def __init__(self, num_points, num_obj, estimator_weights_file, refiner_weights_file=None, batch_size=1): self.num_points = num_points self.bs = batch_size self.estimator = PoseNet(num_points=num_points, num_obj=num_obj) if (torch.cuda.is_available()): self.estimator.cuda() self.estimator.load_state_dict(torch.load(estimator_weights_file)) else: self.estimator.load_state_dict( torch.load(estimator_weights_file, map_location=lambda storage, loc: storage)) self.estimator.eval() if (refiner_weights_file is not None): self.refiner = PoseRefineNet(num_points=num_points, num_obj=num_obj) if (torch.cuda.is_available()): self.refiner.cuda() self.refiner.load_state_dict(torch.load(refiner_weights_file)) self.refiner.eval() else: self.refiner = None
def load_net_model(): parser = argparse.ArgumentParser() parser.add_argument('--seg_model', type=str, default='D:/DenseFusion_1.0_20210308/Seg_Pose/Seg/trained_models/model_2_0.0033125885542725133.pth', help='resume Seg model') parser.add_argument('--model', type=str, default='D:/DenseFusion_1.0_20210308/Seg_Pose/Pose/trained_models/pose_model_2_0.09233990000864985.pth', help='resume PoseNet model') parser.add_argument('--refine_model', type=str, default='D:/DenseFusion_1.0_20210308/Seg_Pose/Pose/trained_models/pose_refine_model_4_0.06547849291308346.pth', help='resume PoseRefineNet model') opt = parser.parse_args() global estimator estimator = PoseNet(num_points=num_points, num_obj=num_objects) estimator.cuda() global refiner refiner = PoseRefineNet(num_points=num_points, num_obj=num_objects) refiner.cuda() estimator.load_state_dict(torch.load(opt.model)) refiner.load_state_dict(torch.load(opt.refine_model)) estimator.eval() refiner.eval() global testdataset testdataset = sp_Dataset(opt.seg_model, num_points, False, 0.0, True)
def main(args): seg_model = segnet() seg_model.cuda() #seg_model.load_state_dict(torch.load('./segschaltgabel.pth')) #uncomment if we are using the original segnet #seg_model.load_state_dict(torch.load('./schaltgabel_pruned.pth')) #seg_model.load_state_dict(torch.load('./stift_pruned.pth')) #seg_model.load_state_dict(torch.load('./flansch_pruned.pth')) if opt.model == 'flansch': seg_model.load_state_dict(torch.load('./segflansch.pth')) #seg_model.load_state_dict(torch.load('./flansch_pruned.pth')) idx = 0 scaled = np.array([[59, -42, 59], [59, -42, -59], [59, 20, -59], [59, 20, 59], [-59, -42, 59], [-59, -42, -59], [-59, 20, -59], [-59, 20, 59] ]) / 1000 #flansch_3d_bbox elif opt.model == 'schaltgabel': seg_model.load_state_dict(torch.load('./segschaltgabel.pth')) #seg_model.load_state_dict(torch.load('./schaltgabel_pruned.pth')) idx = 1 scaled = np.array([[-54.7478, -16.7500, 23], [-54.7478, -16.7500, 0], [54.7478, -16.7500, 0], [54.7478, -16.7500, 23], [-54.7478, 130.85, 23], [-54.7478, 130.85, 0], [54.7478, 130.85, 0], [54.7478, 130.85, 23] ]) / 1000 #schaltgabel_3d_bbox else: #seg_model.load_state_dict(torch.load('./stift_pruned.pth')) seg_model.load_state_dict(torch.load('./segstift.pth')) idx = 2 scaled = np.array( [[-20, -35, 19.9878], [-20, -35, -19.9878], [20, -35, -19.9878], [20, -35, 19.9878], [-20, 87, 19.9878], [-20, 87, -19.9878], [20, 87, -19.9878], [20, 87, 19.9878]]) / 1000 #stift_3d_bbox seg_model.eval() estimator = PoseNet(num_points, num_objects) estimator.cuda() refiner = PoseRefineNet(num_points, num_objects) refiner.cuda() estimator.load_state_dict(torch.load('./pose_model_current.pth')) refiner.load_state_dict(torch.load('./pose_refine_model_current.pth')) estimator.eval() refiner.eval() pe = pose_estimation(seg_model, estimator, refiner, idx, scaled) rospy.init_node('pose_estimation', anonymous=True) try: rospy.spin() except KeyboardInterrupt: print('Shutting down ROS pose estimation module') cv2.destroyAllWindows()
def __init__(self, model, model_with_refinement, width, height, fx, fy, cx, cy, number_points=1000, number_iterations=2): self.width = width self.height = height self.fx = fx self.fy = fy self.cx = cx self.cy = cy self.number_iterations = number_iterations self.norm = transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]) self.border_list = [ -1, 40, 80, 120, 160, 200, 240, 280, 320, 360, 400, 440, 480, 520, 560, 600, 640, 680 ] self.xmap = numpy.array([[j for i in range(self.width)] for j in range(self.height)]) self.ymap = numpy.array([[i for i in range(self.width)] for j in range(self.height)]) self.number_points = number_points self.estimator = PoseNet(num_points=self.number_points, num_obj=21) self.estimator.cuda() self.estimator.load_state_dict(torch.load(model)) self.estimator.eval() self.refiner = PoseRefineNet(num_points=self.number_points, num_obj=21) self.refiner.cuda() self.refiner.load_state_dict(torch.load(model_with_refinement)) self.refiner.eval()
