| | |
|---|
| | | 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() |
|---|
| | | |
|---|
| | |
|---|
| | | |
|---|
| | | 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) |
|---|
| | | |
|---|
| | |
|---|
| | | print 'Loading data.' |
|---|
| | | |
|---|
| | | 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) |
|---|
| | |
|---|
| | | # 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) |
|---|
| | | |
|---|
| | | yaw_error = .0 |
|---|
| | | pitch_error = .0 |
|---|
| | | roll_error = .0 |
|---|
| | | |
|---|
| | | 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 = model(images) |
|---|
| | | pre_yaw, pre_pitch, pre_roll, angles = model(images) |
|---|
| | | yaw = angles[0][:,0].cpu().data * 3 - 99 |
|---|
| | | pitch = angles[0][:,1].cpu().data * 3 - 99 |
|---|
| | | roll = angles[0][:,2].cpu().data * 3 - 99 |
|---|
| | | |
|---|
| | | # Binned predictions |
|---|
| | | _, yaw_bpred = torch.max(yaw.data, 1) |
|---|
| | | _, pitch_bpred = torch.max(pitch.data, 1) |
|---|
| | | _, roll_bpred = torch.max(roll.data, 1) |
|---|
| | | |
|---|
| | | # Continuous predictions |
|---|
| | | yaw_predicted = utils.softmax_temperature(yaw.data, 1) |
|---|
| | | pitch_predicted = utils.softmax_temperature(pitch.data, 1) |
|---|
| | | roll_predicted = utils.softmax_temperature(roll.data, 1) |
|---|
| | | |
|---|
| | | yaw_predicted = torch.sum(yaw_predicted * idx_tensor, 1).cpu() |
|---|
| | | pitch_predicted = torch.sum(pitch_predicted * idx_tensor, 1).cpu() |
|---|
| | | roll_predicted = torch.sum(roll_predicted * idx_tensor, 1).cpu() |
|---|
| | | for idx in xrange(1,args.iter_ref+1): |
|---|
| | | yaw += angles[idx][:,0].cpu().data |
|---|
| | | pitch += angles[idx][:,1].cpu().data |
|---|
| | | roll += angles[idx][:,2].cpu().data |
|---|
| | | |
|---|
| | | # 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 - label_yaw)) |
|---|
| | | pitch_error += torch.sum(torch.abs(pitch - label_pitch)) |
|---|
| | | roll_error += torch.sum(torch.abs(roll - 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 |
|---|
| | | utils.plot_pose_cube(cv2_img, yaw_predicted[0] * 3 - 99, pitch_predicted[0] * 3 - 99, roll_predicted[0] * 3 - 99) |
|---|
| | | if args.dataset == 'BIWI': |
|---|
| | | cv2_img = cv2.imread(os.path.join(args.data_dir, name + '_rgb.png')) |
|---|
| | | else: |
|---|
| | | cv2_img = cv2.imread(os.path.join(args.data_dir, name + '.jpg')) |
|---|
| | | |
|---|
| | | if args.batch_size == 1: |
|---|
| | | error_string = 'y %.4f, p %.4f, r %.4f' % (torch.sum(torch.abs(yaw - label_yaw) * 3), torch.sum(torch.abs(pitch - label_pitch) * 3), torch.sum(torch.abs(roll - label_roll) * 3)) |
|---|
| | | cv2_img = cv2.putText(cv2_img, error_string, (30, cv2_img.shape[0]- 30), fontFace=1, fontScale=2, color=(0,255,0), thickness=2) |
|---|
| | | utils.plot_pose_cube(cv2_img, yaw[0] * 3 - 99, pitch[0] * 3 - 99, roll[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) + |
|---|
