def main():
# ====== set the run settings ======
args = parser.parse_args()
check_if_batch_size_bigger_than_num_classes(args.batch_size, args.number_of_classes)
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
folder_dir = set_project_folder_dir(args.open_new_folder, args.model_dir, use_model_folder_dir=True, mode='test_continues_movie')
print('The setting of the run are:\n{}\n' .format(args))
print('The training would take place on {}\n'.format(device))
print('The project directory is {}' .format(folder_dir))
save_setting_info(args, device, folder_dir)
test_videos_names, labels, label_decoder_dict = load_test_data(args.model_dir)
dataset = UCF101Dataset(args.sampled_data_dir, [test_videos_names, labels], mode='test')
sampler = UCF101DatasetSampler(dataset, args.batch_size)
dataloader = DataLoader(dataset, batch_size=args.batch_size, shuffle=False, sampler=sampler)
plot_label_distribution(dataloader, folder_dir, args.load_all_data_to_RAM, label_decoder_dict, mode='test')
print('Data prepared\nLoading model...')
num_class = len(label_decoder_dict) if args.number_of_classes is None else args.number_of_classes
model = ConvLstm(args.latent_dim, args.hidden_size, args.lstm_layers, args.bidirectional, num_class)
model = model.to(device)
# ====== setting optimizer and criterion parameters ======
criterion = nn.CrossEntropyLoss()
checkpoint = torch.load(os.path.join(args.model_dir, args.model_name))
model.load_state_dict(checkpoint['model_state_dict'])
# ====== inferance_mode ======
test_loss, test_acc, predicted_labels, images = test_model_continues_movie(model, dataloader, device, criterion,
folder_dir, label_decoder_dict)
plot_images_with_predicted_labels(images, label_decoder_dict, predicted_labels, folder_dir, 'test')
# ====== print the status to the console =======
print('test loss {:.8f}, test_acc {:.3f}' .format(test_loss, test_acc))
# ====== save the loss and accuracy in txt file ======
save_loss_info_into_a_file(0, test_loss, 0, test_acc, folder_dir, 'test')
def main():
# ====== set the run settings ======
os.environ["CUDA_DEVICE_ORDER"]="PCI_BUS_ID"
# os.environ["CUDA_VISIBLE_DEVICES"]="4,5,6,7"
os.environ["CUDA_VISIBLE_DEVICES"]="0,1"
args = parser.parse_args()
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
folder_dir = set_project_folder_dir(args.open_new_folder, args.model_dir, use_model_folder_dir=True, mode='test')
print('The setting of the run are:\n{}\n' .format(args))
print('The training would take place on {}\n'.format(device))
print('The project directory is {}' .format(folder_dir))
save_setting_info(args, device, folder_dir)
test_videos_names, labels, label_decoder_dict = load_test_data(args.model_dir)
dataset = CMCDataset(args.sampled_data_dir, [test_videos_names, labels], mode='test')
dataloader = DataLoader(dataset, batch_size=args.batch_size, shuffle=True)
# ======= if args.load_all_data_to_RAM True load dataset directly to the RAM (for faster computation) ======
if args.load_all_data_to_RAM:
dataloader = load_all_dataset_to_RAM_test(dataloader, args.batch_size)
plot_label_distribution(dataloader, folder_dir, args.load_all_data_to_RAM, label_decoder_dict, mode='test')
print('Data prepared\nLoading model...')
num_class = len(label_decoder_dict) if args.number_of_classes is None else args.number_of_classes
model = ConvLstm(args.latent_dim, args.model, args.hidden_size, args.lstm_layers, args.bidirectional, num_class)
model = model.to(device)
# ====== setting optimizer and criterion parameters ======
criterion = nn.CrossEntropyLoss()
checkpoint = torch.load(os.path.join(args.model_dir, args.model_name))
model.load_state_dict(checkpoint['model_state_dict'])
model = nn.DataParallel(model, device_ids=[0,1]).cuda()
# ====== inference_mode ======
test_loss, test_acc, predicted_labels, images, true_labels, index = test_model(model, dataloader, device, criterion,
mode='save_prediction_label_list')
print('test loss {:.8f}, test_acc {:.3f}'.format(test_loss, test_acc))
save_loss_info_into_a_file(0, test_loss, 0, test_acc, folder_dir, 'test')
# ====== analyze the test results ======
plot_images_with_predicted_labels(images, label_decoder_dict, predicted_labels[-1], folder_dir, 'test')
save_path_plots = os.path.join(folder_dir, 'Plots')
create_folder_dir_if_needed(save_path_plots)
for i in range(len(images)):
create_video_with_labels(folder_dir, '{}.avi'.format(dataset.images[index[i]].split('/')[1]),
images[i], None, [predicted_labels[-1][i]], label_decoder_dict, mode='single_movie')
predicted_labels, true_labels = torch.cat(predicted_labels), torch.cat(true_labels)
plot_confusion_matrix(predicted_labels, true_labels, label_decoder_dict, save_path_plots)
plot_acc_per_class(predicted_labels, true_labels, label_decoder_dict, save_path_plots)
def main():
# ====== set the run settings ======
args = parser.parse_args()
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
folder_dir = set_project_folder_dir(args.open_new_folder, args.model_dir, use_model_folder_dir=True, mode='test_youtube_movie')
print('The setting of the run are:\n{}\n' .format(args))
print('The training would take place on {}\n'.format(device))
print('The project directory is {}' .format(folder_dir))
save_setting_info(args, device, folder_dir)
label_decoder_dict = load_test_data(args.model_dir, mode='load_label_decoder_dict')
print('Loading model...')
