def main(args):
train_data = args.train_data
valid_data = args.valid_data
nb_train_samples = args.train_samples
nb_validation_samples = args.valid_samples
model_path = args.model_path
model_weights_path = args.model_weights_path
num_classes = args.num_classes
batch_size = args.batch_size
epochs = args.epochs
loss = args.loss
optimizer = args.optimizer
img_width, img_height = args.target_size
if not os.path.isdir(train_data):
raise EnvironmentError(f'--train-data {train_data} should exist')
if not os.path.isdir(valid_data):
raise EnvironmentError(f'--valid-data {valid_data} should exist')
if K.image_data_format() == 'channels_first':
input_shape = (3, img_width, img_height)
else:
input_shape = (img_width, img_height, 3)
model_params = {
'input_tensor': Input(shape=input_shape),
'classes': num_classes,
'weights': None,
}
print(
f'Start training mobile net for {epochs} epochs.',
f'{nb_train_samples} train samples, {nb_validation_samples} valid samples'
)
model = MobileNet(**model_params)
model.compile(loss=loss, optimizer=optimizer, metrics=['accuracy'])
train_datagen = ImageDataGenerator(rescale=1. / 255)
test_datagen = ImageDataGenerator(rescale=1. / 255)
train_generator = train_datagen.flow_from_directory(
train_data,
target_size=(img_width, img_height),
batch_size=batch_size,
class_mode='categorical',
)
validation_generator = test_datagen.flow_from_directory(
valid_data,
target_size=(img_width, img_height),
batch_size=batch_size,
class_mode='categorical',
)
model.fit_generator(train_generator,
steps_per_epoch=nb_train_samples // batch_size,
epochs=epochs,
validation_data=validation_generator,
validation_steps=nb_validation_samples // batch_size,
verbose=1)
model.save(model_path)
model.save_weights(model_weights_path)
print('Model saved.')
return 0
if earlyStopFlag:
callbacksList.append(earlyStop)
if reduceLRFlag:
callbacksList.append(reduce_lr)
if modelCheckpointFlag:
callbacksList.append(modelCheckpoint)
history = model.fit_generator(
trainGenerator,
steps_per_epoch=trainSamplesNumber // batchSize * foldAugment,
epochs=epochs,
verbose=1,
callbacks=callbacksList,
validation_data=validationGenerator,
class_weight=getClassWeights(trainGenerator.classes),
shuffle=True,
validation_steps=validateSamplesNumber // batchSize)
score = model.evaluate_generator(testGenerator, testSamplesNumber)
print('Test loss:', score[0])
print('Test accuracy:', score[1])
# serialize model to JSON
model_json = model.to_json()
with open(modelFile, "w") as json_file:
json_file.write(model_json)
# serialize weights to HDF5
model.save_weights(weightsFile)
print("Saved model to disk")
lb = LabelBinarizer()
lb.fit(np.asarray(data['primary_microconstituent']))
y = lb.transform(labels)
print('\nLabels Binarized, converting array')
input = np.asarray(processed_imgs)
X_train, X_test, y_train, y_test = train_test_split(
input, y, test_size=0.1, random_state=42)
model = MobileNet(weights=None, classes = 7)
model.summary()
model.compile(loss = 'categorical_crossentropy', optimizer = 'sgd', metrics = ['accuracy'])
time_callback = TimeHistory()
model.fit(X_train, y_train, epochs = 5, batch_size = 32, validation_data=(X_test, y_test), callbacks=[time_callback])
name = 'results/UHCS_MobileNet_Weights'
score = model.evaluate(X_test, y_test)
print('Test score:', score[0])
print('Test accuracy:', score[1])
model.save_weights(name+'.h5')
times = time_callback.times
file = open('MobileNet.txt', 'w')
file.write('Test score:'+ str(score[0])+'\n')
file.write('Test accuracy:'+ str(score[1])+'\n')
file.write(times)
file.close()
from keras.applications.mobilenet import MobileNet
import sys
sys.path.append('/lfs/1/thaonguyen/PuzzleSolving/')
from train_puzzle import PuzzleModel
model = PuzzleModel(input_shape=(76, 76, 27))
new_model = MobileNet(input_shape=None, include_top=False, weights=None)
model.load_weights('/lfs/1/thaonguyen/PuzzleSolving/WEIGHTS/weights-best.hdf5')
mbnet_layer = model.get_layer('mobilenet_1.00_76')
for layer in new_model.layers[1:]:
layer.set_weights(mbnet_layer.get_layer(layer.name).get_weights())
#print mbnet_layer.summary()
new_model.save_weights('mobilenet-weights-best.hdf5')