def __init__(self, args):
sub_dir = datetime.strftime(datetime.now(),
'%m%d-%H%M%S') # prepare saving path
self.save_dir = os.path.join(args.save_dir, sub_dir)
if not os.path.exists(self.save_dir):
os.makedirs(self.save_dir)
setlogger(os.path.join(self.save_dir, 'train.log')) # set logger
for k, v in args.__dict__.items(): # save args
logging.info("{}: {}".format(k, v))
self.args = args
parser.add_argument('--print_step',
type=int,
default=50,
help='the interval of log training information')
args = parser.parse_args()
return args
if __name__ == '__main__':
args = parse_args()
os.environ['CUDA_VISIBLE_DEVICES'] = args.cuda_device.strip()
# Prepare the saving path for the model
sub_dir = args.model_name + '_' + datetime.strftime(
datetime.now(), '%m%d-%H%M%S')
save_dir = os.path.join(args.checkpoint_dir, sub_dir)
if not os.path.exists(save_dir):
os.makedirs(save_dir)
# set the logger
setlogger(os.path.join(save_dir, 'train.log'))
# save the args
for k, v in args.__dict__.items():
logging.info("{}: {}".format(k, v))
trainer = train_utils(args, save_dir)
trainer.setup()
trainer.train()
if __name__ == '__main__':
start_tm = datetime.now()
args = parse_args()
os.environ['CUDA_VISIBLE_DEVICES'] = args.cuda_device.strip()
# Prepare the saving path for the test results
sub_dir = args.model_name+'_'+args.data_name + '_' + datetime.strftime(start_tm, '%m%d-%H%M%S')
save_dir = os.path.join(args.results_dir, sub_dir)
if not os.path.exists(save_dir):
os.makedirs(save_dir)
# Calculate the model file name
model_file_name = model_file_name_from_args(args)
# set the logger
setlogger(os.path.join(save_dir, 'testing.log'))
# save the args
for k, v in args.__dict__.items():
logging.info("{}: {}".format(k, v))
tester = test_utils(args, save_dir, model_file_name)
tester.setup()
results = tester.test()
end_tm = datetime.now()
duration = end_tm - start_tm
report(args=args, results=results, duration=duration, save_dir=save_dir)
help='batchsize of the training process')
parser.add_argument('--num_workers',
type=int,
default=0,
help='the number of training process')
args = parser.parse_args()
return args
if __name__ == '__main__':
args = parse_args()
os.environ['CUDA_VISIBLE_DEVICES'] = args.cuda_device.strip()
# get model name
sub_dir = args.checkpoint_dir.split("\\")[-1]
model_name = args.checkpoint_subdir.split("_")[0]
# get the checkpoint file of best model
path = args.checkpoint_dir
f_list = os.listdir(path)
files = [i for i in f_list if '.pth' in i]
files.sort(key=lambda x: float(x.split('-')[1]), reverse=True)
checkpoint_file = os.path.join(path, files[0])
# set the test logger
setlogger(os.path.join(path, 'test.log'))
evaluater = Evaluate_Utils(args, model_name, checkpoint_file)
evaluater.evaluate()
