使用ImageDataGenerator时的Keras分割火车测试集 [英] Keras split train test set when using ImageDataGenerator

问题描述

我有一个目录，其中包含图像的子文件夹(根据标签).我想在Keras中使用ImageDataGenerator时将此数据分为训练集和测试集.尽管keras中的model.fit()具有用于指定拆分的参数validate_split，但我找不到model.fit_generator()的相同参数.怎么做?

I have a single directory which contains sub-folders (according to labels) of images. I want to split this data into train and test set while using ImageDataGenerator in Keras. Although model.fit() in keras has argument validation_split for specifying the split, I could not find the same for model.fit_generator(). How to do it ?

train_datagen = ImageDataGenerator(rescale=1./255,
    shear_range=0.2,
    zoom_range=0.2,
    horizontal_flip=True)

train_generator = train_datagen.flow_from_directory(
    train_data_dir,
    target_size=(img_width, img_height),
    batch_size=32,
    class_mode='binary')

model.fit_generator(
    train_generator,
    samples_per_epoch=nb_train_samples,
    nb_epoch=nb_epoch,
    validation_data=??,
    nb_val_samples=nb_validation_samples)

我没有用于验证数据的单独目录，需要将其与训练数据分开

I don't have separate directory for validation data, need to split it from the training data

推荐答案

Keras现在使用ImageDataGenerator从单个目录添加了Train/验证拆分:

Keras has now added Train / validation split from a single directory using ImageDataGenerator:

train_datagen = ImageDataGenerator(rescale=1./255,
    shear_range=0.2,
    zoom_range=0.2,
    horizontal_flip=True,
    validation_split=0.2) # set validation split

train_generator = train_datagen.flow_from_directory(
    train_data_dir,
    target_size=(img_height, img_width),
    batch_size=batch_size,
    class_mode='binary',
    subset='training') # set as training data

validation_generator = train_datagen.flow_from_directory(
    train_data_dir, # same directory as training data
    target_size=(img_height, img_width),
    batch_size=batch_size,
    class_mode='binary',
    subset='validation') # set as validation data

model.fit_generator(
    train_generator,
    steps_per_epoch = train_generator.samples // batch_size,
    validation_data = validation_generator, 
    validation_steps = validation_generator.samples // batch_size,
    epochs = nb_epochs)

https://keras.io/preprocessing/image/

这篇关于使用ImageDataGenerator时的Keras分割火车测试集的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！