/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 vote182 views1 answer
Remove newline and space characters from start and end of string python
Python
0 vote183 views1 answer
Numpy find mean of array
Python
0 vote233 views1 answer
How to find pdf file in link beautifulsoup
Python
0 vote213 views1 answer
Assert raises with properties python
Python
3 votes272 views2 answers
Python replace space with underscore
Python
0 vote193 views1 answer
Python Remove Character from String using replace()
Python
0 vote255 views1 answer
Flask extends two base.html
Python Flask
1 vote233 views2 answers
Python get the elements between quotes in string
Python
0 vote184 views1 answer
Robust scaler
Python
1 vote205 views1 answer
Change plot size matplotlib
Python