/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 vote251 views3 answers
Groupby fillna
Python
0 vote249 views1 answer
Set environment variable flask app
Python
0 vote246 views1 answer
Micropython free space esp32 esp2866
Python
2 votes249 views1 answer
Pygityb
Python
2 votes250 views1 answer
Add colour to text in python
Python
6 votes233 views1 answer
How to simulate a key press in python
Python
1 vote252 views3 answers
Flatmap python
Python
0 vote268 views1 answer
How to check if given primary key exists in django model
Python
0 vote263 views1 answer
How to change defaul tpython version\
Python
0 vote237 views4 answers
Regression model build
Python