def __init__(self, posecnn): # posecnn self.posecnn = posecnn # df #camera paras self.cam_cx = 312.9869 #??? self.cam_cy = 241.3109 #??? self.cam_fx = 1066.778 #x方向焦距,水平 self.cam_fy = 1067.487 #y方向焦距,垂直 self.cam_scale = 10000.0 # scale ???? #main self.num_points = 1000 # default self.num_obj = 21 # ycb 已经训练好了,含有21个类,不能改。 self.xmap = np.array([[j for i in range(640)] for j in range(480) ]) # [0000...,1111...,222] 480,640 self.ymap = np.array([ [i for i in range(640)] for j in range(480) ]) # [0 1 2 3..., 0 1 2 3 ..., 0 1 2 3 ...] 480,640 self.norm = transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225 ]) # For img transform in the df self.bs = 1 self.iteration = 2 self.esti_model_file = "src/pose_model_26_0.012863246640872631.pth" self.refine_model_file = "src/pose_refine_model_69_0.009449292959118935.pth" self.estimator = PoseNet(num_points=self.num_points, num_obj=self.num_obj) self.estimator.cuda() self.estimator.load_state_dict(torch.load(self.esti_model_file)) self.estimator.eval() self.refiner = PoseRefineNet(num_points=self.num_points, num_obj=self.num_obj) self.refiner.cuda() self.refiner.load_state_dict(torch.load(self.refine_model_file)) self.refiner.eval() self.lst = [ 1 ] # assume only banana. This is designed for multi-label task, if multi label detected in one img, #they may allocated with different id, id==1.it means the label is 1, id==2, it means the label is 2; so with known the #label, we can know label1 is banana ,label2 is apple like this. self.my_result_wo_refine = [] # ??? self.my_result = []
def main(): # Globals global refiner, estimator # Setup upload folder and run server if not os.path.exists(UPLOAD_FOLDER): os.makedirs(UPLOAD_FOLDER) # Sets up network refiner = PoseRefineNet(num_points=num_points, num_obj=num_obj) refiner.cuda() refiner.load_state_dict(torch.load(opt.refine_model)) refiner.eval() estimator = PoseNet(num_points=num_points, num_obj=num_obj) estimator.cuda() estimator.load_state_dict(torch.load(opt.model)) estimator.eval() app.config['UPLOAD_FOLDER'] = UPLOAD_FOLDER app.run(port=PORT, host='0.0.0.0', debug=False)
def main(): opt.manualSeed = random.randint(1, 10000) random.seed(opt.manualSeed) torch.manual_seed(opt.manualSeed) if not os.path.exists(opt.output_folder): os.makedirs(opt.output_folder) num_points = 1000 #number of points on the input pointcloud num_objects = 21 if (opt.object_indices is None): opt.object_indices = list(range(1, num_objects + 1)) estimator = PoseNet(num_points=num_points, num_obj=num_objects) estimator.cuda() estimator.load_state_dict(torch.load(opt.weights)) output_format = [ otypes.OBJECT_LABEL, otypes.QUATERNION, otypes.IMAGE_CROPPED, otypes.DEPTH_POINTS_MASKED_AND_INDEXES ] estimator.eval() with torch.no_grad(): with std_out_err_redirect_tqdm() as orig_stdout: pbar = tqdm(opt.object_indices, file=orig_stdout, dynamic_ncols=True) for cls in pbar: preprocessors = [InplaneRotator(theta=np.pi / 2)] postprocessors = [ImageNormalizer()] if (opt.num_augmentations > 0): preprocessors.extend([ YCBOcclusionAugmentor(opt.dataset_root), ColorJitter(), ]) postprocessors.append(PointShifter()) dataset = YCBDataset(opt.dataset_root, mode=opt.dataset_mode, object_list=[cls], output_data=output_format, resample_on_error=False, add_syn_background=opt.add_syn_background, add_syn_noise=opt.add_syn_background, preprocessors=preprocessors, postprocessors=postprocessors, image_size=[640, 480], num_points=1000) classes = dataset.classes dataloader = torch.utils.data.DataLoader( dataset, batch_size=1, shuffle=False, num_workers=opt.workers) pbar.set_description('Featurizing {}'.format(classes[cls])) if (opt.num_augmentations > 0): pbar_aug = trange(opt.start_index, opt.num_augmentations, file=orig_stdout, dynamic_ncols=True) else: pbar_aug = [None] for aug_idx in pbar_aug: pbar_save = tqdm(enumerate(dataloader), total=len(dataloader), file=orig_stdout, dynamic_ncols=True) for i, data in pbar_save: if (len(data) == 0 or len(data[0]) == 0): continue idx, quat, img, points, choose = data data_path = dataset.image_list[i] idx = idx - 1 img = Variable(img).cuda() points = Variable(points).cuda() choose = Variable(choose).cuda() idx = Variable(idx).cuda() assert cls == data_path[1] assert cls - 1 == int(idx[0]) pred_r, pred_t, pred_c, emb, feat, feat_global = estimator.allFeatures( img, points, choose, idx) if (opt.num_augmentations > 0): output_filename = '{0}/data/{1}_{2}_{3}_feat.npz'.format( opt.output_folder, data_path[0], classes[cls], aug_idx) else: output_filename = '{0}/data/{1}_{2}_feat.npz'.format( opt.output_folder, data_path[0], classes[cls]) #pbar_save.set_description(output_filename) os.makedirs(os.path.dirname(output_filename), exist_ok=True) how_max, which_max = torch.max(pred_c, 1) max_feat = feat[0, :, which_max[0]].view(-1) pred_t = pred_t[0, :] pred_q = pred_r[0, :, [1, 2, 3, 0]] pred_q /= torch.norm(pred_q, dim=1).view(-1, 1) np.savez( output_filename, max_c=to_np(how_max), max_q=to_np(pred_q[which_max.item()]), max_t=to_np(pred_t[which_max.item()]), pred_c=to_np(pred_c), pred_q=to_np(pred_q), pred_t=to_np(pred_t), quat=to_np(quat)[0], feat=to_np(max_feat), #feat_all = to_np(feat)[0].T, i feat_global=to_np(feat_global)[0], #max_confidence = to_np(how_max), #confidence = to_np(pred_c)[0], )
