Fixing hopenet

natanielruiz

2017-09-14 dd62d6fa4a85f18a29de009a972f5599b19ec946

 code/test.py

@@ -27,12 +27,14 @@
          default='', type=str)
    parser.add_argument('--filename_list', dest='filename_list', help='Path to text file containing relative paths for every example.',
          default='', type=str)
    parser.add_argument('--snapshot', dest='snapshot', help='Name of model snapshot.',
    parser.add_argument('--snapshot', dest='snapshot', help='Path of model snapshot.',
          default='', type=str)
    parser.add_argument('--batch_size', dest='batch_size', help='Batch size.',
          default=1, type=int)
    parser.add_argument('--save_viz', dest='save_viz', help='Save images with pose cube.',
          default=False, type=bool)
    parser.add_argument('--iter_ref', dest='iter_ref', default=1, type=int)
    parser.add_argument('--dataset', dest='dataset', help='Dataset type.', default='AFLW2000', type=str)

    args = parser.parse_args()

@@ -43,12 +45,12 @@

    cudnn.enabled = True
    gpu = args.gpu_id
    snapshot_path = os.path.join('output/snapshots', args.snapshot + '.pkl')
    snapshot_path = args.snapshot

    # ResNet101 with 3 outputs.
    # model = hopenet.Hopenet(torchvision.models.resnet.Bottleneck, [3, 4, 23, 3], 66)
    # ResNet50
    model = hopenet.Hopenet(torchvision.models.resnet.Bottleneck, [3, 4, 6, 3], 66)
    model = hopenet.Hopenet(torchvision.models.resnet.Bottleneck, [3, 4, 6, 3], 66, args.iter_ref)
    # ResNet18
    # model = hopenet.Hopenet(torchvision.models.resnet.BasicBlock, [2, 2, 2, 2], 66)

@@ -59,15 +61,22 @@

    print 'Loading data.'

    # transformations = transforms.Compose([transforms.Scale(224),
    # transforms.RandomCrop(224), transforms.ToTensor()])

    transformations = transforms.Compose([transforms.Scale(224),
    transforms.RandomCrop(224), transforms.ToTensor(),
    transforms.CenterCrop(224), transforms.ToTensor(),
    transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])])

    pose_dataset = datasets.AFLW2000(args.data_dir, args.filename_list,
    if args.dataset == 'AFLW2000':
        pose_dataset = datasets.AFLW2000(args.data_dir, args.filename_list,
                                transformations)
    elif args.dataset == 'BIWI':
        pose_dataset = datasets.BIWI(args.data_dir, args.filename_list, transformations)
    elif args.dataset == 'AFLW':
        pose_dataset = datasets.AFLW(args.data_dir, args.filename_list, transformations)
    elif args.dataset == 'AFW':
        pose_dataset = datasets.AFW(args.data_dir, args.filename_list, transformations)
    else:
        print 'Error: not a valid dataset name'
        sys.exit()
    test_loader = torch.utils.data.DataLoader(dataset=pose_dataset,
                                               batch_size=args.batch_size,
                                               num_workers=2)
@@ -101,11 +110,12 @@
        label_roll = labels[:,2].float()

        pre_yaw, pre_pitch, pre_roll, angles = model(images)
        yaw = angles[:,0].cpu().data
        pitch = angles[:,1].cpu().data
        roll = angles[:,2].cpu().data
        yaw = angles[args.iter_ref][:,0].cpu().data
        pitch = angles[args.iter_ref][:,1].cpu().data
        roll = angles[args.iter_ref][:,2].cpu().data

        # Mean absolute error
        print yaw.numpy(), label_yaw.numpy()
        yaw_error += torch.sum(torch.abs(yaw - label_yaw) * 3)
        pitch_error += torch.sum(torch.abs(pitch - label_pitch) * 3)
        roll_error += torch.sum(torch.abs(roll - label_roll) * 3)