model = CRNN.build(width=config.WIDTH,
height=config.HEIGHT,
depth=1,
classes=config.NUM_CLASSES)
#print(model.summary())
model.compile(loss={'ctc': lambda y_true, y_pred: y_pred}, optimizer=adam)
else:
print("[info] loading {}..".format(args["model"]))
model = CRNN.build(width=config.WIDTH,
height=config.HEIGHT,
depth=1,
classes=config.NUM_CLASSES)
model.load_weights(args["model"])
model.compile(loss={'ctc': lambda y_true, y_pred: y_pred}, optimizer=adam)
callbacks = [
EpochCheckpoint(args["checkpoints"], every=5, startAt=args["start_epoch"])
]
model.fit(trainGen.generator(),
steps_per_epoch=trainGen.numImages // config.BATCH_SIZE,
validation_data=valGen.generator(),
validation_steps=valGen.numImages // config.BATCH_SIZE,
epochs=30,
max_queue_size=config.BATCH_SIZE * 2,
callbacks=callbacks,
verbose=1)
trainGen.close()
valGen.close()
def training(aug, means_path, train_hdf5_path, val_hdf5_path, fig_path, json_path, label_encoder_path, best_weight_path, checkpoint_path, cross_val=None):
# load RGB means
means = json.loads(open(means_path).read())
# initialize image preprocessors
sp, mp, pp, iap = SimplePreprocessor(227, 227), MeanPreprocessor(means['R'], means['G'], means['B']), PatchPreprocessor(227, 227), ImageToArrayPreprocessor()
# initialize training and validation image generator
train_gen = HDF5DatasetGenerator(train_hdf5_path, config.BATCH_SIZE, preprocessors=[pp, mp, iap], aug=aug, classes=config.NUM_CLASSES)
val_gen = HDF5DatasetGenerator(val_hdf5_path, config.BATCH_SIZE, preprocessors=[sp, mp, iap], aug=aug, classes=config.NUM_CLASSES)
metrics = ['accuracy']
if config.DATASET_TYPE == 'age':
le = pickle.loads(open(label_encoder_path, 'rb').read())
agh = AgeGenderHelper(config, deploy)
one_off_mappings = agh.build_oneoff_mappings(le)
one_off = OneOffAccuracy(one_off_mappings)
metrics.append(one_off.one_off_accuracy)
# construct callbacks
callbacks = [TrainingMonitor(fig_path, json_path=json_path, start_at=args['start_epoch']), EpochCheckpoint(checkpoint_path, every=5, start_at=args['start_epoch']), ModelCheckpointsAdvanced(best_weight_path, json_path=json_path, start_at=args['start_epoch'])] #, LearningRateScheduler(decay)
if cross_val is None:
print('[INFO] compiling model...')
else:
print(f'[INFO] compiling model for cross validation {cross_val}...')
if args['start_epoch'] == 0:
if not os.path.exists(checkpoint_path):
os.makedirs(checkpoint_path)
model = AgeGenderNet.build(227, 227, 3, config.NUM_CLASSES, reg=5e-4)
model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=metrics)
else:
model_path = os.path.sep.join([checkpoint_path, f"epoch_{args['start_epoch']}.hdf5"])
print(f"[INFO] loading {model_path}...")
if config.DATASET_TYPE == 'age':
model = load_model(model_path, custom_objects={'one_off_accuracy': one_off.one_off_accuracy})
elif config.DATASET_TYPE == 'gender':
model = load_model(model_path)
# update learning rate
print(f'[INFO] old learning rate: {K.get_value(model.optimizer.lr)}')
K.set_value(model.optimizer.lr, INIT_LR)
print(f'[INFO] new learning rate: {K.get_value(model.optimizer.lr)}')
# train the network
if cross_val is None:
print('[INFO] training the network...')
else:
print(f'[INFO] training the network for cross validation {cross_val}...')