delt = -cmin cmin = 0 cmax += delt if rmax > img_width: delt = rmax - img_width rmax = img_width rmin -= delt if cmax > img_length: delt = cmax - img_length cmax = img_length cmin -= delt return rmin, rmax, cmin, cmax os.environ['CUDA_VISIBLE_DEVICES'] = opt.gpu_id estimator = PoseNet(num_points=num_points, num_obj=num_obj, num_rot=num_rotations) estimator.cuda() estimator.load_state_dict(torch.load(opt.model)) estimator.eval() rot_anchors = torch.from_numpy(estimator.rot_anchors).float().cuda() testlist = [] input_file = open('{0}/test_data_list.txt'.format(dataset_config_dir)) while 1: input_line = input_file.readline() if not input_line: break if input_line[-1:] == '\n': input_line = input_line[:-1] testlist.append(input_line) input_file.close()
os.environ["CUDA_VISIBLE_DEVICES"]="0" # "0,1,2,3" num_objects = 1 num_points = 1000 knn = KNearestNeighbor(1) path = '/home/ash/catkin_ws/src/DF_ros_linemod/' seg = segnet() seg.cuda() seg.load_state_dict(torch.load(path + 'txonigiri/seg_model_02_49.pth')) seg.eval() print("segnet_model loaded ...") pose = PoseNet(num_points, num_objects) pose.cuda() pose.load_state_dict(torch.load(path + 'txonigiri/pose_model.pth')) pose.eval() print("pose_model loaded...") refiner = PoseRefineNet(num_points, num_objects) refiner.cuda() refiner.load_state_dict(torch.load(path + 'txonigiri/pose_refine_model.pth')) refiner.eval() print("pose_refine_model loaded...") #%% def get_bbox(bbox):
def main(): opt.manualSeed = random.randint(1, 10000) random.seed(opt.manualSeed) torch.manual_seed(opt.manualSeed) if opt.dataset == 'linemod': opt.num_objects = 13 opt.num_points = 500 opt.outf = 'trained_models/linemod' opt.log_dir = 'experiments/logs/linemod' output_results = 'check_linemod.txt' opt.repeat_epoch = 20 elif opt.dataset == 'ycb': opt.num_objects = 21 #number of object classes in the dataset opt.num_points = 1000 #number of points on the input pointcloud opt.outf = 'trained_models/ycb' #folder to save trained models opt.log_dir = 'experiments/logs/ycb' #folder to save logs opt.repeat_epoch = 1 #number of repeat times for one epoch training elif opt.dataset == 'ycb-syn': opt.num_objects = 31 # number of object classes in the dataset opt.num_points = 1000 # number of points on the input pointcloud opt.dataset_root = '/data/Akeaveny/Datasets/ycb_syn' opt.outf = 'trained_models/ycb_syn/ycb_syn2' # folder to save trained models opt.log_dir = 'experiments/logs/ycb_syn/ycb_syn2' # folder to save logs output_results = 'check_ycb_syn.txt' opt.w = 0.05 opt.refine_margin = 0.01 elif opt.dataset == 'arl': opt.num_objects = 10 # number of object classes in the dataset opt.num_points = 1000 # number of points on the input pointcloud opt.dataset_root = '/data/Akeaveny/Datasets/arl_dataset' opt.outf = 'trained_models/arl/clutter/arl_finetune_syn_2' # folder to save trained models opt.log_dir = '/home/akeaveny/catkin_ws/src/object-rpe-ak/DenseFusion/experiments/logs/arl/clutter/arl_finetune_syn_2' # folder to save logs output_results = 'check_arl_syn.txt' opt.nepoch = 750 opt.w = 0.05 opt.refine_margin = 0.0045 # TODO opt.repeat_epoch = 20 opt.start_epoch = 0 opt.resume_posenet = 'pose_model_1_0.012397416144377301.pth' opt.resume_refinenet = 'pose_refine_model_153_0.004032851301599294.pth' elif opt.dataset == 'arl1': opt.num_objects = 5 # number of object classes in the dataset opt.num_points = 1000 # number of points on the input pointcloud opt.dataset_root = '/data/Akeaveny/Datasets/arl_dataset' opt.outf = 'trained_models/arl1/clutter/arl_real_2' # folder to save trained models opt.log_dir = '/home/akeaveny/catkin_ws/src/object-rpe-ak/DenseFusion/experiments/logs/arl1/clutter/arl_real_2' # folder to save logs output_results = 'check_arl_syn.txt' opt.nepoch = 750 opt.w = 0.05 opt.refine_margin = 0.015 # opt.start_epoch = 120 # opt.resume_posenet = 'pose_model_current.pth' # opt.resume_refinenet = 'pose_refine_model_115_0.008727498716640046.pth' elif opt.dataset == 'elevator': opt.num_objects = 1 # number of object classes in the dataset opt.num_points = 1000 # number of points on the input pointcloud opt.dataset_root = '/data/Akeaveny/Datasets/elevator_dataset' opt.outf = 'trained_models/elevator/elevator_2' # folder to save trained models opt.log_dir = '/home/akeaveny/catkin_ws/src/object-rpe-ak/DenseFusion/experiments/logs/elevator/elevator_2' # folder