dense(128, activation='relu'),
    tf.keras.layers.Dense(10, activation='softmax')
])

model.compile(optimizer='adam',
              loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=False),
              metrics=['sparse_categorical_accuracy'])

model.fit(x_train, y_train, batch_size=32, epochs=5, validation_data=(x_test, y_test), validation_freq=1)
model.summary()

数据增强

如果数据量过少，模型见识不足。增加数据，提高泛化力。

用来应对因为拍照角度不同引起的图片变形

image_gen_train=tf,keras.preprocessing,image.ImageDataGenneratorP(...)

image_gen)train,fit(x_train)

import tensorflow as tf
from tensorflow.keras.preprocessing.image import ImageDataGenerator

fashion = tf.keras.datasets.fashion_mnist
(x_train, y_train), (x_test, y_test) = fashion.load_data()
x_train, x_test = x_train / 255.0, x_test / 255.0

x_train = x_train.reshape(x_train.shape[0], 28, 28, 1)  # 给数据增加一个维度，使数据和网络结构匹配

image_gen_train = ImageDataGenerator(
    rescale=1. / 1.,  # 如为图像，分母为255时，可归至0～1
    rotation_range=45,  # 随机45度旋转
    width_shift_range=.15,  # 宽度偏移
    height_shift_range=.15,  # 高度偏移
    horizontal_flip=True,  # 水平翻转
    zoom_range=0.5  # 将图像随机缩放阈量50％
)
image_gen_train.fit(x_train)

model = tf.keras.models.Sequential([
    tf.keras.layers.Flatten(),
    tf.keras.layers.Dense(128, activation='relu'),
    tf.keras.layers.Dense(10, activation='softmax')
])

model.compile(optimizer='adam',
              loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=False),
              metrics=['sparse_categorical_accuracy'])

model.fit(image_gen_train.flow(x_train, y_train, batch_size=32), epochs=5, validation_data=(x_test, y_test),
          validation_freq=1)
model.summary()

因为是标准MINST数据集，因此在准确度上看不出来，需要在具体应用中才能体现

断点续训

实时保存最优模型

保存模型参数可以使用tensorflow提供的ModelCheckpoint(filepath=checkpoint_save,

save_weight_only,sabe_best_only)

参数提取

获取各层网络最优参数，可以在各个平台实现应用

model.trainable_variables 返回模型中可训练参数

acc/loss可视化

查看训练效果

history=model.fit()

import tensorflow as tf
import os
import numpy as np
from matplotlib import pyplot as plt

np.set_printoptions(threshold=np.inf)

fashion = tf.keras.datasets.fashion_mnist
(x_train, y_train), (x_test, y_test) = fashion.load_data()
x_train, x_test = x_train / 255.0, x_test / 255.0

model = tf.keras.models.Sequential([
    tf.keras.layers.Flatten(),
    tf.keras.layers.Dense(128, activation='relu'),
    tf.keras.layers.Dense(10, activation='softmax')
])

model.compile(optimizer='adam',
              loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=False),
              metrics=['sparse_categorical_accuracy'])

checkpoint_save_path = "./checkpoint/fashion.ckpt"
if os.path.exists(checkpoint_save_path + '.index'):
    print('-------------load the model-----------------')
    model.load_weights(checkpoint_save_path)

cp_callback = tf.keras.callbacks.ModelCheckpoint(filepath=checkpoint_save_path,
                                                 save_weights_only=True,
                                                 save_best_only=True)

history = model.fit(x_train, y_train, batch_size=32, epochs=5, validation_data=(x_test, y_test), validation_freq=1,
                    callbacks=[cp_callback])
model.summary()

print(model.trainable_variables)
file = open('./weights.txt', 'w')
for v in model.trainable_variables:
    file.write(str(v.name) + '\n')
    file.write(str(v.shape) + '\n')
    file.write(str(v.numpy()) + '\n')
file.close()

###############################################    show   ###############################################

# 显示训练集和验证集的acc和loss曲线
acc = history.history['sparse_categorical_accuracy']
val_acc = history.history['val_sparse_categorical_accuracy']
loss = history.history['loss']
val_loss = history.history['val_loss']

plt.subplot(1, 2, 1) 画出第一列
plt.plot(acc, label='Training Accuracy')
plt.plot(val_acc, label='Validation Accuracy')
plt.title('Training and Validation Accuracy')
plt.legend()

plt.subplot(1, 2, 2) #画出第二列
plt.plot(loss, label='Training Loss')
plt.plot(val_loss, label='Validation Loss')
plt.title('Training and Validation Loss')
plt.legend()
plt.show()

应用程序

给图识物

给出一张图片，输出预测结果

1.复现模型 Sequential加载模型

2.加载参数 load_weights(model_save_path)

3.预测结果

我们需要对颜色取反，我们的训练图片是黑底白字

减少了背景噪声的影响

from PIL import Image
import numpy as np
import tensorflow as tf

type = ['T-shirt/top', 'Trouser', 'Pullover', 'Dress', 'Coat', 'Sandal', 'Shirt', 'Sneaker', 'Bag', 'Ankle boot']

model_save_path = './checkpoint/fashion.ckpt'
model = tf.keras.models.Sequential([
    tf.keras.layers.Flatten(),
    tf.keras.layers.Dense(128, activation='relu'),
    tf.keras.layers.Dense(10, activation='softmax')
])
                                        
model.load_weights(model_save_path)

preNum = int(input("input the number of test pictures:"))
for i in range(preNum):
    image_path = input("the path of test picture:")
    img = Image.open(image_path)
    img=img.resize((28,28),Image.ANTIALIAS)
    img_arr = np.array(img.convert('L'))
    img_arr = 255 - img_arr  #每个像素点= 255 - 各自点当前灰度值
    img_arr = img_arr/255.0
    x_predict = img_arr[tf.newaxis,...]

    result = model.predict(x_predict)
    pred=tf.argmax(result, axis=1)
    print('\n')
    print(type[int(pred)])