С помощью @nuric я смог ввести несколько изображений.Вот полный код для создания потока:
def get_flow_from_dataframe(generator, dataframe,
image_shape=(64, 64),
subset='training',
color_mode='grayscale', batch_size=64):
train_generator_1 = generator.flow_from_dataframe(dataframe, target_size=image_shape,
color_mode=color_mode,
x_col='image_1',
y_col='prediction',
class_mode='binary',
shuffle=True,
batch_size=batch_size,
seed=7,
subset=subset, drop_duplicates=False)
train_generator_2 = generator.flow_from_dataframe(dataframe, target_size=image_shape,
color_mode=color_mode,
x_col='image_2',
y_col='prediction',
class_mode='binary',
shuffle=True,
batch_size=batch_size,
seed=7,
subset=subset, drop_duplicates=False)
while True:
x_1 = train_generator_1.next()
x_2 = train_generator_2.next()
yield [x_1[0], x_2[0]], x_1[1]
Полный код fit_generator:
train_gen = get_flow_from_dataframe(generator, dataframe, image_shape=(64, 64),
color_mode='rgb',
batch_size=batch_size)
valid_gen = get_flow_from_dataframe(generator, dataframe, image_shape=(64, 64),
color_mode='rgb',
batch_size=batch_size,
subset='validation')
model.fit_generator(train_gen, epochs=50,
steps_per_epoch=step_size,
validation_data=valid_gen,
validation_steps=step_size,
callbacks=get_call_backs('../models/model_1.h5', monitor='val_acc'),
)
Также, как я вижу, потребление памяти огромно.