to save logs output_results = 'check_arl_syn.txt' opt.nepoch = 750 opt.w = 0.05 opt.refine_margin = 0.015 opt.nepoch = 750 opt.w = 0.05 opt.refine_margin = 0.015 # TODO opt.repeat_epoch = 40 # opt.start_epoch = 47 # opt.resume_posenet = 'pose_model_current.pth' # opt.resume_refinenet = 'pose_refine_model_46_0.007581770288279472.pth' else: print('Unknown dataset') return estimator = PoseNet(num_points=opt.num_points, num_obj=opt.num_objects) estimator.cuda() refiner = PoseRefineNet(num_points=opt.num_points, num_obj=opt.num_objects) refiner.cuda() if opt.resume_posenet != '': estimator.load_state_dict( torch.load('{0}/{1}'.format(opt.outf, opt.resume_posenet))) if opt.resume_refinenet != '': refiner.load_state_dict( torch.load('{0}/{1}'.format(opt.outf, opt.resume_refinenet))) opt.refine_start = False opt.decay_start = False opt.lr *= opt.lr_rate opt.w *= opt.w_rate opt.batch_size = int(opt.batch_size / opt.iteration) optimizer = optim.Adam(refiner.parameters(), lr=opt.lr) else: opt.refine_start = False opt.decay_start = False optimizer = optim.Adam(estimator.parameters(), lr=opt.lr) if opt.dataset == 'ycb': dataset = PoseDataset_ycb('train', opt.num_points, True, opt.dataset_root, opt.noise_trans, opt.refine_start) elif opt.dataset == 'linemod': dataset = PoseDataset_linemod('train', opt.num_points, True, opt.dataset_root, opt.noise_trans, opt.refine_start) elif opt.dataset == 'ycb-syn': dataset = PoseDataset_ycb_syn('train', opt.num_points, True, opt.dataset_root, opt.noise_trans, opt.refine_start) elif opt.dataset == 'arl': dataset = PoseDataset_arl('train', opt.num_points, True, opt.dataset_root, opt.noise_trans, opt.refine_start) elif opt.dataset == 'arl1': dataset = PoseDataset_arl1('train', opt.num_points, True, opt.dataset_root, opt.noise_trans, opt.refine_start) elif opt.dataset == 'elevator': dataset = PoseDataset_elevator('train', opt.num_points, True, opt.dataset_root, opt.noise_trans, opt.refine_start) dataloader = torch.utils.data.DataLoader(dataset, batch_size=1, shuffle=True, num_workers=opt.workers) if opt.dataset == 'ycb': test_dataset = PoseDataset_ycb('test', opt.num_points, False, opt.dataset_root, 0.0, opt.refine_start) elif opt.dataset == 'linemod': test_dataset = PoseDataset_linemod('test', opt.num_points, False, opt.dataset_root, 0.0, opt.refine_start) elif opt.dataset == 'ycb-syn': test_dataset = PoseDataset_ycb_syn('test', opt.num_points, True, opt.dataset_root, 0.0, opt.refine_start) elif opt.dataset == 'arl': test_dataset = PoseDataset_arl('test', opt.num_points, True, opt.dataset_root, 0.0, opt.refine_start) elif opt.dataset == 'arl1': test_dataset = PoseDataset_arl1('test', opt.num_points, True, opt.dataset_root, 0.0, opt.refine_start) elif opt.dataset == 'elevator': test_dataset = PoseDataset_elevator('test', opt.num_points, True, opt.dataset_root, 0.0, opt.refine_start) testdataloader = torch.utils.data.DataLoader(test_dataset, batch_size=1, shuffle=False, num_workers=opt.workers) opt.sym_list = dataset.get_sym_list() opt.num_points_mesh = dataset.get_num_points_mesh() print( '>>>>>>>>----------Dataset loaded!---------<<<<<<<<\nlength of the training set: {0}\nlength of the testing set: {1}\nnumber of sample points on mesh: {2}\nsymmetry object list: {3}' .format(len(dataset), len(test_dataset), opt.num_points_mesh, opt.sym_list)) criterion = Loss(opt.num_points_mesh, opt.sym_list) criterion_refine = Loss_refine(opt.num_points_mesh, opt.sym_list) best_test = np.Inf if opt.start_epoch == 1: for log in os.listdir(opt.log_dir): os.remove(os.path.join(opt.log_dir, log)) st_time = time.time() ###################### ###################### # TODO (ak): set up tensor board # if not os.path.exists(opt.log_dir): # os.makedirs(opt.log_dir) # # writer = SummaryWriter(opt.log_dir) ###################### ###################### for epoch in range(opt.start_epoch, opt.nepoch): logger = setup_logger( 'epoch%d' % epoch, os.path.join(opt.log_dir, 'epoch_%d_log.txt' % epoch)) logger.info('Train time {0}'.format( time.strftime("%Hh %Mm %Ss", time.gmtime(time.time() - st_time)) + ', ' + 'Training started')) train_count = 0 train_dis_avg = 0.0 if opt.refine_start: estimator.eval() refiner.train() else: estimator.train() optimizer.zero_grad() for rep in range(opt.repeat_epoch): ################## # train ################## for i, data in enumerate(dataloader, 0): points, choose, img, target, model_points, idx = data # TODO: txt file # fw = open(test_folder + output_results, 'w') # fw.write('Points\n{0}\n\nchoose\n{1}\n\nimg\n{2}\n\ntarget\n{3}\n\nmodel_points\n{4}'.format(points, choose, img, target, model_points)) # fw.close() points, choose, img, target, model_points, idx = Variable(points).cuda(), \ Variable(choose).cuda(), \ Variable(img).cuda(), \ Variable(target).cuda(), \ Variable(model_points).cuda(), \ Variable(idx).cuda() pred_r, pred_t, pred_c, emb = estimator( img, points, choose, idx) loss, dis, new_points, new_target = criterion( pred_r, pred_t, pred_c, target, model_points, idx, points, opt.w, opt.refine_start) if opt.refine_start: for ite in range(0, opt.iteration): pred_r, pred_t = refiner(new_points, emb, idx) dis, new_points, new_target = criterion_refine( pred_r, pred_t, new_target, model_points, idx, new_points) dis.backward() else: loss.backward() train_dis_avg += dis.item() train_count += 1 if train_count % opt.batch_size == 0: logger.info( 'Train time {} Epoch {} Batch {} Frame {}/{} Avg_dis: {:.2f} [cm]' .format( time.strftime("%Hh %Mm %Ss", time.gmtime(time.time() - st_time)), epoch, int(train_count / opt.batch_size), train_count, len(dataset.list), train_dis_avg / opt.batch_size * 100)) optimizer.step() optimizer.zero_grad() # TODO: tensorboard # if train_count != 0 and train_count % 250 == 0: # scalar_info = {'loss': loss.item(), # 'dis': train_dis_avg / opt.batch_size} # for key, val in scalar_info.items(): # writer.add_scalar(key, val, train_count) train_dis_avg = 0 if train_count != 0 and train_count % 1000 == 0: if opt.refine_start: torch.save( refiner.state_dict(), '{0}/pose_refine_model_current.pth'.format( opt.outf)) else: torch.save( estimator.state_dict(), '{0}/pose_model_current.pth'.format(opt.outf)) # TODO: tensorboard # scalar_info = {'loss': loss.item(), # 'dis': dis.item()} # for key, val in scalar_info.items(): # writer.add_scalar(key, val, train_count) print( '>>>>>>>>----------epoch {0} train finish---------<<<<<<<<'.format( epoch)) logger = setup_logger( 'epoch%d_test' % epoch, os.path.join(opt.log_dir, 'epoch_%d_test_log.txt' % epoch)) logger.info('Test time {0}'.format( time.strftime("%Hh %Mm %Ss", time.gmtime(time.time() - st_time)) + ', ' + 'Testing started')) test_dis = 0.0 test_count = 0 estimator.eval() refiner.eval() for j, data in enumerate(testdataloader, 0): points, choose, img, target, model_points, idx = data points, choose, img, target, model_points, idx = Variable(points).cuda(), \ Variable(choose).cuda(), \ Variable(img).cuda(), \ Variable(target).cuda(), \ Variable(model_points).cuda(), \ Variable(idx).cuda() pred_r, pred_t, pred_c, emb = estimator(img, points, choose, idx) _, dis, new_points, new_target = criterion(pred_r, pred_t, pred_c, target, model_points, idx, points, opt.w, opt.refine_start) if opt.refine_start: for ite in range(0, opt.iteration): pred_r, pred_t = refiner(new_points, emb, idx) dis, new_points, new_target = criterion_refine( pred_r, pred_t, new_target, model_points, idx, new_points) test_dis += dis.item() logger.info('Test time {} Test Frame No.{} dis: {} [cm]'.format( time.strftime("%Hh %Mm %Ss", time.gmtime(time.time() - st_time)), test_count, dis * 100)) test_count += 1 test_dis = test_dis / test_count logger.info( 'Test time {} Epoch {} TEST FINISH Avg dis: {} [cm]'.format( time.strftime("%Hh %Mm %Ss", time.gmtime(time.time() - st_time)), epoch, test_dis * 100)) # TODO: tensorboard # scalar_info = {'test dis': test_dis} # for key, val in scalar_info.items(): # writer.add_scalar(key, val, train_count) if test_dis <= best_test: best_test = test_dis if opt.refine_start: torch.save( refiner.state_dict(), '{0}/pose_refine_model_{1}_{2}.pth'.format( opt.outf, epoch, test_dis)) else: torch.save( estimator.state_dict(), '{0}/pose_model_{1}_{2}.pth'.format( opt.outf, epoch, test_dis)) print(epoch, '>>>>>>>>----------BEST TEST MODEL SAVED---------<<<<<<<<') if best_test < opt.decay_margin and not opt.decay_start: opt.decay_start = True opt.lr *= opt.lr_rate opt.w *= opt.w_rate optimizer = optim.Adam(estimator.parameters(), lr=opt.lr) if best_test < opt.refine_margin and not opt.refine_start: opt.refine_start = True opt.batch_size = int(opt.batch_size / opt.iteration) optimizer = optim.Adam(refiner.parameters(), lr=opt.lr) if opt.dataset == 'ycb': dataset = PoseDataset_ycb('train', opt.num_points, True, opt.dataset_root, opt.noise_trans, opt.refine_start) elif opt.dataset == 'linemod': dataset = PoseDataset_linemod('train', opt.num_points, True, opt.dataset_root, opt.noise_trans, opt.refine_start) elif opt.dataset == 'ycb-syn': dataset = PoseDataset_ycb_syn('train', opt.num_points, True, opt.dataset_root, opt.noise_trans, opt.refine_start) elif opt.dataset == 'arl': dataset = PoseDataset_arl('train', opt.num_points, True, opt.dataset_root, opt.noise_trans, opt.refine_start) elif opt.dataset == 'arl1': dataset = PoseDataset_arl1('train', opt.num_points, True, opt.dataset_root, opt.noise_trans, opt.refine_start) elif opt.dataset == 'elevator': dataset = PoseDataset_elevator('train', opt.num_points, True, opt.dataset_root, opt.noise_trans, opt.refine_start) dataloader = torch.utils.data.DataLoader(dataset, batch_size=1, shuffle=True, num_workers=opt.workers) if opt.dataset == 'ycb': test_dataset = PoseDataset_ycb('test', opt.num_points, False, opt.dataset_root, 0.0, opt.refine_start) elif opt.dataset == 'linemod': test_dataset = PoseDataset_linemod('test', opt.num_points, False, opt.dataset_root, 0.0, opt.refine_start) elif opt.dataset == 'ycb-syn': test_dataset = PoseDataset_ycb_syn('test', opt.num_points, True, opt.dataset_root, 0.0, opt.refine_start) elif opt.dataset == 'arl': test_dataset = PoseDataset_arl('test', opt.num_points, True, opt.dataset_root, 0.0, opt.refine_start) elif opt.dataset == 'arl1': test_dataset = PoseDataset_arl1('test', opt.num_points, True, opt.dataset_root, 0.0, opt.refine_start) elif opt.dataset == 'elevator': test_dataset = PoseDataset_elevator('test', opt.num_points, True, opt.dataset_root, 0.0, opt.refine_start) testdataloader = torch.utils.data.DataLoader( test_dataset, batch_size=1, shuffle=False, num_workers=opt.workers) opt.sym_list = dataset.get_sym_list() opt.num_points_mesh = dataset.get_num_points_mesh() print( '>>>>>>>>----------Dataset loaded!---------<<<<<<<<\nlength of the training set: {0}\nlength of the testing set: {1}\nnumber of sample points on mesh: {2}\nsymmetry object list: {3}' .format(len(dataset), len(test_dataset), opt.num_points_mesh, opt.sym_list)) criterion = Loss(opt.num_points_mesh, opt.sym_list) criterion_refine = Loss_refine(opt.num_points_mesh, opt.sym_list)
def main(): # g13: parameter setting ------------------- batch_id = 1 opt.dataset ='linemod' opt.dataset_root = './datasets/linemod/Linemod_preprocessed' estimator_path = 'trained_checkpoints/linemod/pose_model_9_0.01310166542980859.pth' refiner_path = 'trained_checkpoints/linemod/pose_refine_model_493_0.006761023565178073.pth' opt.resume_posenet = estimator_path opt.resume_posenet = refiner_path dataset_config_dir = 'datasets/linemod/dataset_config' output_result_dir = 'experiments/eval_result/linemod' bs = 1 #fixed because of the default setting in torch.utils.data.DataLoader opt.iteration = 2 #default is 4 in eval_linemod.py t1_idx = 0 t1_total_eval_num = 3 axis_range = 0.1 # the length of X, Y, and Z axis in 3D vimg_dir = 'verify_img' if not os.path.exists(vimg_dir): os.makedirs(vimg_dir) #------------------------------------------- if opt.dataset == 'ycb': opt.num_objects = 21 #number of object classes in the dataset opt.num_points = 1000 #number of points on the input pointcloud opt.outf = 'trained_models/ycb' #folder to save trained models opt.log_dir = 'experiments/logs/ycb' #folder to save logs opt.repeat_epoch = 1 #number of repeat times for one epoch training elif opt.dataset == 'linemod': opt.num_objects = 13 opt.num_points = 500 opt.outf = 'trained_models/linemod' opt.log_dir = 'experiments/logs/linemod' opt.repeat_epoch = 20 else: print('Unknown dataset') return estimator = PoseNet(num_points = opt.num_points, num_obj = opt.num_objects) estimator.cuda() refiner = PoseRefineNet(num_points = opt.num_points, num_obj = opt.num_objects) refiner.cuda() if opt.resume_posenet != '': estimator.load_state_dict(torch.load(estimator_path)) if opt.resume_refinenet != '': refiner.load_state_dict(torch.load(refiner_path)) opt.refine_start = True opt.decay_start = True opt.lr *= opt.lr_rate opt.w *= opt.w_rate opt.batch_size = int(opt.batch_size / opt.iteration) optimizer = optim.Adam(refiner.parameters(), lr=opt.lr) else: opt.refine_start = False opt.decay_start = False optimizer = optim.Adam(estimator.parameters(), lr=opt.lr) if opt.dataset == 'ycb': test_dataset = PoseDataset_ycb('test', opt.num_points, False, opt.dataset_root, 0.0, opt.refine_start) elif opt.dataset == 'linemod': test_dataset = PoseDataset_linemod('test', opt.num_points, False, opt.dataset_root, 0.0, opt.refine_start) testdataloader = torch.utils.data.DataLoader(test_dataset, batch_size=1, shuffle=False, num_workers=opt.workers) print('complete loading testing loader\n') opt.sym_list = test_dataset.get_sym_list() opt.num_points_mesh = test_dataset.get_num_points_mesh() print('>>>>>>>>----------Dataset loaded!---------<<<<<<<<\n\ length of the testing set: {0}\nnumber of sample points on mesh: {1}\n\ symmetry object list: {2}'\ .format( len(test_dataset), opt.num_points_mesh, opt.sym_list)) #load pytorch model estimator.eval() refiner.eval() criterion = Loss(opt.num_points_mesh, opt.sym_list) criterion_refine = Loss_refine(opt.num_points_mesh, opt.sym_list) fw = open('{0}/t1_eval_result_logs.txt'.format(output_result_dir), 'w') #Pose estimation for j, data in enumerate(testdataloader, 0): # g13: modify this part for evaluation target-------------------- if j == t1_total_eval_num: break #---------------------------------------------------------------- points, choose, img, target, model_points, idx = data if len(points.size()) == 2: print('No.{0} NOT Pass! Lost detection!'.format(j)) fw.write('No.{0} NOT Pass! Lost detection!\n'.format(j)) continue points, choose, img, target, model_points, idx = Variable(points).cuda(), \ Variable(choose).cuda(), \ Variable(img).cuda(), \ Variable(target).cuda(), \ Variable(model_points).cuda(), \ Variable(idx).cuda() pred_r, pred_t, pred_c, emb = estimator(img, points, choose, idx) _, dis, new_points, new_target = criterion(pred_r, pred_t, pred_c, target, model_points, idx, points, opt.w, opt.refine_start) #if opt.refine_start: #iterative poserefinement # for ite in range(0, opt.iteration): # pred_r, pred_t = refiner(new_points, emb, idx) # dis, new_points, new_target = criterion_refine(pred_r, pred_t, new_target, model_points, idx, new_points) pred_r = pred_r / torch.norm(pred_r, dim=2).view(1, opt.num_points, 1) pred_c = pred_c.view(bs, opt.num_points) how_max, which_max = torch.max(pred_c, 1) pred_t = pred_t.view(bs * opt.num_points, 1, 3) my_r = pred_r[0][which_max[0]].view(-1).cpu().data.numpy() my_t = (points.view(bs * opt.num_points, 1, 3) + pred_t)[which_max[0]].view(-1).cpu().data.numpy() my_pred = np.append(my_r, my_t) for ite in range(0, opt.iteration): T = Variable(torch.from_numpy(my_t.astype(np.float32))).cuda().view(1, 3).repeat(opt.num_points, 1).contiguous().view(1, opt.num_points, 3) my_mat = quaternion_matrix(my_r) R = Variable(torch.from_numpy(my_mat[:3, :3].astype(np.float32))).cuda().view(1, 3, 3) my_mat[0:3, 3] = my_t new_points = torch.bmm((points - T), R).contiguous() pred_r, pred_t = refiner(new_points, emb, idx) pred_r = pred_r.view(1, 1, -1) pred_r = pred_r / (torch.norm(pred_r, dim=2).view(1, 1, 1)) my_r_2 = pred_r.view(-1).cpu().data.numpy() my_t_2 = pred_t.view(-1).cpu().data.numpy() my_mat_2 = quaternion_matrix(my_r_2) my_mat_2[0:3, 3] = my_t_2 my_mat_final = np.dot(my_mat, my_mat_2) my_r_final = copy.deepcopy(my_mat_final) my_r_final[0:3, 3] = 0 my_r_final = quaternion_from_matrix(my_r_final, True) my_t_final = np.array([my_mat_final[0][3], my_mat_final[1][3], my_mat_final[2][3]]) my_pred = np.append(my_r_final, my_t_final) my_r = my_r_final my_t = my_t_final # g13: start drawing pose on image------------------------------------ # pick up image print("index {0}: {1}".format(j, test_dataset.list_rgb[j])) img = Image.open(test_dataset.list_rgb[j]) # pick up center position by bbox meta_file = open('{0}/data/{1}/gt.yml'.format(opt.dataset_root, '%02d' % test_dataset.list_obj[j]), 'r') meta = {} meta = yaml.load(meta_file) which_item = test_dataset.list_rank[j] bbx = meta[which_item][0]['obj_bb'] draw = ImageDraw.Draw(img) # draw box (ensure this is the right object) draw.line((bbx[0],bbx[1], bbx[0], bbx[1]+bbx[3]), fill=(255,0,0), width=5) draw.line((bbx[0],bbx[1], bbx[0]+bbx[2], bbx[1]), fill=(255,0,0), width=5) draw.line((bbx[0],bbx[1]+bbx[3], bbx[0]+bbx[2], bbx[1]+bbx[3]), fill=(255,0,0), width=5) draw.line((bbx[0]+bbx[2],bbx[1], bbx[0]+bbx[2], bbx[1]+bbx[3]), fill=(255,0,0), width=5) #get center c_x = bbx[0]+int(bbx[2]/2) c_y = bbx[1]+int(bbx[3]/2) draw.point((c_x,c_y), fill=(255,255,0)) #get the 3D position of center cam_intrinsic = np.zeros((3,3)) cam_intrinsic.itemset(0, test_dataset.cam_fx) cam_intrinsic.itemset(4, test_dataset.cam_fy) cam_intrinsic.itemset(2, test_dataset.cam_cx) cam_intrinsic.itemset(5, test_dataset.cam_cy) cam_intrinsic.itemset(8, 1) cam_extrinsic = my_mat_final[0:3, :] cam2d_3d = np.matmul(cam_intrinsic, cam_extrinsic) cen_3d = np.matmul(np.linalg.pinv(cam2d_3d), [[c_x],[c_y],[1]]) # replace img.show() with plt.imshow(img) #transpose three 3D axis point into 2D x_3d = cen_3d + [[axis_range],[0],[0],[0]] y_3d = cen_3d + [[0],[axis_range],[0],[0]] z_3d = cen_3d + [[0],[0],[axis_range],[0]] x_2d = np.matmul(cam2d_3d, x_3d) y_2d = np.matmul(cam2d_3d, y_3d) z_2d = np.matmul(cam2d_3d, z_3d) #draw the axis on 2D draw.line((c_x, c_y, x_2d[0], x_2d[1]), fill=(255,255,0), width=5) draw.line((c_x, c_y, y_2d[0], y_2d[1]), fill=(0,255,0), width=5) draw.line((c_x, c_y, z_2d[0], z_2d[1]), fill=(0,0,255), width=5) #g13: show image #img.show() #save file under file img_file_name = '{0}/pred_obj{1}_pic{2}.png'.format(vimg_dir, test_dataset.list_obj[j], which_item) img.save( img_file_name, "PNG" ) img.close()
