def extract_features_batch(model, config, source_path, target_path, voxel_size, device): folders = get_folder_list(source_path) assert len( folders) > 0, f"Could not find 3DMatch folders under {source_path}" logging.info(folders) list_file = os.path.join(target_path, "list.txt") f = open(list_file, "w") timer, tmeter = Timer(), AverageMeter() num_feat = 0 model.eval() for fo in folders: if 'evaluation' in fo: continue files = get_file_list(fo, ".ply") fo_base = os.path.basename(fo) f.write("%s %d\n" % (fo_base, len(files))) for i, fi in enumerate(files): # Extract features from a file pcd = o3d.io.read_point_cloud(fi) save_fn = "%s_%03d" % (fo_base, i) if i % 100 == 0: logging.info(f"{i} / {len(files)}: {save_fn}") timer.tic() xyz_down, feature = extract_features(model, xyz=np.array(pcd.points), rgb=None, normal=None, voxel_size=voxel_size, device=device, skip_check=True) t = timer.toc() if i > 0: tmeter.update(t) num_feat += len(xyz_down) np.savez_compressed(os.path.join(target_path, save_fn), points=np.array(pcd.points), xyz=xyz_down, feature=feature.detach().cpu().numpy()) if i % 20 == 0 and i > 0: # 最后一项算的是每个点的特征提取时间 logging.info( f'Average time: {tmeter.avg}, FPS: {num_feat / tmeter.sum}, time / feat: {tmeter.sum / num_feat}, ' ) f.close()
def calibrate_neighbors(dataset, config, collate_fn, keep_ratio=0.8, samples_threshold=2000): timer = Timer() last_display = timer.total_time # From config parameter, compute higher bound of neighbors number in a neighborhood hist_n = int(np.ceil(4 / 3 * np.pi * (config.deform_radius + 1)**3)) neighb_hists = np.zeros((config.num_layers, hist_n), dtype=np.int32) # Get histogram of neighborhood sizes i in 1 epoch max. for i in range(len(dataset)): timer.tic() batched_input = collate_fn([dataset[i]], config, neighborhood_limits=[hist_n] * 5) # update histogram counts = [ torch.sum(neighb_mat < neighb_mat.shape[0], dim=1).numpy() for neighb_mat in batched_input['neighbors'] ] hists = [np.bincount(c, minlength=hist_n)[:hist_n] for c in counts] neighb_hists += np.vstack(hists) timer.toc() if timer.total_time - last_display > 0.1: last_display = timer.total_time print(f"Calib Neighbors {i:08d}: timings {timer.total_time:4.2f}s") if np.min(np.sum(neighb_hists, axis=1)) > samples_threshold: break cumsum = np.cumsum(neighb_hists.T, axis=0) percentiles = np.sum(cumsum < (keep_ratio * cumsum[hist_n - 1, :]), axis=0) neighborhood_limits = percentiles print('\n') return neighborhood_limits
def ctpn(self, sess, net, image_name): """ :param sess: 会话 :param net: 创建的测试网络 :param image_name: 所要测试的单张图片的目录 :return: """ timer = Timer() timer.tic() # 读取图片 image = cv2.imread(image_name) shape = image.shape[:2] # 获取高,宽 # resize_im,返回缩放后的图片和相应的缩放比。缩放比定义为 修改后的图/原图 img, scale = TestClass.resize_im(image, scale=self._cfg.TEST.SCALE, max_scale=self._cfg.TEST.MAX_SCALE) # 将图片去均值化 im_orig = img.astype(np.float32, copy=True) im_orig -= self._cfg.TRAIN.PIXEL_MEANS # 将缩放和去均值化以后的图片,放入网络进行前向计算,获取分数和对应的文本片段,该片段为映射到最原始图片的坐标 scores, boxes = TestClass.test_ctpn(sess, net, im_orig, scale) # 此处调用了一个文本检测器 textdetector = TextDetector(self._cfg) """ 输入参数分别为: N×4矩阵,每行为一个已经映射回最初的图片的文字片段坐标 N维向量,对应的分数 两维向量,分别为最原始图片的高宽 返回: 一个N×9的矩阵,表示N个拼接以后的完整的文本框。每一行,前八个元素一次是左上,右上,左下,右下的坐标,最后一个元素是文本框的分数 """ boxes = textdetector.detect(boxes, scores, shape) self.draw_boxes(image, image_name, boxes, scale) timer.toc() print(('Detection took {:.3f}s for ' '{:d} object proposals').format(timer.total_time, boxes.shape[0]))
