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 ostrain_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 ImageDataGeneratorfashion = 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 / 255.0x_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0～1rotation_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 pltnp.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 / 255.0model = 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 tftype = ['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/255.0x_predict = img_arr[tf.newaxis,...]result = model.predict(x_predict)pred=tf.argmax(result, axis=1)print('\n')print(type[int(pred)])