num_class = len(label_decoder_dict) if args.number_of_classes is None else args.number_of_classes
model = ConvLstm(args.latent_dim, args.hidden_size, args.lstm_layers, args.bidirectional, num_class)
model = model.to(device)
checkpoint = torch.load(os.path.join(args.model_dir, args.model_name))
model.load_state_dict(checkpoint['model_state_dict'])
# ====== inferance_mode ======
if args.video_file_name is None and args.preprocessing_movie_mode != 'live':
test_videos_names = [file_name for file_name in os.listdir(args.sampled_data_dir) if '.avi' in file_name]
elif args.video_file_name is None:
test_videos_names = [file_name for file_name in os.listdir(args.row_data_dir)]
else:
test_videos_names = [args.video_file_name]
if args.preprocessing_movie_mode == 'preprocessed':
dataset = UCF101Dataset(args.sampled_data_dir, [test_videos_names], mode='test', dataset='youtube')
dataloader = DataLoader(dataset, batch_size=1, shuffle=False)
video_original_size_dict = load_and_extract_video_original_size(args.sampled_data_dir)
test_model_continues_movie_youtube(model, dataloader, device, folder_dir, label_decoder_dict, args.batch_size,
args.preprocessing_movie_mode, video_original_size=video_original_size_dict)
elif args.preprocessing_movie_mode == 'live':
movie_name_to_test = sample(test_videos_names, 1)
test_movie, video_original_size = main_procesing_data(args, folder_dir, sampled_video_file=movie_name_to_test,
processing_mode='live')
test_model_continues_movie_youtube(model, torch.stack(test_movie), device, folder_dir, label_decoder_dict,
args.batch_size, args.preprocessing_movie_mode,
video_original_size=video_original_size)
else:
print_error_preprocessing_movie_mode()
def main():
# ====== set the run settings ======
os.environ["CUDA_DEVICE_ORDER"] = "PCI_BUS_ID"
# os.environ["CUDA_VISIBLE_DEVICES"]="4,5,6,7"
os.environ["CUDA_VISIBLE_DEVICES"] = "0,1"
args = parser.parse_args()
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
folder_dir = set_project_folder_dir(args.open_new_folder, args.local_dir)
print('The setting of the run are:\n{}\n'.format(args))
print('The training would take place on {}\n'.format(device))
print('The project directory is {}'.format(folder_dir))
save_setting_info(args, device, folder_dir)
tensorboard_writer = SummaryWriter(folder_dir)
print('Initializing Datasets and Dataloaders...')
train_data_names, val_data_names, label_decoder_dict = split_data(
args.ucf_list_dir, args.seed, args.number_of_classes, args.split_size,
folder_dir)
dataset_order = ['train', 'val']
datasets = {
dataset_order[index]: UCF101Dataset(args.sampled_data_dir,
x,
mode=dataset_order[index])
for index, x in enumerate([train_data_names, val_data_names])
}
dataloaders = {
x: DataLoader(datasets[x], batch_size=args.batch_size, shuffle=True)
for x in ['train', 'val']
}
# ======= if args.load_all_data_to_RAM True load dataset directly to the RAM (for faster computation) ======
if args.load_all_data_to_RAM:
dataloaders = load_all_dataset_to_RAM(dataloaders, dataset_order,
args.batch_size)
plot_label_distribution(dataloaders, folder_dir, args.load_all_data_to_RAM,
label_decoder_dict)
print('Data prepared\nLoading model...')
num_class = len(
label_decoder_dict
) if args.number_of_classes is None else args.number_of_classes
model = ConvLstm(args.latent_dim, args.model, args.hidden_size,
args.lstm_layers, args.bidirectional, num_class)
model = model.to(device)
# ====== setting optimizer and criterion parameters ======
optimizer = torch.optim.Adam(model.parameters(), lr=args.lr)
criterion = nn.CrossEntropyLoss()
if args.load_checkpoint:
checkpoint = torch.load(args.checkpoint_path)
model.load_state_dict(checkpoint['model_state_dict'])
# model = nn.DataParallel(model, device_ids=[0,1,2,3]).cuda()
model = nn.DataParallel(model, device_ids=[0, 1]).cuda()
# ====== start training the model ======
for epoch in range(args.epochs):
start_epoch = time.time()
train_loss, train_acc = train_model(model, dataloaders['train'],
device, optimizer, criterion)
if (epoch % args.val_check_interval) == 0:
val_loss, val_acc, predicted_labels, images = test_model(
model, dataloaders['val'], device, criterion)
plot_images_with_predicted_labels(images, label_decoder_dict,
predicted_labels, folder_dir,
epoch)
end_epoch = time.time()
# ====== print the status to the console and write it in tensorboard =======
print(
'Epoch {} : Train loss {:.8f}, Train acc {:.3f}, Val loss {:.8f}, Val acc {:.3f}, epoch time {:.4f}'
.format(epoch, train_loss, train_acc, val_loss, val_acc,
end_epoch - start_epoch))
tensorboard_writer.add_scalars('train/val loss', {
'train_loss': train_loss,
'val loss': val_loss
}, epoch)
tensorboard_writer.add_scalars('train/val accuracy', {
'train_accuracy': train_acc,
'val accuracy': val_acc
}, epoch)
# ====== save the loss and accuracy in txt file ======
save_loss_info_into_a_file(train_loss, val_loss, train_acc,
val_acc, folder_dir, epoch)
if (epoch % args.checkpoint_interval) == 0:
hp_dict = {'model_state_dict': model.module.state_dict()}
save_model_dir = os.path.join(folder_dir,
'Saved_model_checkpoints')
create_folder_dir_if_needed(save_model_dir)
torch.save(
hp_dict,
os.path.join(save_model_dir, 'epoch_{}.pth.tar'.format(epoch)))