model.fit_generator(train_gen.generator(), steps_per_epoch=train_gen.num_images//config.BATCH_SIZE, validation_data=val_gen.generator(), validation_steps=val_gen.num_images//config.BATCH_SIZE, epochs=MAX_EPOCH-args['start_epoch'], verbose=2, callbacks=callbacks)
# close dataset
train_gen.close()
val_gen.close()
# otherwise, load the checkpoint from disk
else:
print("[INFO] loading {}...".format(args["model"]))
model = load_model(args["model"])
# update the learning rate
print("[INFO] old learning rate: {}".format(K.get_value(
model.optimizer.lr)))
K.set_value(model.optimizer.lr, 1e-5)
print("[INFO] new learning rate: {}".format(K.get_value(
model.optimizer.lr)))
# construct the set of callbacks
callbacks = [
EpochCheckpoint(args["checkpoints"], every=5),
TrainingMonitor(config.FIG_PATH,
jsonPath=config.JSON_PATH,
startAt=args["start_epoch"])
]
# train the network
model.fit_generator(trainGen.generator(),
steps_per_epoch=trainGen.numImages // 64,
validation_data=valGen.generator(),
validation_steps=valGen.numImages // 64,
epochs=10,
max_queue_size=64 * 2,
callbacks=callbacks,
verbose=1)
model.compile(optimizer='adam',
loss='categorical_crossentropy',
metrics=['accuracy'])
# otherwise load the checkpoint from disk
else:
print(f"[INFO] loading {args['model']}")
model = load_model(args['model'])
# update learning rate
print(f'[INFO] old learning rate: {K.get_value(model.optimizer.lr)}')
K.set_value(model.optimizer.lr, 1e-5)
print(f'[INFO] new learning rate: {K.get_value(model.optimizer.lr)}')
# construct set of callbacks
callbacks = [
EpochCheckpoint(args['checkpoints'], every=5,
start_at=args['start_epoch']),
TrainingMonitor(config.FIG_PATH,
json_path=config.JSON_PATH,
start_at=args['start_epoch'])
]
# train the network
model.fit_generator(train_gen.generator(),
steps_per_epoch=train_gen.num_images // 64,
validation_data=val_gen.generator(),
validation_steps=val_gen.num_images // 64,
epochs=40,
verbose=2,
callbacks=callbacks)
# close the database
def main():
"""Train ResNet on Cifar10 dataset
"""
# construct the argument parse and parse the arguments
args = argparse.ArgumentParser()
args.add_argument("-c",
"--checkpoints",
required=True,
help="path to output checkpoint directory")
args.add_argument("-m",
"--model",
type=str,
help="path to *specific* model checkpoint to load")
args.add_argument("-s",
"--start-epoch",
type=int,
default=0,
help="epoch to restart training at")
args = vars(args.parse_args())
# load the training and testing data, converting the images from integers to floats
print("[INFO] loading CIFAR-10 data...")
((train_x, train_y), (test_x, test_y)) = cifar10.load_data()
train_x = train_x.astype("float")
test_x = test_x.astype("float")
# apply mean subtraction to the data
mean = np.mean(train_x, axis=0)
train_x -= mean
test_x -= mean
# convert the labels from integers to vectors
label_binarizer = LabelBinarizer()
train_y = label_binarizer.fit_transform(train_y)
test_y = label_binarizer.transform(test_y)
# construct the image generator for data augmentation
aug = ImageDataGenerator(width_shift_range=0.1,
height_shift_range=0.1,
horizontal_flip=True,
fill_mode="nearest")
# if there is no specific model checkpoint supplied, then initialize
# the network (ResNet-56) and compile the model
if args["model"] is None:
print("[INFO] compiling model...")
