/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

12 votes185 views3 answers
Matplotlib legend
Python
0 vote151 views1 answer
Python for loop float increment
Python
1 vote135 views1 answer
How to scroll down to end of page in selenium python
Python
1 vote180 views3 answers
Check cuda version pytorch
Python
2 votes159 views1 answer
How to get text of a tag in selenium python
Python
0 vote163 views1 answer
Compare input with list python
Python
5 votes178 views2 answers
Use selenium without opening browser
Python
52 votes138 views6 answers
Time it python
Python
0 vote152 views1 answer
Python check variable is tuple
Python
1 vote143 views1 answer
Python to mac executable
Python