自制数据集代码如下:
- import tensorflow as tf
- from PIL import Image
- import numpy as np
- import os
- train_path = './mnist_image_label/mnist_train_jpg_60000/'
- train_txt = './mnist_image_label/mnist_train_jpg_60000.txt'
- x_train_savepath = './mnist_image_label/mnist_x_train.npy'
- y_train_savepath = './mnist_image_label/mnist_y_train.npy'
- test_path = './mnist_image_label/mnist_test_jpg_10000/'
- test_txt = './mnist_image_label/mnist_test_jpg_10000.txt'
- x_test_savepath = './mnist_image_label/mnist_x_test.npy'
- y_test_savepath = './mnist_image_label/mnist_y_test.npy'
- def generateds(path, txt):
- f = open(txt, 'r') # 以只读形式打开txt文件
- contents = f.readlines() # 读取文件中所有行
- f.close() # 关闭txt文件
- x, y_ = [], [] # 建立空列表
- for content in contents: # 逐行取出
- value = content.split() # 以空格分开,图片路径为value[0] , 标签为value[1] , 存入列表
- img_path = path + value[0] # 拼出图片路径和文件名
- img = Image.open(img_path) # 读入图片
- img = np.array(img.convert('L')) # 图片变为8位宽灰度值的np.array格式
- img = img / 255. # 数据归一化 (实现预处理)
- x.append(img) # 归一化后的数据,贴到列表x
- y_.append(value[1]) # 标签贴到列表y_
- print('loading : ' + content) # 打印状态提示
- x = np.array(x) # 变为np.array格式
- y_ = np.array(y_) # 变为np.array格式
- y_ = y_.astype(np.int64) # 变为64位整型
- return x, y_ # 返回输入特征x,返回标签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()
复制代码 第一次运行时,由于没有进行数据集的训练,以是会先实行generateds函数,然后生成.npy格式的数据集。第二次运行时,由于第一次运行已经生成了数据集,体系会检测到数据集,进而实行数据的训练。
数据加强:
我们可能会因为拍照角度,阴影的种种原因导致数据的效果并不是那么好,以是可以引入数据加强。


image_gen_train.fit(x_train) 这里的fit须要输入一个四位数据,以是须要对x.train进行reshape处理。处理后可以把6万张,28行28列的数据 新增加一个通道为1的数据。这里的通道1指的是灰度值,之后就按照batch打包送入model.fit实行训练过程。
代码:
- import tensorflow as tf
- from tensorflow.keras.preprocessing.image import ImageDataGenerator
- mnist = tf.keras.datasets.mnist
- (x_train, y_train), (x_test, y_test) = mnist.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,从(60000, 28, 28)reshape为(60000, 28, 28, 1)
- 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=False, # 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()
复制代码 断点续训很简单,就是可以生存训练的结果,使你在下次预测的时候不须要重新训练数据集,直接利用存放在本地的训练结果进行预测就行。

- import tensorflow as tf
- import os
- mnist = tf.keras.datasets.mnist
- (x_train, y_train), (x_test, y_test) = mnist.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/mnist.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()
复制代码
save_weights_only 只生存模型参数
save_best_only 只生存最优模型
fit中加入callback,返回给history
免责声明:如果侵犯了您的权益,请联系站长,我们会及时删除侵权内容,谢谢合作!更多信息从访问主页:qidao123.com:ToB企服之家,中国第一个企服评测及商务社交产业平台。 |