low_class_count_thresh=args.low_class_count_thresh,
data_splits={
'val_size': 0.2,
'test_size': 0.2
},
tfrecord_root_dir=args.tfrecord_dir,
data_db_path=args.data_db_path,
num_shards=10)
train_config = TrainConfig(
model_name=args.model_name,
model_dir=args.model_dir,
batch_size=args.batch_size,
frozen_layers=None, #(0,-4),
base_learning_rate=args.base_learning_rate,
buffer_size=500,
num_epochs=args.num_epochs,
preprocessing=True,
augment_images=True,
augmentations=['rotate', 'flip'],
regularization=regularizer,
seed=5,
verbose=True)
experiment_config = ExperimentConfig(dataset_config=dataset_config,
train_config=train_config)
mlflow.tensorflow.autolog()
# mlflow.log_params(experiment_config)
print(
data_splits={
'val_size': 0.2,
'test_size': 0.2
},
tfrecord_root_dir=args.tfrecord_dir,
# data_db_path=args.data_db_path,
num_shards=10)
train_config_source_domain = TrainConfig(
model_name=args.model_name,
model_dir=args.model_dir,
batch_size=args.batch_size,
frozen_layers=None,
base_learning_rate=args.base_learning_rate,
buffer_size=500,
num_epochs=args.num_epochs,
preprocessing=True,
x_col='x',
y_col='y',
augment_images=True,
augmentations=['rotate', 'flip'],
regularization=regularizer,
seed=5,
verbose=True)
train_config_target_domain = TrainConfig(
model_name=args.model_name,
model_dir=args.model_dir,
batch_size=args.batch_size,
frozen_layers=None,
base_learning_rate=args.base_learning_rate * 0.5,
buffer_size=500,
label_col='family',
target_size=target_size,
num_channels=args.num_channels,
low_class_count_thresh=3,
data_splits={
'val_size': 0.2,
'test_size': 0.2
},
num_shards=10,
input_format=dict)
train_config = TrainConfig(model_name=args.model_name,
batch_size=args.batch_size,
frozen_layers=(0, -4),
base_learning_rate=args.base_learning_rate,
buffer_size=500,
num_epochs=args.num_epochs,
preprocessing=True,
augment_images=True,
augmentations=['rotate', 'flip'],
seed=4) #3)
experiment_config = ExperimentConfig(dataset_config=dataset_config,
train_config=train_config)
trainer = TFDSTrainer(experiment_config=experiment_config)
##LOAD AND PLOT 1 BATCH OF IMAGES AND LABELS FROM FOSSIL DATASET
# experiment_dir = os.path.join(r'/media/data/jacob/Fossil_Project','experiments',trainer.config.model_name,trainer.config.dataset_name)
train_data = trainer.get_data_loader(
subset='train') #, skip_preprocessing=True)
label_col='family',
target_size=(224, 224),
channels=3,
low_class_count_thresh=3,
data_splits={
'val_size': 0.2,
'test_size': 0.2
},
tfrecord_root_dir=r'/media/data/jacob/Fossil_Project/tfrecord_data',
num_shards=10)
train_config = TrainConfig(model_name='vgg16',
batch_size=64,
frozen_layers=(0, -4),
base_learning_rate=1e-4,
buffer_size=1000,
num_epochs=100,
preprocessing='imagenet',
augment_images=True,
seed=3)
experiment_config = ExperimentConfig(dataset_config=dataset_config,
train_config=train_config)
trainer = BaseTrainer(experiment_config=experiment_config)
##LOAD AND PLOT 1 BATCH OF IMAGES AND LABELS FROM FOSSIL DATASET
experiment_dir = os.path.join(r'/media/data/jacob/Fossil_Project',
'experiments', trainer.config.model_name,
trainer.config.dataset_name)
def main(dataset_name='PNAS',
model_name='vgg16',
experiment_dir=r'/media/data/jacob/Fossil_Project/vgg16/PNAS',
gpu_ids=[0],
tfrecord_root_dir=r'/media/data/jacob/Fossil_Project/tfrecord_data',
batch_size=64,
target_size=(224, 224),
base_learning_rate=0.001,
num_epochs=100,
preprocessing='imagenet',
augment_images=False):
reset_eager_session()
# tf.reset_default_graph()
dataset_config = DatasetConfig(dataset_name=dataset_name,
label_col='family',
target_size=target_size,
channels=3,
low_class_count_thresh=3,
data_splits={
'val_size': 0.2,
'test_size': 0.2
},
tfrecord_root_dir=tfrecord_root_dir,
num_shards=10)
train_config = TrainConfig(model_name=model_name,
batch_size=batch_size,
frozen_layers=(0, -4),
base_learning_rate=base_learning_rate,
buffer_size=1000,
num_epochs=num_epochs,
preprocessing=preprocessing,
augment_images=augment_images,
seed=3)
experiment_config = ExperimentConfig(dataset_config=dataset_config,
train_config=train_config)
############################################
#TODO: Move config definitions outside main() for:
# 1. simplifying overall logic in main & segregating configuration to section marked by if __name__=='__main__'
# 2. Moving towards defining most or all run parameters in separate config files
############################################
def build_tunable_model(hp):
return build_model(name=hp.Choice('name',
values=[
'shallow', 'vgg16', 'xception',
'resnet_50_v2', 'resnet_101_v2'
]),
num_classes=10000,
frozen_layers=(0, -4),
input_shape=(224, 224, 3),
base_learning_rate=hp.Float('base_learning_rate',
min_value=1e-6,
max__value=0.01,
sampling='log'))
RandomSearch(build_tunable_model,
objective='val_accuracy',
max_trials=num_epochs,
seed=seed,
hyperparameters=None,
tune_new_entries=True,
allow_new_entries=True,
**kwargs)
trainer = BaseTrainer(experiment_config=experiment_config)
train_data = trainer.get_data_loader(subset='train')
val_data = trainer.get_data_loader(subset='val')
test_data = trainer.get_data_loader(subset='test')
# AUTOTUNE = tf.data.experimental.AUTOTUNE
# train_data = tfds.load("mnist", split='train').shuffle(1000).batch(batch_size).repeat().prefetch(AUTOTUNE)
model_params = trainer.get_model_params('train')
fit_params = trainer.get_fit_params()
callbacks = get_callbacks(weights_best=os.path.join(
experiment_dir, 'weights_best.h5'),
logs_dir=os.path.join(experiment_dir, 'logdir'),
restore_best_weights=False)
model = build_model(
**model_params
) #name='shallow', num_classes=10000, frozen_layers=(0,-4), input_shape=(224,224,3), base_learning_rate=0.0001)
history = model.fit(train_data,
steps_per_epoch=fit_params['steps_per_epoch'],
epochs=fit_params['epochs'],
validation_data=val_data,
validation_steps=fit_params['validation_steps'],
callbacks=callbacks)
return history