Added continuous labels

natanielruiz

2017-09-19 ec44ac453f794a5368e702315addfedcea3a4299

 code/test_preangles.py

@@ -97,12 +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)

@@ -121,15 +121,18 @@
        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)
        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'))
            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)