Added continuous labels

natanielruiz

2017-09-19 ec44ac453f794a5368e702315addfedcea3a4299

 code/test_preangles.py

@@ -33,6 +33,7 @@
          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('--dataset', dest='dataset', help='Dataset type.', default='AFLW2000', type=str)

    args = parser.parse_args()

@@ -48,7 +49,7 @@
    # 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, 0)
    # ResNet18
    # model = hopenet.Hopenet(torchvision.models.resnet.BasicBlock, [2, 2, 2, 2], 66)

@@ -59,15 +60,22 @@

    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)
@@ -79,10 +87,6 @@
    # Test the Model
    model.eval()  # Change model to 'eval' mode (BN uses moving mean/var).
    total = 0
    n_margins = 20
    yaw_correct = np.zeros(n_margins)
    pitch_correct = np.zeros(n_margins)
    roll_correct = np.zeros(n_margins)

    idx_tensor = [idx for idx in xrange(66)]
    idx_tensor = torch.FloatTensor(idx_tensor).cuda(gpu)
@@ -93,12 +97,12 @@

    l1loss = torch.nn.L1Loss(size_average=False)

    for i, (images, labels, name) in enumerate(test_loader):
    for i, (images, labels, cont_labels, name) in enumerate(test_loader):
        images = Variable(images).cuda(gpu)
        total += labels.size(0)
        label_yaw = labels[:,0].float()
        label_pitch = labels[:,1].float()
        label_roll = labels[:,2].float()
        total += cont_labels.size(0)
        label_yaw = cont_labels[:,0].float()
        label_pitch = cont_labels[:,1].float()
        label_roll = cont_labels[:,2].float()

        yaw, pitch, roll, angles = model(images)

@@ -117,33 +121,21 @@
        roll_predicted = torch.sum(roll_predicted * idx_tensor, 1).cpu()

        # Mean absolute error
        yaw_error += torch.sum(torch.abs(yaw_predicted - label_yaw) * 3)
        pitch_error += torch.sum(torch.abs(pitch_predicted - label_pitch) * 3)
        roll_error += torch.sum(torch.abs(roll_predicted - label_roll) * 3)

        # Binned Accuracy
        # for er in xrange(n_margins):
        #     yaw_bpred[er] += (label_yaw[0] in range(yaw_bpred[0,0] - er, yaw_bpred[0,0] + er + 1))
        #     pitch_bpred[er] += (label_pitch[0] in range(pitch_bpred[0,0] - er, pitch_bpred[0,0] + er + 1))
        #     roll_bpred[er] += (label_roll[0] in range(roll_bpred[0,0] - er, roll_bpred[0,0] + er + 1))

        # print label_yaw[0], yaw_bpred[0,0]
        yaw_error += torch.sum(torch.abs(yaw_predicted * 3 - 99 - label_yaw))
        pitch_error += torch.sum(torch.abs(pitch_predicted * 3 - 99 - label_pitch))
        roll_error += torch.sum(torch.abs(roll_predicted * 3 - 99 - label_roll))

        # Save images with pose cube.
        # TODO: fix for larger batch size
        if args.save_viz:
            name = name[0]
            cv2_img = cv2.imread(os.path.join(args.data_dir, name + '.jpg'))
            #print os.path.join('output/images', name + '.jpg')
            #print label_yaw[0] * 3 - 99, label_pitch[0] * 3 - 99, label_roll[0] * 3 - 99
            #print yaw_predicted * 3 - 99, pitch_predicted * 3 - 99, roll_predicted * 3 - 99
            if args.batch_size == 1:
                error_string = 'y %.2f, p %.2f, r %.2f' % (torch.sum(torch.abs(yaw_predicted - label_yaw) * 3), torch.sum(torch.abs(pitch_predicted - label_pitch) * 3), torch.sum(torch.abs(roll_predicted - label_roll) * 3))
                cv2_img = cv2.putText(cv2_img, error_string, (30, cv2_img.shape[0]- 30), fontFace=1, fontScale=1, color=(0,0,255), thickness=1)
            utils.plot_pose_cube(cv2_img, yaw_predicted[0] * 3 - 99, pitch_predicted[0] * 3 - 99, roll_predicted[0] * 3 - 99)
            cv2.imwrite(os.path.join('output/images', name + '.jpg'), cv2_img)

    print('Test error in degrees of the model on the ' + str(total) +
    ' test images. Yaw: %.4f, Pitch: %.4f, Roll: %.4f' % (yaw_error / total,
    pitch_error / total, roll_error / total))

    # Binned accuracy
    # for idx in xrange(len(yaw_correct)):
    #     print yaw_correct[idx] / total, pitch_correct[idx] / total, roll_correct[idx] / total