当我开始训练数据集时弹出输入用完数据错误

Posted 2023-03-29

【中文标题】当我开始训练数据集时弹出输入用完数据错误

【英文标题】：input ran out of data error popping up when i start training the dataset

【发布时间】：2020-09-07 01:22:00

【问题描述】：

我正在寻找运行我的训练集，但是当我尝试运行模型时它不断给出错误它会弹出这个错误“您的输入数据用完了；中断训练。确保您的数据集或生成器可以生成至少steps_per_epoch * epochs 批次（在本例中为 12000 批次）。构建数据集时可能需要使用 repeat() 函数。 在此处输入代码 # 卷积神经网络

# Importing the libraries
import tensorflow as tf
from keras.preprocessing.image import ImageDataGenerator
tf.__version__

# Part 1 - Data Preprocessing

# Generating images for the Training set
train_datagen = ImageDataGenerator(rescale = 1./255,
                                   shear_range = 0.2,
                                   zoom_range = 0.2,
                                   horizontal_flip = True)

# Generating images for the Test set
test_datagen = ImageDataGenerator(rescale = 1./255)

# Creating the Training set
training_set = train_datagen.flow_from_directory('dataset/train',
                                                 target_size = (64, 64),
                                                 batch_size = 32,
                                                 class_mode = 'binary')

# Creating the Test set
test_set = test_datagen.flow_from_directory('dataset/test',
                                            target_size = (64, 64),
                                            batch_size = 32,
                                            class_mode = 'binary')

# Part 2 - Building the CNN

# Initialising the CNN
cnn = tf.keras.models.Sequential()

# Step 1 - Convolution
cnn.add(tf.keras.layers.Conv2D(filters=32, kernel_size=3, padding="same", activation="relu", input_shape=[64, 64, 3]))

# Step 2 - Pooling
cnn.add(tf.keras.layers.MaxPool2D(pool_size=2, strides=2, padding='valid'))

# Adding a second convolutional layer
cnn.add(tf.keras.layers.Conv2D(filters=32, kernel_size=3, padding="same", activation="relu"))
cnn.add(tf.keras.layers.MaxPool2D(pool_size=2, strides=2, padding='valid'))

# Step 3 - Flattening
cnn.add(tf.keras.layers.Flatten())

# Step 4 - Full Connection
cnn.add(tf.keras.layers.Dense(units=128, activation='relu'))

# Step 5 - Output Layer
cnn.add(tf.keras.layers.Dense(units=1, activation='sigmoid'))

# Part 3 - Training the CNN

# Compiling the CNN
cnn.compile(optimizer = 'adam', loss = 'binary_crossentropy', metrics = ['accuracy'])

# Training the CNN on the Training set and evaluating it on the Test set
cnn.fit_generator(training_set,
                  steps_per_epoch = 4000,
                  epochs = 3,
                  validation_data = test_set,
                  validation_steps = 2000)

【参考方案1】：

steps_per_epochs 记录了每个时期的 批次 数量，因此实际上您需要验证您的数据集中至少有 steps_per_ecpoh * batch_size 图像（而不是您所写的 steps_per_ecpoh * epochs ）。对于茶和验证数据集都是如此。

一种常见的方法是设置steps_per_ecpoh=floor(len(dataset)/batch_size)。 ImageDataGenerator 类的默认 batch_size 为 32，您可以通过传递相关参数来更改它。