class CTPNTrainer(BaseTrain): def __init__(self, sess, model, data, logger): super(CTPNTrainer, self).__init__(sess, model, data, logger) self.imdb = data.load_imdb('voc_2007_trainval') self.roidb = data.get_training_roidb(self.imdb) self.pretrained_model = cfg.PRETRAINED_MODEL if cfg.PRETRAINED_MODEL else None # print('Computing bounding-box regression targets...') # if cfg.TRAIN.BBOX_REG: # self.bbox_means, self.bbox_stds = data.add_bbox_regression_targets(self.roidb) # print('done') self.timer = Timer() def get_train_op(self, loss): lr = tf.Variable(cfg.TRAIN.LEARNING_RATE, trainable=False) if cfg.TRAIN.SOLVER == 'Adam': opt = tf.train.AdamOptimizer(cfg.TRAIN.LEARNING_RATE) elif cfg.TRAIN.SOLVER == 'RMS': opt = tf.train.RMSPropOptimizer(cfg.TRAIN.LEARNING_RATE) else: momentum = cfg.TRAIN.MOMENTUM opt = tf.train.MomentumOptimizer(lr, momentum) if cfg.TRAIN.WITH_CLIP: tvars = tf.trainable_variables() grads, _ = tf.clip_by_global_norm(tf.gradients(loss, tvars), 10.0) train_op = opt.apply_gradients(list(zip(grads, tvars)), global_step=self.global_step) else: train_op = opt.minimize(loss, global_step=self.global_step) return train_op, lr def load_model(self, restore): restore_iter = 0 if self.pretrained_model is not None and not restore: try: print(('Loading pretrained model weights from {:s}').format( self.pretrained_model)) self.model.load_npz(self.pretrained_model, self.sess, True) except: raise 'Check your pretrained model {:s}'.format( self.pretrained_model) # resuming a trainer if restore: ckpt_path = self.model.load_ckpt(self.sess) stem = os.path.splitext(os.path.basename(ckpt_path))[0] restore_iter = int(stem.split('_')[-1]) self.sess.run(self.global_step.assign(restore_iter)) return restore_iter def train(self, max_iters, restore=False): """Network training loop.""" data_layer = DataGenerator(self.roidb, self.imdb.nrof_classes, self.data) total_loss, model_loss, rpn_cross_entropy, rpn_loss_box = self.model.build_loss( ohem=cfg.TRAIN.OHEM) summary_op, log_image, log_image_data, log_image_name = self.logger.init_summary( rpn_reg_loss=rpn_loss_box, rpn_cls_loss=rpn_cross_entropy, model_loss=model_loss, total_loss=total_loss) train_op, lr = self.get_train_op(total_loss) # intialize variables self.sess.run(tf.global_variables_initializer()) restore_iter = self.load_model(restore) fetch_list = [ total_loss, model_loss, rpn_cross_entropy, rpn_loss_box, summary_op, train_op ] print(restore_iter, max_iters) for _iter in range(restore_iter, max_iters, cfg.TRAIN.EPOCH_SIZE): losses = self.train_epoch(_iter, lr, data_layer, fetch_list) print('iter: %d / %d, total loss: %.4f, model loss: %.4f, rpn_loss_cls: %.4f, rpn_loss_box: %.4f, lr: %f' % \ (_iter+cfg.TRAIN.EPOCH_SIZE, max_iters, losses[0], losses[1], losses[2], losses[3], losses[5].eval())) self.logger.summarize(losses[4], self.global_step.eval()) self.save(_iter + cfg.TRAIN.EPOCH_SIZE) def train_epoch(self, tm_iter, lr, data_layer, fetch_list): loop = tqdm(range(cfg.TRAIN.EPOCH_SIZE)) for _iter in loop: tm_iter += _iter if tm_iter != 0 and tm_iter % cfg.TRAIN.STEPSIZE == 0: self.sess.run(tf.assign(lr, lr.eval() * cfg.TRAIN.GAMMA)) self.timer.tic() total_loss_val, model_loss_val, rpn_loss_cls_val, rpn_loss_box_val, summary_str, _ = \ self.train_step(data_layer,fetch_list) _diff_time = self.timer.toc(average=False) print('speed: {:.3f}s / iter'.format(_diff_time)) return total_loss_val, model_loss_val, rpn_loss_cls_val, rpn_loss_box_val, summary_str, lr def train_step(self, data_layer, fetch_list): blobs = data_layer.forward() feed_dict = { self.model.data: blobs['data'], self.model.im_info: blobs['im_info'], self.model.keep_prob: 0.5, self.model.gt_boxes: blobs['gt_boxes'], self.model.gt_ishard: blobs['gt_ishard'], self.model.dontcare_areas: blobs['dontcare_areas'] } return self.sess.run(fetches=fetch_list, feed_dict=feed_dict)
