/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 vote173 views2 answers
Coin flip numpy
Python
2 votes170 views1 answer
Python numba
Python
0 vote224 views1 answer
Python if index not out of range
Python
12 votes278 views5 answers
Merge two dataframes based on column
Python
-1 vote168 views2 answers
Django cleanup
Python
56 votes173 views6 answers
Scikit learn train test split
Python
20 votes197 views2 answers
Python list of paths
Python
15 votes192 views3 answers
Python current year
Python
0 vote215 views1 answer
Py3 dict values
Python
3 votes157 views1 answer
Python list to tensor
Python