ocr识别训练数据

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

# 假设你已经有了一个包含OCR图像和对应标签的数据集
train_dir = 'path_to_train_data'
val_dir = 'path_to_val_data'

# 数据增强和预处理
train_datagen = ImageDataGenerator(
    rescale=1./255,
    rotation_range=10,
    width_shift_range=0.1,
    height_shift_range=0.1,
    shear_range=0.1,
    zoom_range=0.1,
    horizontal_flip=False,
    fill_mode='nearest'
)

val_datagen = ImageDataGenerator(rescale=1./255)

train_generator = train_datagen.flow_from_directory(
    train_dir,
    target_size=(128, 128),
    batch_size=32,
    class_mode='categorical'  # 或 'binary'，取决于你的标签类型
)

val_generator = val_datagen.flow_from_directory(
    val_dir,
    target_size=(128, 128),
    batch_size=32,
    class_mode='categorical'  # 或 'binary'
)

# 构建模型（这里以简单卷积神经网络为例）
model = tf.keras.models.Sequential([
    tf.keras.layers.Conv2D(32, (3, 3), activation='relu', input_shape=(128, 128, 3)),
    tf.keras.layers.MaxPooling2D((2, 2)),
    tf.keras.layers.Conv2D(64, (3, 3), activation='relu'),
    tf.keras.layers.MaxPooling2D((2, 2)),
    tf.keras.layers.Conv2D(128, (3, 3), activation='relu'),
    tf.keras.layers.Flatten(),
    tf.keras.layers.Dense(128, activation='relu'),
    tf.keras.layers.Dense(num_classes, activation='softmax')  # num_classes是你的类别数
])

# 编译和训练模型
model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])
model.fit(train_generator, epochs=10, validation_data=val_generator)