opt = SGD(lr=1e-1)
model = ResNet.build(32,
32,
3,
10, (9, 9, 9), (64, 64, 128, 256),
reg=0.0005)
model.compile(loss="categorical_crossentropy",
optimizer=opt,
metrics=["accuracy"])
# otherwise, load the checkpoint from disk
else:
print("[INFO] loading {}...".format(args["model"]))
model = load_model(args["model"])
# update the learning rate
print("[INFO] old learning rate: {}".format(
K.get_value(model.optimizer.lr)))
K.set_value(model.optimizer.lr, 1e-5)
print("[INFO] new learning rate: {}".format(
K.get_value(model.optimizer.lr)))
# construct the set of callbacks
callbacks = [
EpochCheckpoint(args["checkpoints"],
every=5,
start_at=args["start_epoch"]),
TrainingMonitor("output/resnet56_cifar10.png",
json_path="output/resnet56_cifar10.json",
start_at=args["start_epoch"])
]
# train the network
print("[INFO] training network...")
model.fit_generator(aug.flow(train_x, train_y, batch_size=128),
validation_data=(test_x, test_y),
steps_per_epoch=len(train_x) // 128,
epochs=100,
callbacks=callbacks,
verbose=1)
def main():
"""Train ResNet
"""
# construct the argument parse and parse the arguments
args = argparse.ArgumentParser()
args.add_argument("-c",
"--checkpoints",
required=True,
help="path to output checkpoint directory")
args.add_argument("-m",
"--model",
type=str,
help="path to *specific* model checkpoint to load")
args.add_argument("-s",
"--start-epoch",
type=int,
default=0,
help="epoch to restart training at")
args = vars(args.parse_args())
# construct the training image generator for data augmentation
aug = ImageDataGenerator(
rotation_range=18,
zoom_range=0.15,
width_shift_range=0.2,
height_shift_range=0.2,
shear_range=0.15,
horizontal_flip=True,
fill_mode="nearest",
)
# load the RGB means for the training set
means = json.loads(open(config.DATASET_MEAN).read())
# initialize the image preprocessors
simple_preprocessor = SimplePreprocessor(64, 64)
mean_preprocessor = MeanPreprocessor(means["R"], means["G"], means["B"])
image_to_array_preprocessor = ImageToArrayPreprocessor()
# initialize the training and validation dataset generators
train_gen = HDF5DatasetGenerator(
config.TRAIN_HDF5,
64,
augmentation=aug,
preprocessors=[
simple_preprocessor, mean_preprocessor, image_to_array_preprocessor
],
classes=config.NUM_CLASSES,
)
val_gen = HDF5DatasetGenerator(
config.VAL_HDF5,
64,
preprocessors=[
simple_preprocessor, mean_preprocessor, image_to_array_preprocessor
],
classes=config.NUM_CLASSES,
)
# if there is no specific model checkpoint supplied, then initialize
# the network and compile the model
if args["model"] is None:
print("[INFO] compiling model...")
model = ResNet.build(64,
64,
3,
config.NUM_CLASSES, (3, 4, 6),
(64, 128, 256, 512),
reg=0.0005,
dataset="tiny_imagenet")
opt = SGD(lr=1e-1, momentum=0.9)
model.compile(loss="categorical_crossentropy",
optimizer=opt,
metrics=["accuracy"])
# otherwise, load the checkpoint from disk
else:
print("[INFO] loading {}...".format(args["model"]))
model = load_model(args["model"])
# update the learning rate
print("[INFO] old learning rate: {}".format(
K.get_value(model.optimizer.lr)))
K.set_value(model.optimizer.lr, 1e-5)
print("[INFO] new learning rate: {}".format(
K.get_value(model.optimizer.lr)))
# construct the set of callbacks
callbacks = [
EpochCheckpoint(args["checkpoints"],
every=5,
start_at=args["start_epoch"]),
TrainingMonitor(config.FIG_PATH,
json_path=config.JSON_PATH,
start_at=args["start_epoch"]),
]
# train the network
model.fit_generator(
train_gen.generator(),
steps_per_epoch=train_gen.num_images // 64,
validation_data=val_gen.generator(),
validation_steps=val_gen.num_images // 64,
epochs=50,
max_queue_size=10,
callbacks=callbacks,
verbose=1,
)
# close the databases
train_gen.close()
val_gen.close()