batch_size=config.batch_size,
shuffle=False,
num_workers=8,
pin_memory=True)
setattr(dataloader['base'], 'total_item_len', len(base_set))
# ---------------------------- model ------------------------------------
if config.model_name == 'resnet18':
model = ResNet18(config.code_length, classes, config.class_mask)
elif config.model_name == 'alexnet':
model = AlexNet(config.code_length, classes, config.class_mask)
else:
print('undefined model ! ')
model = nn.DataParallel(model)
model.cuda()
# ---------------------------- loss and opt ------------------------------------
criterion = nn.CrossEntropyLoss()
criterion_hash = nn.MSELoss()
optimizer = optim.SGD(model.parameters(), lr=config.lr, momentum=0.9)
exp_lr_scheduler = lr_scheduler.StepLR(optimizer, step_size=30, gamma=0.1)
# ---------------------------- log and train ------------------------------------
log_file = open(
config.model_name + '_' + config.dataset + '_' +
str(config.code_length) + '.log', 'a')
log_file.write(str(config))
log_file.write('\n')
print('training start ...')
train_model(model, dataloader, criterion, criterion_hash, optimizer,
# net = net.cuda()
# for name, parameters in net.named_parameters():
# print(name, ':', parameters.size())
# exit()
print("weight init..")
weights_init(net)
criterion = nn.CrossEntropyLoss()
# weight_path = "/home/zengweijia/.jupyter/cnrpark/parking_lot_occupancy_detection/weights/carnet_60_0.001.pth"
# net.load_state_dict({k.replace('module.', ''): v for k, v in torch.load(weight_path, map_location="cpu").items()})
if args.path == '':
net = train(args.epochs,
args.train_img,
args.train_lab,
transforms=transforms,
net=net,
criterion=criterion)
# net=train(args.epochs, args.train_img, args.train_lab, transforms, net, criterion)
PATH = './weights/' + args.model + '_' + args.shuf_type + '_' + args.train_data + '.pth'
torch.save(net.state_dict(), PATH)
else:
PATH = args.path
if args.model == 'mAlexNet':
net = mAlexNet()
elif args.model == 'AlexNet':
net = AlexNet()
net.cuda()
net.load_state_dict(torch.load(PATH))
# accuracy = test(args.test_img, args.test_lab, transforms, net)
# print("\nThe accuracy of training on '{}' and testing on '{}' is {:.3f}.".format(args.train_lab.split('.')[0], args.test_lab.split('.')[0], accuracy))
if __name__ == "__main__":
if args.model == 'mAlexNet':
net = mAlexNet()
elif args.model == 'AlexNet':
net = AlexNet()
elif args.model == "carnet":
net = carNet()
elif args.model == 'stn_shuf':
net = stn_shufflenet()
elif args.model == 'stn_trans_shuf':
net = stn_trans_shufflenet()
elif args.model == 'shuf':
net = torchvision.models.shufflenet_v2_x1_0(pretrained=False,
num_classes=2)
elif args.model == 'trans_shuf':
net = trans_shufflenet()
torch.set_default_tensor_type('torch.FloatTensor')
print("test net:carNet..")
# print({k.replace('module.',''):v for k,v in torch.load(args.path,map_location="cpu").items()})
# exit()
net.load_state_dict({
k.replace('module.', ''): v
for k, v in torch.load(args.path, map_location="cpu").items()
})
if torch.cuda.is_available():
net.cuda(int(args.cuda_device))
# exit()
acc = test(args.test_img, args.test_lab, net)
print(args.test_lab, acc)