def _valid_epoch(self): # Change the network to evaluation mode self.model.eval() self.val_data_loader.dataset.reset_seed(0) num_data = 0 hit_ratio_meter, feat_match_ratio, loss_meter, rte_meter, rre_meter = AverageMeter( ), AverageMeter(), AverageMeter(), AverageMeter(), AverageMeter() data_timer, feat_timer, matching_timer = Timer(), Timer(), Timer() tot_num_data = len(self.val_data_loader.dataset) if self.val_max_iter > 0: tot_num_data = min(self.val_max_iter, tot_num_data) data_loader_iter = self.val_data_loader.__iter__() for batch_idx in range(tot_num_data): data_timer.tic() input_dict = data_loader_iter.next() data_timer.toc() # pairs consist of (xyz1 index, xyz0 index) feat_timer.tic() sinput0 = ME.SparseTensor( input_dict['sinput0_F'], coords=input_dict['sinput0_C']).to(self.device) F0 = self.model(sinput0).F sinput1 = ME.SparseTensor( input_dict['sinput1_F'], coords=input_dict['sinput1_C']).to(self.device) F1 = self.model(sinput1).F feat_timer.toc() matching_timer.tic() xyz0, xyz1, T_gt = input_dict['pcd0'], input_dict['pcd1'], input_dict['T_gt'] xyz0_corr, xyz1_corr = self.find_corr(xyz0, xyz1, F0, F1, subsample_size=5000) T_est = te.est_quad_linear_robust(xyz0_corr, xyz1_corr) loss = corr_dist(T_est, T_gt, xyz0, xyz1, weight=None) loss_meter.update(loss) rte = np.linalg.norm(T_est[:3, 3] - T_gt[:3, 3]) rte_meter.update(rte) rre = np.arccos((np.trace(T_est[:3, :3].t() @ T_gt[:3, :3]) - 1) / 2) if not np.isnan(rre): rre_meter.update(rre) hit_ratio = self.evaluate_hit_ratio( xyz0_corr, xyz1_corr, T_gt, thresh=self.config.hit_ratio_thresh) hit_ratio_meter.update(hit_ratio) feat_match_ratio.update(hit_ratio > 0.05) matching_timer.toc() num_data += 1 torch.cuda.empty_cache() if batch_idx % 100 == 0 and batch_idx > 0: logging.info(' '.join([ f"Validation iter {num_data} / {tot_num_data} : Data Loading Time: {data_timer.avg:.3f},", f"Feature Extraction Time: {feat_timer.avg:.3f}, Matching Time: {matching_timer.avg:.3f},", f"Loss: {loss_meter.avg:.3f}, RTE: {rte_meter.avg:.3f}, RRE: {rre_meter.avg:.3f},", f"Hit Ratio: {hit_ratio_meter.avg:.3f}, Feat Match Ratio: {feat_match_ratio.avg:.3f}" ])) data_timer.reset() logging.info(' '.join([ f"Final Loss: {loss_meter.avg:.3f}, RTE: {rte_meter.avg:.3f}, RRE: {rre_meter.avg:.3f},", f"Hit Ratio: {hit_ratio_meter.avg:.3f}, Feat Match Ratio: {feat_match_ratio.avg:.3f}" ])) return { "loss": loss_meter.avg, "rre": rre_meter.avg, "rte": rte_meter.avg, 'feat_match_ratio': feat_match_ratio.avg, 'hit_ratio': hit_ratio_meter.avg }
def _valid_epoch(self, data_loader_iter): # Change the network to evaluation mode self.model.eval() num_data = 0 hit_ratio_meter, reciprocity_ratio_meter = AverageMeter( ), AverageMeter() reciprocity_hit_ratio_meter = AverageMeter() data_timer, feat_timer = Timer(), Timer() tot_num_data = len(self.val_data_loader.dataset) if self.val_max_iter > 0: tot_num_data = min(self.val_max_iter, tot_num_data) for curr_iter in range(tot_num_data): data_timer.tic() input_dict = self.get_data(data_loader_iter) data_timer.toc() # pairs consist of (xyz1 index, xyz0 index) feat_timer.tic() with torch.no_grad(): F0 = self.model(input_dict['img0'].to(self.device)) F1 = self.model(input_dict['img1'].to(self.device)) feat_timer.toc() # Test self.num_pos_per_batch * self.batch_size features only. _, _, H0, W0 = F0.shape _, _, H1, W1 = F1.shape for batch_idx, pair in enumerate(input_dict['pairs']): N = len(pair) sel = np.random.choice(N, min(N, self.config.num_pos_per_batch), replace=False) curr_pair = pair[sel] w0, h0, w1, h1 = torch.floor(curr_pair.t() / self.out_tensor_stride).long() feats0 = F0[batch_idx, :, h0, w0] nn_inds1 = find_nn_gpu(feats0, F1[batch_idx, :].view(F1.shape[1], -1), nn_max_n=self.config.nn_max_n, transposed=True) # Convert the index to coordinate: BxCxHxW xs1 = nn_inds1 % W1 ys1 = nn_inds1 // W1 # Test reciprocity nn_inds0 = find_nn_gpu(F1[batch_idx, :, ys1, xs1], F0[batch_idx, :].view(F0.shape[1], -1), nn_max_n=self.config.nn_max_n, transposed=True) # Convert the index to coordinate: BxCxHxW xs0 = nn_inds0 % W0 ys0 = nn_inds0 // W0 dist_sq = (w1 - xs1)**2 + (h1 - ys1)**2 is_correct = dist_sq < (self.config.ucn_inlier_threshold_pixel / self.out_tensor_stride)**2 hit_ratio_meter.update(is_correct.sum().item() / len(is_correct)) # Recipocity test result dist_sq_nn = (w0 - xs0)**2 + (h0 - ys0)**2 mask = dist_sq_nn < (self.config.ucn_inlier_threshold_pixel / self.out_tensor_stride)**2 reciprocity_ratio_meter.update(mask.sum().item() / float(len(mask))) reciprocity_hit_ratio_meter.update( is_correct[mask].sum().item() / (mask.sum().item() + eps)) torch.cuda.empty_cache() # visualize_image_correspondence(input_dict['img0'][batch_idx, 0].numpy() + 0.5, # input_dict['img1'][batch_idx, 0].numpy() + 0.5, # F0[batch_idx], F1[batch_idx], curr_iter, # self.config) num_data += 1 if num_data % 100 == 0: logging.info(', '.join([ f"Validation iter {num_data} / {tot_num_data} : Data Loading Time: {data_timer.avg:.3f}", f"Feature Extraction Time: {feat_timer.avg:.3f}, Hit Ratio: {hit_ratio_meter.avg}", f"Reciprocity Ratio: {reciprocity_ratio_meter.avg}, Reci Filtered Hit Ratio: {reciprocity_hit_ratio_meter.avg}" ])) data_timer.reset() logging.info(', '.join([ f"Validation : Data Loading Time: {data_timer.avg:.3f}", f"Feature Extraction Time: {feat_timer.avg:.3f}, Hit Ratio: {hit_ratio_meter.avg}", f"Reciprocity Ratio: {reciprocity_ratio_meter.avg}, Reci Filtered Hit Ratio: {reciprocity_hit_ratio_meter.avg}" ])) return { 'hit_ratio': hit_ratio_meter.avg, 'reciprocity_ratio': reciprocity_ratio_meter.avg, 'reciprocity_hit_ratio': reciprocity_hit_ratio_meter.avg, }
def main(config): test_loader = make_data_loader( config, config.test_phase, 1, num_threads=config.test_num_workers, shuffle=True) num_feats = 1 device = torch.device('cuda' if torch.cuda.is_available() else 'cpu') Model = load_model(config.model) model = Model( num_feats, config.model_n_out, bn_momentum=config.bn_momentum, conv1_kernel_size=config.conv1_kernel_size, normalize_feature=config.normalize_feature) checkpoint = torch.load(config.save_dir + '/checkpoint.pth') model.load_state_dict(checkpoint['state_dict']) model = model.to(device) model.eval() success_meter, rte_meter, rre_meter = AverageMeter(), AverageMeter(), AverageMeter() data_timer, feat_timer, reg_timer = Timer(), Timer(), Timer() test_iter = test_loader.__iter__() N = len(test_iter) n_gpu_failures = 0 # downsample_voxel_size = 2 * config.voxel_size for i in range(len(test_iter)): data_timer.tic() try: data_dict = test_iter.next() except ValueError: n_gpu_failures += 1 logging.info(f"# Erroneous GPU Pair {n_gpu_failures}") continue data_timer.toc() xyz0, xyz1 = data_dict['pcd0'], data_dict['pcd1'] T_gth = data_dict['T_gt'] xyz0np, xyz1np = xyz0.numpy(), xyz1.numpy() pcd0 = make_open3d_point_cloud(xyz0np) pcd1 = make_open3d_point_cloud(xyz1np) with torch.no_grad(): feat_timer.tic() sinput0 = ME.SparseTensor( data_dict['sinput0_F'].to(device), coordinates=data_dict['sinput0_C'].to(device)) F0 = model(sinput0).F.detach() sinput1 = ME.SparseTensor( data_dict['sinput1_F'].to(device), coordinates=data_dict['sinput1_C'].to(device)) F1 = model(sinput1).F.detach() feat_timer.toc() feat0 = make_open3d_feature(F0, 32, F0.shape[0]) feat1 = make_open3d_feature(F1, 32, F1.shape[0]) reg_timer.tic() distance_threshold = config.voxel_size * 1.0 ransac_result = o3d.registration.registration_ransac_based_on_feature_matching( pcd0, pcd1, feat0, feat1, distance_threshold, o3d.registration.TransformationEstimationPointToPoint(False), 4, [ o3d.registration.CorrespondenceCheckerBasedOnEdgeLength(0.9), o3d.registration.CorrespondenceCheckerBasedOnDistance( distance_threshold) ], o3d.registration.RANSACConvergenceCriteria(4000000, 10000)) T_ransac = torch.from_numpy( ransac_result.transformation.astype(np.float32)) reg_timer.toc() # Translation error rte = np.linalg.norm(T_ransac[:3, 3] - T_gth[:3, 3]) rre = np.arccos((np.trace(T_ransac[:3, :3].t() @ T_gth[:3, :3]) - 1) / 2) # Check if the ransac was successful. successful if rte < 2m and rre < 5◦ # http://openaccess.thecvf.com/content_ECCV_2018/papers/Zi_Jian_Yew_3DFeat-Net_Weakly_Supervised_ECCV_2018_paper.pdf if rte < 2: rte_meter.update(rte) if not np.isnan(rre) and rre < np.pi / 180 * 5: rre_meter.update(rre) if rte < 2 and not np.isnan(rre) and rre < np.pi / 180 * 5: success_meter.update(1) else: success_meter.update(0) logging.info(f"Failed with RTE: {rte}, RRE: {rre}") if i % 10 == 0: logging.info( f"{i} / {N}: Data time: {data_timer.avg}, Feat time: {feat_timer.avg}," + f" Reg time: {reg_timer.avg}, RTE: {rte_meter.avg}," + f" RRE: {rre_meter.avg}, Success: {success_meter.sum} / {success_meter.count}" + f" ({success_meter.avg * 100} %)") data_timer.reset() feat_timer.reset() reg_timer.reset() logging.info( f"RTE: {rte_meter.avg}, var: {rte_meter.var}," + f" RRE: {rre_meter.avg}, var: {rre_meter.var}, Success: {success_meter.sum} " + f"/ {success_meter.count} ({success_meter.avg * 100} %)")
def _valid_epoch(self): # Change the network to evaluation mode self.model.eval() self.val_data_loader.dataset.reset_seed(0) num_data = 0 hit_ratio_meter, feat_match_ratio, loss_meter, rte_meter, rre_meter = AverageMeter( ), AverageMeter(), AverageMeter(), AverageMeter(), AverageMeter() data_timer, feat_timer, matching_timer = Timer(), Timer(), Timer() tot_num_data = len(self.val_data_loader.dataset) if self.val_max_iter > 0: tot_num_data = min(self.val_max_iter, tot_num_data) data_loader_iter = self.val_data_loader.__iter__() for batch_idx in range(tot_num_data): data_timer.tic() input_dict = data_loader_iter.next() data_timer.toc() # pairs consist of (xyz1 index, xyz0 index) feat_timer.tic() coords = input_dict['sinput0_C'].to(self.device) sinput0 = ME.SparseTensor( input_dict['sinput0_F'].to(self.device), coordinates=input_dict['sinput0_C'].to(self.device).type(torch.float)) F0 = self.model(sinput0).F sinput1 = ME.SparseTensor( input_dict['sinput1_F'].to(self.device), coordinates=input_dict['sinput1_C'].to(self.device).type(torch.float)) F1 = self.model(sinput1).F feat_timer.toc() matching_timer.tic() xyz0, xyz1, T_gt = input_dict['pcd0'], input_dict['pcd1'], input_dict['T_gt'] xyz0_corr, xyz1_corr = self.find_corr(xyz0, xyz1, F0, F1, subsample_size=5000) if False: from sklearn.decomposition import PCA import open3d as o3d pc0 = o3d.geometry.PointCloud() pc0.points = o3d.utility.Vector3dVector(xyz0.numpy()) pca = PCA(n_components=3) colors = pca.fit_transform(torch.cat((F0, F1), axis=0).cpu().numpy()) colors -= colors.min() colors /= colors.max() pc0.colors = o3d.utility.Vector3dVector(colors[0:F0.shape[0]]) o3d.io.write_point_cloud("pc0.ply", pc0) pc0.transform(T_gt.numpy()) o3d.io.write_point_cloud("pc0_trans.ply", pc0) pc1 = o3d.geometry.PointCloud() pc1.points = o3d.utility.Vector3dVector(xyz1.numpy()) pc1.colors = o3d.utility.Vector3dVector(colors[F0.shape[0]:]) o3d.io.write_point_cloud("pc1.ply", pc1) ind_0 = input_dict['correspondences'][:, 0].type(torch.long) ind_1 = input_dict['correspondences'][:, 1].type(torch.long) pc1.points = o3d.utility.Vector3dVector(xyz1[ind_1].numpy()) pc1.colors = o3d.utility.Vector3dVector( colors[F0.shape[0]:][ind_1]) o3d.io.write_point_cloud("pc1_corr.ply", pc1) pc0.points = o3d.utility.Vector3dVector(xyz0[ind_0].numpy()) pc0.colors = o3d.utility.Vector3dVector(colors[:F0.shape[0]][ind_0]) pc0.transform(T_gt.numpy()) o3d.io.write_point_cloud("pc0_trans_corr.ply", pc0) import pdb pdb.set_trace() #pc0.points = o3d.utility.Vector3dVector(xyz0_corr.numpy()) # pc0.transform(T_gt.numpy()) #o3d.io.write_point_cloud("xyz0_corr_trans.ply" , pc0) # #pc0.points = o3d.utility.Vector3dVector(xyz1_corr.numpy()) #o3d.io.write_point_cloud("xyz1_corr_trans.ply" , pc0) T_est = te.est_quad_linear_robust(xyz0_corr, xyz1_corr) loss = corr_dist(T_est, T_gt, xyz0, xyz1, weight=None) loss_meter.update(loss) rte = np.linalg.norm(T_est[:3, 3] - T_gt[:3, 3]) rte_meter.update(rte) rre = np.arccos((np.trace(T_est[:3, :3].t() @ T_gt[:3, :3]) - 1) / 2) if not np.isnan(rre): rre_meter.update(rre) hit_ratio = self.evaluate_hit_ratio(xyz0_corr, xyz1_corr, T_gt, thresh=self.config.hit_ratio_thresh) hit_ratio_meter.update(hit_ratio) feat_match_ratio.update(hit_ratio > 0.05) matching_timer.toc() num_data += 1 torch.cuda.empty_cache() if batch_idx % 100 == 0 and batch_idx > 0: logging.info(' '.join([ f"Validation iter {num_data} / {tot_num_data} : Data Loading Time: {data_timer.avg:.3f},", f"Feature Extraction Time: {feat_timer.avg:.3f}, Matching Time: {matching_timer.avg:.3f},", f"Loss: {loss_meter.avg:.3f}, RTE: {rte_meter.avg:.3f}, RRE: {rre_meter.avg:.3f},", f"Hit Ratio: {hit_ratio_meter.avg:.3f}, Feat Match Ratio: {feat_match_ratio.avg:.3f}" ])) data_timer.reset() logging.info(' '.join([ f"Final Loss: {loss_meter.avg:.3f}, RTE: {rte_meter.avg:.3f}, RRE: {rre_meter.avg:.3f},", f"Hit Ratio: {hit_ratio_meter.avg:.3f}, Feat Match Ratio: {feat_match_ratio.avg:.3f}" ])) return { "loss": loss_meter.avg, "rre": rre_meter.avg, "rte": rte_meter.avg, 'feat_match_ratio': feat_match_ratio.avg, 'hit_ratio': hit_ratio_meter.avg }
def test_net(self, graph): timer = Timer() timer.tic() if os.path.exists(self._cfg.TEST.RESULT_DIR_TXT): shutil.rmtree(self._cfg.TEST.RESULT_DIR_TXT) os.makedirs(self._cfg.TEST.RESULT_DIR_TXT) if os.path.exists(self._cfg.TEST.RESULT_DIR_PIC): shutil.rmtree(self._cfg.TEST.RESULT_DIR_PIC) os.makedirs(self._cfg.TEST.RESULT_DIR_PIC) saver = tf.train.Saver() # 创建一个Session config = tf.ConfigProto(allow_soft_placement=True) config.gpu_options.allocator_type = 'BFC' config.gpu_options.per_process_gpu_memory_fraction = 0.7 # 不能太大,否则报错 sess = tf.Session(config=config, graph=graph) # 获取一个Saver()实例 # 恢复模型参数 ckpt = tf.train.get_checkpoint_state(self._cfg.COMMON.CKPT) if ckpt and ckpt.model_checkpoint_path: print('Restoring from {}...'