/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

0 vote319 views1 answer
How to add the sum of multiple columns into another column in a dataframe
Python
0 vote331 views1 answer
Turtle python screen border
Python
0 vote321 views1 answer
Matplotlib clear plot
Python
0 vote368 views1 answer
Module 'networkx' has no attribute 'graphviz_layout'
Python
0 vote304 views1 answer
Runtime errors in python
Python
0 vote307 views1 answer
Convert math equation from string to int
Python
3 votes338 views1 answer
Drop duplicates pandas first column
Python
1 vote329 views1 answer
Chaine de caractere python
Python
0 vote300 views1 answer
Détruire une variable python
Python
23 votes462 views3 answers
Pip install django rest framework
Python Django