def demo(args): model = torch.nn.DataParallel(RAFT(args)) model.load_state_dict(torch.load(args.model)) # , map_location=torch.device('cpu'))) model = model.module model.to(DEVICE) model.eval() with torch.no_grad(): images = glob.glob(os.path.join(args.path, '*.png')) + \ glob.glob(os.path.join(args.path, '*.jpg')) images = sorted(images) for imfile1, imfile2 in zip(images[:-1], images[1:]): image1 = load_image(imfile1) image2 = load_image(imfile2) padder = InputPadder(image1.shape) image1, image2 = padder.pad(image1, image2) flow_low, flow_up = model(image1, image2, iters=20, test_mode=True) flow = padder.unpad(flow_up[0]).permute(1, 2, 0).cpu().numpy() image1 = padder.unpad(image1[0]).permute(1, 2, 0).cpu().numpy() image2 = padder.unpad(image2[0]).permute(1, 2, 0).cpu().numpy() subname = imfile1.split("/") savename = os.path.join(args.result, subname[-1]) vizproject(savename, image1, image2, flow)
def validate_sintel(model, iters=32): """ Peform validation using the Sintel (train) split """ model.eval() results = {} for dstype in ['clean', 'final']: val_dataset = datasets.MpiSintel(split='training', dstype=dstype) epe_list = [] for val_id in range(len(val_dataset)): image1, image2, flow_gt, _ = val_dataset[val_id] image1 = image1[None].cuda() image2 = image2[None].cuda() padder = InputPadder(image1.shape) image1, image2 = padder.pad(image1, image2) flow_low, flow_pr = model(image1, image2, iters=iters, test_mode=True) flow = padder.unpad(flow_pr[0]).cpu() epe = torch.sum((flow - flow_gt)**2, dim=0).sqrt() epe_list.append(epe.view(-1).numpy()) epe_all = np.concatenate(epe_list) epe = np.mean(epe_all) px1 = np.mean(epe_all<1) px3 = np.mean(epe_all<3) px5 = np.mean(epe_all<5) print("Validation (%s) EPE: %f, 1px: %f, 3px: %f, 5px: %f" % (dstype, epe, px1, px3, px5)) results[dstype] = np.mean(epe_list) return results
def demo(args): model = torch.nn.DataParallel(RAFT(args)) model.load_state_dict(torch.load(args.model)) model = model.module model.to(DEVICE) model.eval() with torch.no_grad(): images = glob.glob(os.path.join(args.path, '*.png')) + \ glob.glob(os.path.join(args.path, '*.jpg')) images = natsorted(images) for imfile1, imfile2 in tqdm(zip(images[:-1], images[1:]), total=len(images)): try : image1 = load_image(imfile1) image2 = load_image(imfile2) padder = InputPadder(image1.shape) image1, image2 = padder.pad(image1, image2) flow_low, flow_up = model(image1, image2, iters=20, test_mode=True) # Flow Up is the upsampled version if args.save : path = Path(args.path_save) path.mkdir(parents=True, exist_ok=True) flow = padder.unpad(flow_up[0]).permute(1, 2, 0).cpu().numpy() frame_utils.writeFlow(imfile1.replace(args.path,args.path_save).replace('.png','.flo'), flow) else : viz(image1, flow_up) except Exception as e : print(f'Error with {imfile1} : {e}')
def create_sintel_submission(model, iters=32, warm_start=False, output_path='sintel_submission'): """ Create submission for the Sintel leaderboard """ model.eval() for dstype in ['clean', 'final']: test_dataset = datasets.MpiSintel(split='test', aug_params=None, dstype=dstype) flow_prev, sequence_prev = None, None for test_id in range(len(test_dataset)): image1, image2, (sequence, frame) = test_dataset[test_id] if sequence != sequence_prev: flow_prev = None padder = InputPadder(image1.shape) image1, image2 = padder.pad(image1[None].cuda(), image2[None].cuda()) flow_low, flow_pr = model(image1, image2, iters=iters, flow_init=flow_prev, test_mode=True) flow = padder.unpad(flow_pr[0]).permute(1, 2, 0).cpu().numpy() if warm_start: flow_prev = forward_interpolate(flow_low[0])[None].cuda() output_dir = os.path.join(output_path, dstype, sequence) output_file = os.path.join(output_dir, 'frame%04d.flo' % (frame+1)) if not os.path.exists(output_dir): os.makedirs(output_dir) frame_utils.writeFlow(output_file, flow) sequence_prev = sequence
