# Extract feature vectors and write out to user-specified file (if such file does not yet exist)
if os.path.isfile(features_file_path):
logging.info('Features file detected; skipping feature extraction')
else:
logging.info('Features file not detected; now extracting features...')
# Create data loader for the revelant part (train, val, or test) of the dataset
logging.info('Loading ' + ('small ' if arguments.small else '') +
arguments.dataset_type + ' dataset...')
train_data_loader = data_loader.fetch_dataloader(
[arguments.dataset_type], arguments.data_directory, parameters,
arguments.small)[arguments.dataset_type]
logging.info('...done.')
# Configure model
model = net.DenseNet169(parameters, return_features=True)
if parameters.cuda: model = model.cuda()
# Load weights from trained model
utils.load_checkpoint(
os.path.join(arguments.model_directory,
arguments.restore_file + '.pth.tar'), model)
extract_feature_vectors(model, train_data_loader, parameters,
features_file_path)
logging.info('...done.')
# Read feature vectors and labels and print information about them
analyze_feature_vector_clusters(features_file_path,
distance=utils.L2_distance)
analyze_feature_vector_clusters(features_file_path,
torch.manual_seed(230)
if parameters.cuda: torch.cuda.manual_seed(230)
# Configure logger
utils.set_logger(os.path.join(arguments.model_dir, 'train_embedding.log'))
# Create data loaders for training and validation data
logging.info('Loading train datasets...')
data_loaders = data_loader.fetch_dataloader(['train'], arguments.data_dir,
parameters, arguments.small,
False, True)
train_data_loader = data_loaders['train']
logging.info('...done.')
# Configure model and optimizer
model = net.DenseNet169(
parameters, True).cuda() if parameters.cuda else net.DenseNet169(
parameters, True)
optimizer = optim.Adam(model.parameters(),
lr=parameters.learning_rate,
weight_decay=parameters.L2_penalty)
# Configure schedule for decaying learning rate
scheduler = optim.lr_scheduler.ReduceLROnPlateau(
optimizer,
mode='min',
factor=parameters.learning_rate_decay_factor,
patience=parameters.learning_rate_decay_patience,
verbose=True) # Print message every time learning rate is reduced
if arguments.small:
num_train_data = 3924
else: