attr.model.compile(loss='binary_crossentropy',
optimizer=Adam(lr=0.00001),
metrics=['accuracy'])
plot_model(attr.model, to_file=attr.summ_basename + '-architecture.png')
# this is the augmentation configuration we will use for training
train_datagen = create_image_generator(True, True)
# this is the augmentation configuration we will use for testing:
# only rescaling
test_datagen = create_image_generator(True, False)
attr.train_generator = train_datagen.flow_from_directory(
attr.train_data_dir,
target_size=(attr.img_width, attr.img_height),
batch_size=attr.batch_size,
shuffle=True,
class_mode='binary')
attr.validation_generator = test_datagen.flow_from_directory(
attr.validation_data_dir,
target_size=(attr.img_width, attr.img_height),
batch_size=attr.batch_size,
shuffle=True,
class_mode='binary')
attr.test_generator = test_datagen.flow_from_directory(
attr.test_data_dir,
target_size=(attr.img_width, attr.img_height),
batch_size=1,
shuffle=False,
plot_model(attr.model, to_file=attr.summ_basename + '-architecture.png')
# compile model using accuracy as main metric, rmsprop (gradient descendent)
attr.model.compile(loss='binary_crossentropy',
optimizer=RMSprop(lr=0.000001),
metrics=['accuracy'])
# this is the augmentation configuration we will use for training
train_datagen = create_image_generator(False, True)
# this is the augmentation configuration we will use for testing:
# nothing is done.
test_datagen = create_image_generator(False, False)
attr.train_generator = multimodal_flow_from_directory_generator(attr.train_data_dir, attr.csv_path, train_datagen, attr.batch_size, attr.img_height, attr.img_width, 'binary', True)
attr.validation_generator = multimodal_flow_from_directory_generator(attr.validation_data_dir, attr.csv_path, test_datagen, attr.batch_size, attr.img_height, attr.img_width, 'binary', True)
attr.test_generator = multimodal_flow_from_directory_generator(attr.test_data_dir, attr.csv_path, test_datagen, 1, attr.img_height, attr.img_width, 'binary', False)
print("[INFO] Calculating samples and steps...")
attr.calculate_samples_len()
attr.calculate_steps()
attr.increment_seq()
# Persist execution attributes for session resume
save_execution_attributes(attr, attr.summ_basename + '-execution-attributes.properties')
time_callback = TimeCallback()
# compile the model (should be done *after* setting layers to non-trainable)
attr.model.compile(
optimizer=SGD(lr=0.0001, momentum=0.9),
loss='categorical_crossentropy',
metrics=['accuracy'],
)
attr.train_generator = MultimodalGenerator(npy_path=attr.numpy_path +
'/train-categorical.npy',
batch_size=attr.batch_size,
height=attr.img_height,
width=attr.img_width,
channels=3,
classes=2,
should_shuffle=True,
is_categorical=True,
is_debug=False,
width_shift=0.2,
height_shift=0.2,
rotation_angle=15,
shear_factor=10,
zoom_factor=0.2)
attr.validation_generator = MultimodalGenerator(npy_path=attr.numpy_path +
'/valid-categorical.npy',
batch_size=attr.batch_size,
height=attr.img_height,
width=attr.img_width,
channels=3,
classes=2,
attr.calculate_steps()
attr.increment_seq()
# Persist execution attributes for session resume
save_execution_attributes(attr, attr.summ_basename + '-execution-attributes.properties')
# this is the augmentation configuration we will use for training
train_datagen = create_image_generator(False, True)
# this is the augmentation configuration we will use for testing:
# nothing is done.
test_datagen = create_image_generator(False, False)
attr.train_generator = multimodal_flow_generator(images_train, attributes_train, labels_train, train_datagen, attr.batch_size)
attr.validation_generator = multimodal_flow_generator(images_valid, attributes_valid, labels_valid, test_datagen, attr.batch_size)
attr.test_generator = multimodal_flow_generator(images_test, attributes_test, labels_test, test_datagen, 1)
time_callback = TimeCallback()
callbacks = [time_callback, EarlyStopping(monitor='val_acc', patience=10, mode='max', restore_best_weights=True),
ModelCheckpoint(attr.curr_basename + "-ckweights.h5", mode='max', verbose=1, monitor='val_acc', save_best_only=True)]
# training time
history = attr.model.fit_generator(
attr.train_generator,
steps_per_epoch=attr.steps_train,
epochs=attr.epochs,
validation_data=attr.validation_generator,
attr.model.add(layers.Dense(1024, activation='relu'))
attr.model.add(layers.Dropout(0.3))
attr.model.add(layers.Dense(2, activation='softmax'))
# Show a summary of the model. Check the number of trainable parameters
attr.model.summary()
plot_model(attr.model, to_file=attr.summ_basename + '-architecture.png')
# prepare data augmentation configuration
train_datagen = create_image_generator(True, True)
test_datagen = create_image_generator(True, False)
attr.train_generator = train_datagen.flow_from_directory(
attr.train_data_dir,
target_size=(attr.img_height, attr.img_width),
batch_size=attr.batch_size,
class_mode='categorical',
shuffle=True)
# Create a generator for prediction
attr.validation_generator = test_datagen.flow_from_directory(
attr.validation_data_dir,
target_size=(attr.img_height, attr.img_width),
batch_size=attr.batch_size,
class_mode='categorical',
shuffle=True)
attr.test_generator = test_datagen.flow_from_directory(
attr.test_data_dir,
target_size=(attr.img_height, attr.img_width),
batch_size=1,