def create_kitti_submission(model, iters=24, output_path='kitti_submission', write_png=False): """ Create submission for the Sintel leaderboard """ model.eval() test_dataset = datasets.KITTI(split='testing', aug_params=None) if not os.path.exists(output_path): os.makedirs(output_path) if write_png: out_path_png = output_path + '_png' if not os.path.exists(out_path_png): os.makedirs(out_path_png) for test_id in range(len(test_dataset)): image1, image2, (frame_id, ) = test_dataset[test_id] padder = InputPadder(image1.shape, mode='kitti') image1, image2 = padder.pad(image1[None].cuda(), image2[None].cuda()) _, flow_pr = model(image1, image2, iters=iters, test_mode=True) flow = padder.unpad(flow_pr[0]).permute(1, 2, 0).cpu().numpy() if write_png: output_filename_png = os.path.join(out_path_png, frame_id + '.png') cv2.imwrite(output_filename_png, flow_viz.flow_to_image(flow)) output_filename = os.path.join(output_path, frame_id) frame_utils.writeFlowKITTI(output_filename, flow)
def evaluate_davis(model, iters=32): """ Peform validation using the Sintel (train) split """ model.eval() val_dataset = datasets.DAVISDataset(split='train') for val_id in tqdm(range(len(val_dataset))): image1, image2, image_paths = val_dataset[val_id] image1 = image1[None].cuda() image2 = image2[None].cuda() padder = InputPadder(image1.shape) image1, image2 = padder.pad(image1, image2) _, flow_pr = model(image1, image2, iters=iters, test_mode=True) forward_flow = padder.unpad(flow_pr[0]).permute(1, 2, 0).cpu().numpy() _, flow_pr = model(image2, image1, iters=iters, test_mode=True) backward_flow = padder.unpad(flow_pr[0]).permute(1, 2, 0).cpu().numpy() # find out result storing paths fpath = image_paths[0] ind = fpath.rfind("/") name = fpath[ind + 1:fpath.rfind(".")] folder_path = fpath[:ind] flow_folder = folder_path.replace("JPEGImages", "Flows") flowviz_folder = folder_path.replace("JPEGImages", "FlowVizs") flow_path = os.path.join(flow_folder, f"forward_{name}.flo") flowviz_path = os.path.join(flowviz_folder, f"forward_{name}.png") if not os.path.exists(flow_folder): os.makedirs(flow_folder) if not os.path.exists(flowviz_folder): os.makedirs(flowviz_folder) frame_utils.writeFlow(flow_path, forward_flow) Image.fromarray(flow_viz.flow_to_image(forward_flow)).save( open(flowviz_path, "wb"), format="PNG") flow_path = os.path.join(flow_folder, f"backward_{name}.flo") flowviz_path = os.path.join(flowviz_folder, f"backward_{name}.png") frame_utils.writeFlow(flow_path, backward_flow) Image.fromarray(flow_viz.flow_to_image(backward_flow)).save( open(flowviz_path, "wb"), format="PNG")
def infer(model, seq_img_dir, suffix, iters=24, backward_flow=True): if backward_flow: flow_img_dir = os.path.join(seq_img_dir, '../flow_backward_img_{}'.format(suffix)) flow_np_dir = os.path.join(seq_img_dir, '../flow_backward_np_{}'.format(suffix)) # flow_np_save_path = os.path.join(seq_img_dir, '../flow_backward_{}.npy'.format(suffix)) else: flow_img_dir = os.path.join(seq_img_dir, '../flow_forward_img_{}'.format(suffix)) flow_np_dir = os.path.join(seq_img_dir, '../flow_forward_np_{}'.format(suffix)) # flow_np_save_path = os.path.join(seq_img_dir, '../flow_forward_{}.npy'.format(suffix)) if not os.path.exists(flow_img_dir): os.makedirs(flow_img_dir) if not os.path.exists(flow_np_dir): os.makedirs(flow_np_dir) model.eval() dataset = datasets.InferVideoDataset(seq_img_dir, backward_flow=backward_flow) # flow_list, flow_img_list = [], [] for val_id in tqdm.tqdm(range(len(dataset))): image1, image2, path1, path2 = dataset[val_id] image1 = image1[None].cuda() image2 = image2[None].cuda() padder = InputPadder(image1.shape, mode='sintel') image1, image2 = padder.pad(image1, image2) flow_low, flow_pr = model(image1, image2, iters=iters, test_mode=True) flow = padder.unpad(flow_pr[0]).cpu() # map flow to rgb image # pdb.set_trace() # flow = flow[0].permute(1,2,0).cpu().numpy() flow = flow.permute(1, 2, 0).cpu().numpy() flow_img = flow_viz.flow_to_image(flow) # flow_list.append(flow) # flow_img_list.append(flow_img) imageio.imwrite(os.path.join(flow_img_dir, path1.split('/')[-1]), flow_img) np.save( os.path.join(flow_np_dir, path1.split('/')[-1].split('.')[0] + '.npy'), flow)
def compute_flow_dir(model, dirpath, dirpathsave, resize=None) : images = glob.glob(os.path.join(dirpath, '*.png')) + \ glob.glob(os.path.join(dirpath, '*.jpg')) images = natsorted(images) for imfile1, imfile2 in tqdm(zip(images[:-1], images[1:]), total=len(images)): image1 = load_image(imfile1) image2 = load_image(imfile2) extension=imfile1.split('.')[-1] padder = InputPadder(image1.shape) image1, image2 = padder.pad(image1, image2) flow_low, flow_up = model(image1, image2, iters=20, test_mode=True) # Flow Up is the upsampled version if resize is not None : flow_up = nn.functional.interpolate(flow_up, size=resize, mode='bilinear', align_corners=False) path = Path(dirpathsave) path.mkdir(parents=True, exist_ok=True) flow = padder.unpad(flow_up[0]).permute(1, 2, 0).cpu().numpy() frame_utils.writeFlow(imfile1.replace(dirpath, dirpathsave).replace(extension,'flo'), flow)
def validate_kitti(model, args, iters=24): """ Peform validation using the KITTI-2015 (train) split """ model.eval() val_dataset = datasets.KITTI(split='training', root=args.dataset) from tqdm import tqdm out_list, epe_list = [], [] for _, val_id in enumerate(tqdm(list(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, mode='kitti') image1, image2 = padder.pad(image1, image2) flow_low, flow_pr = model(image1, image2, iters=iters, test_mode=True) flow = padder.unpad(flow_pr[0]).cpu() epe = torch.sum((flow - 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}
for imfile1, imfile2 in zip(images[100:101], images[101:102]):#zip(images[:-1], images[1:]): print(imfile1 + ' ' + imfile2) for scaling in range(8,9,1): image1, img_orig1 = load_image(imfile1,scaling=scaling) image2, img_orig2 = load_image(imfile2,scaling=scaling) padder = InputPadder(image1.shape) image1, image2 = padder.pad(image1, image2) flow_low, flow_up = model(image1, image2, iters=20, test_mode=True) B,C,W,H = img_orig1.shape Bf,Cf,Wf,Hf = flow_up.shape flow_up = F.interpolate(flow_up,(W,H),mode='bicubic') flow_up[:,0,:,:] = flow_up[:,0,:,:]*W/Wf flow_up[:,1,:,:] = flow_up[:,1,:,:]*H/Hf warpimg1 = warp(img_orig2,flow_up) #wrapimg2 = warp(image1,flow_up) image1 = padder.unpad(img_orig1[0]).permute(1, 2, 0).cpu() #image2 = padder.unpad(image2[0]).permute(1, 2, 0).cpu().numpy() warpimg1 = padder.unpad(warpimg1[0]).permute(1, 2, 0).cpu() i_loss = (image1 - warpimg1).abs() image1 = image1.numpy() warpimg1 = warpimg1.numpy() #wrapimg2 = padder.unpad(wrapimg2[0]).permute(1, 2, 0).cpu().numpy() # save result subname = imfile1.split("/") savename = os.path.join(args.result, str(scaling) + '_' + subname[-1]) diffimg = np.abs(image1 - warpimg1) print(str(scaling) + ': ' + str(np.mean(diffimg[200:4100, 200:7480,:]))) print(str(scaling) + ': ' + str(i_loss.mean()) img_flo = 0.5*(image1 + warpimg1) #flow = padder.unpad(flow_up[0]).permute(1, 2, 0).cpu().numpy()
