/Python/Imagedatagenerator split train test

Imagedatagenerator split train test

How to do train test split in keras 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)

Source: stackoverflow.com

Similar codes

1 vote138 views2 answers
Django queryset unique values
Python
2 votes138 views1 answer
Clone website
Python
-1 vote138 views2 answers
How to set pandas dataframe as global
Python
0 vote145 views1 answer
How to output index of list python without braquets
Python
0 vote138 views1 answer
Python Script to check how many images are broken
Python
0 vote161 views1 answer
How to make print float value without scientific notation in dataframe in jupyter notebook
Python
0 vote133 views1 answer
Simplest flask memcached
Python
0 vote149 views1 answer
How to show webcam in opencv
Python
2 votes179 views1 answer
Run flask application in development mode stack overflow
Python
0 vote173 views1 answer
Django extend user model
Python Django