def main():
wandb.init(project="msc_thesis_hendrig")
ap = argparse.ArgumentParser()
ap.add_argument("data_path", help="Path to data root")
ap.add_argument("vocabulary_path", help="Path to vocabulary file")
ap.add_argument("config", help="Path to config file")
ap.add_argument("-m",
"--models",
help="Directory to store trained models (optional)")
ap.add_argument("-l",
"--log",
help="Path to store training log (optional)")
ap.add_argument("-e",
"--eval_only",
help="Whether to run just the final model evaluation")
args = ap.parse_args()
config = yaml.safe_load(open(args.config))
wandb.config.update(args)
wandb.config.update(config)
lowest_memory_gpu = gpu_selector.GPUSelector().pick_gpu_lowest_memory()
if lowest_memory_gpu is not None:
os.environ["CUDA_VISIBLE_DEVICES"] = str(lowest_memory_gpu)
print("Training with configuration:", config)
data = data_loader.DataLoader(args.data_path, config["data"],
vocabulary.Vocabulary(args.vocabulary_path))
if args.eval_only:
if args.models is None or args.log is None:
raise ValueError(
"Must provide a path to pre-trained models when running final evaluation"
)
test(data, config, args.models, args.log)
else:
train(data, config, args.models, args.log)
def main():
ap = argparse.ArgumentParser()
ap.add_argument("data_path", help="Path to data root")
ap.add_argument("vocabulary_path", help="Path to vocabulary file")
ap.add_argument("config", help="Path to config file")
ap.add_argument("-m",
"--models",
help="Directory to store trained models (optional)")
ap.add_argument("-l",
"--log",
help="Path to store training log (optional)")
ap.add_argument("-e",
"--eval_only",
help="Whether to run just the final model evaluation")
args = ap.parse_args()
config = yaml.safe_load(open(args.config))
print("Training with configuration:", config)
data = data_loader.DataLoader(args.data_path, config["data"],
vocabulary.Vocabulary(args.vocabulary_path))
if args.eval_only:
if args.models is None or args.log is None:
raise ValueError(
"Must provide a path to pre-trained models when running final evaluation"
)
test(data, config, args.models, args.log)
else:
train(data, config, args.models, args.log)
def __init__(self, action, debug_flag=False):
self.debug_flag = debug_flag
self.base_directory = os.path.dirname(__file__)
# Conditions for Loading Context
# Either GUI, TRAINING
print('Starting the Face Recognition Module Context Creation for ',
action)
print('Creating Configuration Module in Context')
# Load Configuration for UI and training
self.configuration = config.Configuration(self.base_directory,
debug_flag)
self.configuration.load_configuration(
os.path.join(os.path.dirname(__file__),
"configuration/application/app.config"))
print('Creating Tensorflow in Session')
# Load tensorflow session for training
# self.config = tf.ConfigProto()
# self.config.gpu_options.allow_growth = False
# self.sess = tf.InteractiveSession(config=self.config)
print('Creating Data Module in Context')
# Load Data Module which will do everything about data Reading, Writing, Separating data
self.data_loader = data_loader.DataLoader(self.base_directory,
self.configuration)
print('Creating Model Module in Context')
# Load Model module to store and restore model after training or testing time
self.model_loader = model.Model(self.base_directory,
self.configuration)
print('Creating Information Module in Context')
# Load Info Module to see the information about the module
self.info = info.Information()
print('Creating Pre Processing Module in Context')
# Load Preprocessing Module will do the preprocessing
self.preprocess = preprocess.Preprocessing(self.configuration)
self.resultwritter = rs.ResultWriter(self.base_directory,
self.configuration)
if action == "TRAIN":
print('Creating Data Augmentation Module in Context')
# Load DataAugumentation Module will do the data augumentation
self.augment = augment1.Augmentation(self.configuration)
print('Creating data separation Module in context')
self.data_separation = dataseparation.DataSeparation(
self.configuration)
print('Creating Model Preparation Module in Context')
self.model_preparation = nnmodel.NNModel(self.base_directory,
self.configuration)
print('Creating Batch Module in Context')
self.batch_prepare = pb.Prepare_Batch()
print('Creating Evaluation Module in Context')
# Load Detection Module
if action == "GUI":
print('Creating Face Detection Module in Context')
self.detect = self.face_detector()
print('Creating Face Recognition Module in Context')
self.recognize = self.face_recognizer(
self.configuration.recognizer_type)
print('Creating Post Processing Module in Context')
# Post Processing Module
self.postprocess = postprocess.Postprocessing(self.data_loader)