/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 vote353 views1 answer
Python saveAsTextFile
Python
1 vote323 views1 answer
How to add string to all values of column in pandas
Python
15 votes315 views1 answer
Importing file from another folder python
Python
0 vote303 views1 answer
Pandas selection row/columns
Python
0 vote339 views1 answer
Show all urls django extensions
Python Django
4 votes335 views1 answer
Get file creation date py
Python
0 vote321 views1 answer
Concatenação de Strings
Python
0 vote289 views1 answer
Displaying cv2.imshow on specific window position
Python
1 vote319 views1 answer
If a number times a number is true python
Python
9 votes355 views2 answers
Lambda condition python
Python