def validate_kitti_colorjitter(model, args, iters=24): """ Peform validation using the KITTI-2015 (train) split """ from torchvision.transforms import ColorJitter from tqdm import tqdm model.eval() val_dataset = datasets.KITTI(split='training', root=args.dataset) jitterparam = 0.86 photo_aug = ColorJitter(brightness=jitterparam, contrast=jitterparam, saturation=jitterparam, hue=jitterparam / 3.14) def color_transform(img1, img2, photo_aug): torch.manual_seed(1234) np.random.seed(1234) img1 = img1.permute([1, 2, 0]).numpy().astype(np.uint8) img2 = img2.permute([1, 2, 0]).numpy().astype(np.uint8) image_stack = np.concatenate([img1, img2], axis=0) image_stack = np.array(photo_aug(Image.fromarray(image_stack)), dtype=np.uint8) img1, img2 = np.split(image_stack, 2, axis=0) img1 = torch.from_numpy(img1).permute([2, 0, 1]).float() img2 = torch.from_numpy(img2).permute([2, 0, 1]).float() return img1, img2 out_list, epe_list = [], [] for _, val_id in enumerate(tqdm(list(range(len(val_dataset))))): image1, image2, flow_gt, valid_gt = val_dataset[val_id] image1, image2 = color_transform(image1, image2, photo_aug) image1 = image1[None].cuda() image2 = image2[None].cuda() padder = InputPadder(image1.shape, mode='kitti') image1, image2 = padder.pad(image1, image2) flow_low, flow_pr = model(image1, image2, iters=iters, test_mode=True) flow = padder.unpad(flow_pr[0]).cpu() epe = torch.sum((flow - 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 print("Index: %d, valnum: %d" % (val_id, torch.sum(valid_gt).item())) 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("jitterparam:%f, Validation KITTI: %f, %f" % (jitterparam, epe, f1)) return {'kitti-epe': epe, 'kitti-f1': f1}
def validate_kitti_customized(model, iters=24): """ Peform validation using the KITTI-2015 (train) split """ model.eval() val_dataset = datasets.KITTI( split='training', root='/home/shengjie/Documents/Data/Kitti/kitti_stereo/stereo15') 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, mode='kitti') image1, image2 = padder.pad(image1, image2) flow_low, flow_pr = model(image1, image2, iters=iters, test_mode=True) flow = padder.unpad(flow_pr[0]).cpu() flowT = flow.cpu() flownp = flowT.numpy() image1_vls = padder.unpad(image1[0]).cpu() image2_vls = padder.unpad(image2[0]).cpu() image1_vlsnp = image1_vls.permute([1, 2, 0]).cpu().numpy().astype(np.uint8) image2_vlsnp = image2_vls.permute([1, 2, 0]).cpu().numpy().astype(np.uint8) flow_gt_vls_np = flow_gt.cpu().numpy() valid_gt_vls_np = valid_gt.cpu().numpy() _, h, w = flowT.shape xx, yy = np.meshgrid(range(w), range(h), indexing='xy') resampledxx = xx + flowT[0].cpu().numpy() resampledyy = yy + flowT[1].cpu().numpy() epipole_vote(xx, yy, flownp, image1_vlsnp, image2_vlsnp, flow_gt_vls_np, valid_gt_vls_np) resampledxx = ((resampledxx / (w - 1)) - 0.5) * 2 resampledyy = ((resampledyy / (h - 1)) - 0.5) * 2 resamplegrid = torch.stack( [torch.from_numpy(resampledxx), torch.from_numpy(resampledyy)], dim=2).unsqueeze(0).float() image1_recon_vls = torch.nn.functional.grid_sample( input=image2_vls.unsqueeze(0), grid=resamplegrid, mode='bilinear', padding_mode='reflection') # rndx = np.random.randint(0, w) # rndy = np.random.randint(0, h) rndx = 215 rndy = 278 tarx = rndx + flownp[0, int(rndy), int(rndx)] tary = rndy + flownp[1, int(rndy), int(rndx)] plt.figure() plt.imshow(image1.squeeze().permute([1, 2, 0 ]).cpu().numpy().astype(np.uint8)) plt.scatter(rndx, rndy, 1, 'r') plt.figure() plt.imshow(image2.squeeze().permute([1, 2, 0 ]).cpu().numpy().astype(np.uint8)) plt.scatter(tarx, tary, 1, 'r') plt.figure() plt.imshow(image1_recon_vls.squeeze().permute( [1, 2, 0]).cpu().numpy().astype(np.uint8)) import PIL.Image as Image from core.utils.flow_viz import flow_to_image flowimg = flow_to_image(flow.permute([1, 2, 0]).cpu().numpy()) Image.fromarray(flowimg).show() epe = torch.sum((flow - 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}