def model_eval(args):
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
print('Using device:', device)
# load the model
model_config_args = load_configuration(args.directory,
args.config_file_name, device)
model = DenseNet(model_config_args)
model_state_dict = torch.load('{:s}/{:s}'.format(
args.directory, args.state_dict_file_name),
map_location=device)
model.load_state_dict(model_state_dict)
# get performance
trainloader, validateloader, testloader, classes = load_data(args.bsize)
eval_result = {}
eval_result['parameter_size'] = get_parameter_count(model)
eval_result['train_accuracy'] = test_model(model, trainloader, device,
args.one_batch)
eval_result['validate_accuracy'] = test_model(model, validateloader,
device, args.one_batch)
eval_result['test_accuracy'] = test_model(model, testloader, device,
args.one_batch)
print(eval_result)
f = open('{:s}/{:s}'.format(args.directory, args.save_file_name), 'w')
f.write(json.dumps(eval_result))
f.close()
best_acc = 0
start_epoch = args.start_epoch
if not os.path.isdir(args.save_path):
mkdir_p(args.save_path)
title = "CIFAR-100"
if args.resume:
print("==> Resuming from checkpoint..")
assert os.path.isfile(args.resume), "Error: no checkpoint directory found !!!"
args.save_path = os.path.dirname(args.resume)
checkpoint = torch.load(args.resume)
best_acc = checkpoint["best_acc"]
start_epoch = checkpoint["epoch"]
model.load_state_dict(checkpoint["state_dict"])
optimizer.load_state_dict(checkpoint["optimizer"])
logger = Logger(os.path.join(args.save_path, "log.txt"), title=title, resume=True)
else:
logger = Logger(os.path.join(args.save_path, "log.txt"), title=title)
logger.set_names(
["Learning Rate", "Train Loss", "Valid Loss", "Train Acc.", "Valid Acc."]
)
if args.evaluate:
print("\nEvaluation only")
test_loss, test_acc = test(testLoader, model, criterion, start_epoch, device)
print(" Test Loss: %0.8f, Test Acc: %.3f" % (test_loss, test_acc))
exit()