Function validate_kitti

evaluate_FlowFormer.py:113–149

Peform validation using the KITTI-2015 (train) split

(model)

@torch.no_grad()
def validate_kitti(model):
    """ Peform validation using the KITTI-2015 (train) split """
    model.eval()
    val_dataset = datasets.KITTI(split='training')

    out_list, epe_list = [], []
    for val_id in range(len(val_dataset)):
        image1, image2, flow_gt, valid_gt = val_dataset[val_id]
        image1 = image1[None].cuda()
        image2 = image2[None].cuda()

        padder = InputPadder(image1.shape)
        image1, image2 = padder.pad(image1, image2)

        flow_pre = model(image1, image2)

        flow_pre = padder.unpad(flow_pre[0]).cpu()[0]

        epe = torch.sum((flow_pre - flow_gt)**2, dim=0).sqrt()
        mag = torch.sum(flow_gt**2, dim=0).sqrt()

        epe = epe.view(-1)
        mag = mag.view(-1)
        val = valid_gt.view(-1) >= 0.5

        out = ((epe > 3.0) & ((epe/mag) > 0.05)).float()
        epe_list.append(epe[val].mean().item())
        out_list.append(out[val].cpu().numpy())

    epe_list = np.array(epe_list)
    out_list = np.concatenate(out_list)

    epe = np.mean(epe_list)
    f1 = 100 * np.mean(out_list)

    print("Validation KITTI: %f, %f" % (epe, f1))
    return {'kitti-epe': epe, 'kitti-f1': f1}


if __name__ == '__main__':