/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

2 votes114 views3 answers
Python beep
Python
0 vote128 views1 answer
Python String to array using list comprehension
Python
0 vote159 views1 answer
Unsupported media type django
Python Django
2 votes124 views1 answer
Save df to txt
Python
0 vote118 views1 answer
Murugan adimai child artist name
Python
0 vote95 views1 answer
Django model plural
Python
3 votes103 views2 answers
Python initialize a 2d array
Python
0 vote97 views1 answer
Unique mark boolean django model field
Python
1 vote96 views2 answers
Python mp4 to mp3
Python
16 votes95 views5 answers
Fibonacci series
Python