/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 vote148 views1 answer
Python look up how many rows in dataframe
Python
13 votes126 views3 answers
Permutation python
Python
0 vote146 views1 answer
Formate a phonenumber in phonenumber package with PhoneNumberFormat
Python
9 votes131 views2 answers
Remove all rows without a value pandas
Python
3 votes175 views1 answer
How to connect templates in django
Python Django
2 votes131 views4 answers
Histogram Plot Seaborn
Python
2 votes159 views3 answers
Scatter plot actual vs predicted python
Python
12 votes134 views4 answers
Python remove
Python
1 vote137 views1 answer
Import antigravity in python
Python
16 votes135 views6 answers
Turtle
Python