.format(ckpt.model_checkpoint_path), end=' ') try: saver.restore(sess, ckpt.model_checkpoint_path) except: raise 'Check your pretrained {:s}'.format(ckpt.model_checkpoint_path) print('done') else: raise 'Check your pretrained {:s}'.format(self._cfg.TEST.RESULT_DIR) # # TODO 这里需要仔细测试一下 # im_names = glob.glob(os.path.join(self._cfg.TEST.DATA_DIR, '*.png')) + \ # glob.glob(os.path.join(self._cfg.TEST.DATA_DIR, '*.jpg')) im_names = os.listdir(self._cfg.TEST.DATA_DIR) assert len(im_names) > 0, "Nothing to test" i = 0 for im in im_names: im_name = os.path.join(self._cfg.TEST.DATA_DIR, im) # print('~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~') # print(('Testing for image {:s}'.format(im_name))) try: self.ctpn(sess, self._net, im_name) except NoPositiveError: print("Warning!!, get no region of interest in picture {}".format(im)) continue except: print("the pic {} may has problems".format(im)) continue i += 1 if i % 10 == 0: timer.toc() print('Detection took {:.3f}s for 10 pic'.format(timer.total_time)) # 最后关闭session sess.close()
def _train_epoch(self, epoch): gc.collect() self.model.train() # Epoch starts from 1 self.data_loader.sampler.set_epoch(epoch) data_timer, total_timer = Timer(), Timer() start_iter = (epoch - 1) * len(self.data_loader) data_timer.tic() total_timer.tic() for curr_iter, input_dict in enumerate(self.data_loader): data_timer.toc() self.optimizer.zero_grad() batch_pos_loss, batch_neg_loss, batch_loss = 0, 0, 0 sinput0 = ME.SparseTensor(input_dict['sinput0_F'].to(self.device), coordinates=input_dict['sinput0_C'].to( self.device)) F0 = self.model(sinput0).F sinput1 = ME.SparseTensor(input_dict['sinput1_F'].to(self.device), coordinates=input_dict['sinput1_C'].to( self.device)) F1 = self.model(sinput1).F pos_pairs = input_dict['correspondences'] pos_loss, neg_loss = self.contrastive_hardest_negative_loss( input_dict['pcd0_rot'], input_dict['pcd1'], F0, F1, pos_pairs, num_pos=self.config.num_pos_per_batch * self.config.batch_size, num_hn_samples=self.config.num_hn_samples_per_batch * self.config.batch_size, matching_search_voxel_size=self.config.voxel_size * self.config.positive_pair_search_voxel_size_multiplier) loss = pos_loss + self.neg_weight * neg_loss loss.backward() batch_loss += loss.item() batch_pos_loss += pos_loss.item() batch_neg_loss += neg_loss.item() self.sum_gradients() self.optimizer.step() torch.cuda.empty_cache() total_timer.toc() if curr_iter % self.config.stat_freq == 0: report = torch.tensor( [1.0, batch_loss, batch_pos_loss, batch_neg_loss], device=torch.cuda.current_device()) dist.all_reduce(report, op=dist.ReduceOp.SUM) count = report[0].item() m_batch_loss = report[1].item() / count m_batch_pos_loss = report[2].item() / count m_batch_neg_loss = report[3].item() / count if self.rank == 0: self.writer.add_scalar('train/loss', m_batch_loss, start_iter + curr_iter) self.writer.add_scalar('train/pos_loss', m_batch_pos_loss, start_iter + curr_iter) self.writer.add_scalar('train/neg_loss', m_batch_neg_loss, start_iter + curr_iter) logging.info( "Train Epoch: {} [{}/{}], Current Loss: {:.3e} Pos: {:.3f} Neg: {:.3f}" .format(epoch, curr_iter, len( self.data_loader), m_batch_loss, m_batch_pos_loss, m_batch_neg_loss) + "\tData time: {:.4f}, Train time: {:.4f}, Iter time: {:.4f}" .format(data_timer.avg, total_timer.avg - data_timer.avg, total_timer.avg)) total_timer.reset() total_timer.tic() data_timer.tic()
def main(config): test_loader = make_data_loader(config, config.test_phase, 1, num_threads=config.test_num_thread, shuffle=False) num_feats = 1 device = torch.device('cuda' if torch.cuda.is_available() else 'cpu') Model = load_model(config.model) model = Model(num_feats, config.model_n_out, bn_momentum=config.bn_momentum, conv1_kernel_size=config.conv1_kernel_size, normalize_feature=config.normalize_feature) checkpoint = torch.load(config.save_dir + '/checkpoint.pth') model.load_state_dict(checkpoint['state_dict']) model = model.to(device) model.eval() success_meter, rte_meter, rre_meter = AverageMeter(), AverageMeter( ), AverageMeter() data_timer, feat_timer, reg_timer = Timer(), Timer(), Timer() test_iter = test_loader.__iter__() N = len(test_iter) n_gpu_failures = 0 # downsample_voxel_size = 2 * config.voxel_size list_results_to_save = [] for i in range(len(test_iter)): data_timer.tic() try: data_dict = test_iter.next() except ValueError: n_gpu_failures += 1 logging.info(f"# Erroneous GPU Pair {n_gpu_failures}") continue data_timer.toc() xyz0, xyz1 = data_dict['pcd0'], data_dict['pcd1'] T_gth = data_dict['T_gt'] xyz0np, xyz1np = xyz0.numpy(), xyz1.numpy() #import pdb # pdb.set_trace() pcd0 = make_open3d_point_cloud(xyz0np) pcd1 = make_open3d_point_cloud(xyz1np) with torch.no_grad(): feat_timer.tic() sinput0 = ME.SparseTensor( data_dict['sinput0_F'].to(device), coordinates=data_dict['sinput0_C'].to(device)) F0 = model(sinput0).F.detach() sinput1 = ME.SparseTensor( data_dict['sinput1_F'].to(device), coordinates=data_dict['sinput1_C'].to(device)) F1 = model(sinput1).F.detach() feat_timer.toc() # saving files to pkl print(i) dict_sample = { "pts_source": xyz0np, "feat_source": F0.cpu().detach().numpy(), "pts_target": xyz1np, "feat_target": F1.cpu().detach().numpy() } list_results_to_save.append(dict_sample) import pickle path_results_to_save = "fcgf.results.pkl" print('Saving results to ', path_results_to_save) pickle.dump(list_results_to_save, open(path_results_to_save, 'wb')) print('Saved!') import pdb pdb.set_trace()
def dump_correspondences(config): # load model device = torch.device('cuda' if torch.cuda.is_available() else 'cpu') checkpoint = torch.load(config.weights) model = ResUNetBN2D2(1, 64, normalize_feature=True) model.load_state_dict(checkpoint['state_dict']) model.eval() model = model.to(device) print("load model") # load dataset source = config.source with h5py.File(config.target, 'r+') as ofp: new_data = {} keys = ['ucn_coords', 'ucn_n_coords'] for k in keys: if k in ofp.keys(): new_data[k] = ofp[k] else: new_data[k] = ofp.create_group(k) len_dset = len(ofp['coords']) keys = ofp['ucn_coords'].keys() print("len dataset : ", len_dset) matching_timer, write_timer = Timer(), Timer() # extract correspondences for i in range(len_dset): # skip existing pair if str(i) in keys: continue _coords = ofp['coords'][str(i)] img_path0 = _coords.attrs['img0'] img_path1 = _coords.attrs['img1'] img_idx0 = int(_coords.attrs['idx0']) + 1 img_idx1 = int(_coords.attrs['idx1']) + 1 calib_path0 = "/".join(img_path0.split("/")[:-2]) calib_path0 += f"/calibration/calibration_{img_idx0:06d}.h5" calib_path1 = "/".join(img_path1.split("/")[:-2]) calib_path1 += f"/calibration/calibration_{img_idx1:06d}.h5" img0 = prep_image(osp.join(source, img_path0)) img1 = prep_image(osp.join(source, img_path1)) F0 = model(to_normalized_torch(img0, device)) F1 = model(to_normalized_torch(img1, device)) args = (img0, img1, calib_path0, calib_path1, F0, F1, i, len_dset, source) matching_timer.tic() coords, n_coords = dump_correspondence_single(args) matching_timer.toc() write_timer.tic() coords_data = new_data['ucn_coords'].create_dataset( str(i), coords.shape, dtype=np.float32) coords_data[:] = coords.astype(np.float32) n_coords_data = new_data['ucn_n_coords'].create_dataset( str(i), n_coords.shape, dtype=np.float32) n_coords_data[:] = n_coords.astype(np.float32) write_timer.toc() print( f"[{i}/{len_dset}] save {coords.shape} coordinate, matching {matching_timer.avg:.3f}, write {write_timer.avg:.3f}" )