def main(): class_id = 0 class_file = open('datasets/ycb/dataset_config/classes.txt') cld = {} while 1: class_input = class_file.readline() if not class_input: break input_file = open('{0}/models/{1}/points.xyz'.format( opt.dataset_root, class_input[:-1])) cld[class_id] = [] while 1: input_line = input_file.readline() if not input_line: break input_line = input_line[:-1].split(' ') cld[class_id].append([ float(input_line[0]), float(input_line[1]), float(input_line[2]) ]) cld[class_id] = np.array(cld[class_id]) input_file.close() class_id += 1 opt.manualSeed = random.randint(1, 10000) random.seed(opt.manualSeed) torch.manual_seed(opt.manualSeed) symmetry_obj_idx = [12, 15, 18, 19, 20] if opt.dataset == 'ycb': opt.num_objects = 21 # number of object classes in the dataset opt.num_points = 1000 # number of points on the input pointcloud opt.outf = 'trained_models/ycb/' + opt.output_dir # folder to save trained models opt.test_output = 'experiments/output/ycb/' + opt.output_dir if not os.path.exists(opt.test_output): os.makedirs(opt.test_output, exist_ok=True) opt.repeat_epoch = 1 # number of repeat times for one epoch training elif opt.dataset == 'linemod': opt.num_objects = 13 opt.num_points = 500 opt.outf = 'trained_models/linemod' opt.log_dir = 'experiments/logs/linemod' opt.repeat_epoch = 20 else: print('Unknown dataset') return estimator = PoseNet(num_points=opt.num_points, num_obj=opt.num_objects, object_max=opt.object_max) estimator.cuda() if opt.resume_posenet != '': estimator.load_state_dict( torch.load('{0}/{1}'.format(opt.outf, opt.resume_posenet))) opt.refine_start = False opt.decay_start = False dataset = PoseDataset_ycb('train', opt.num_points, False, opt.dataset_root, opt.noise_trans, opt.seg_type, True) test_dataset = PoseDataset_ycb('test', opt.num_points, False, opt.dataset_root, 0.0, opt.seg_type, True) testdataloader = torch.utils.data.DataLoader(test_dataset, shuffle=False, num_workers=opt.workers) opt.sym_list = dataset.get_sym_list() opt.num_points_mesh = dataset.get_num_points_mesh() print( '>>>>>>>>----------Dataset loaded!---------<<<<<<<<\nlength of the training set: {0}\nlength of the testing set: {1}\nnumber of sample points on mesh: {2}\nsymmetry object list: {3}' .format(len(dataset), len(test_dataset), opt.num_points_mesh, opt.sym_list)) criterion = Loss(opt.num_points_mesh, opt.sym_list) logger = setup_logger( 'final_eval_tf_with_seg_square', os.path.join(opt.test_output, 'final_eval_tf_with_seg_square.txt')) object_max = opt.object_max total_test_dis = {key: [] for key in range(0, object_max)} total_test_count = {key: [] for key in range(0, object_max)} dir_test_dis = {key: [] for key in range(0, object_max)} dir_test_count = {key: [] for key in range(0, object_max)} # for add total_unseen_objects = {key: [] for key in range(0, object_max)} total_object_without_pose = {key: [] for key in range(0, object_max)} dir_add_count = {key: [] for key in range(0, object_max)} dir_add_count_unseen = {key: [] for key in range(0, object_max)} dir_add_02_count_unseen = {key: [] for key in range(0, object_max)} dir_add_pure_count = {key: [] for key in range(0, object_max)} dir_add_s_count = {key: [] for key in range(0, object_max)} dir_add_02_count = {key: [] for key in range(0, object_max)} dir_add_pure_02_count = {key: [] for key in range(0, object_max)} dir_add_s_02_count = {key: [] for key in range(0, object_max)} total_add_count = {key: [] for key in range(0, object_max)} total_add_count_unseen = {key: [] for key in range(0, object_max)} total_add_02_count_unseen = {key: [] for key in range(0, object_max)} total_add_pure_count = {key: [] for key in range(0, object_max)} total_add_s_count = {key: [] for key in range(0, object_max)} total_add_02_count = {key: [] for key in range(0, object_max)} total_add_pure_02_count = {key: [] for key in range(0, object_max)} total_add_s_02_count = {key: [] for key in range(0, object_max)} dir_dbd_count = {key: [] for key in range(0, object_max)} dir_drr_count = {key: [] for key in range(0, object_max)} dir_ada_count = {key: [] for key in range(0, object_max)} dir_distance_1_count = {key: [] for key in range(0, object_max)} total_dbd_count = {key: [] for key in range(0, object_max)} total_drr_count = {key: [] for key in range(0, object_max)} total_ada_count = {key: [] for key in range(0, object_max)} total_distance_1_count = {key: [] for key in range(0, object_max)} last_dis = {key: [] for key in range(0, object_max)} for i in range(object_max): total_unseen_objects[i] = 0 total_object_without_pose[i] = 0 total_test_dis[i] = 0. total_test_count[i] = 0 dir_test_dis[i] = 0. dir_test_count[i] = 0 # for add dir_add_count[i] = 0 dir_add_count_unseen[i] = 0 dir_add_02_count_unseen[i] = 0 dir_add_pure_count[i] = 0 dir_add_s_count[i] = 0 dir_add_02_count[i] = 0 total_add_count[i] = 0 total_add_count_unseen[i] = 0 total_add_02_count_unseen[i] = 0 total_add_pure_count[i] = 0 total_add_s_count[i] = 0 total_add_02_count[i] = 0 dir_add_pure_02_count[i] = 0 dir_add_s_02_count[i] = 0 total_add_pure_02_count[i] = 0 total_add_s_02_count[i] = 0 # for stable dir_dbd_count[i] = 0. dir_drr_count[i] = 0 dir_ada_count[i] = 0. dir_distance_1_count[i] = 0. total_dbd_count[i] = 0. total_drr_count[i] = 0 total_ada_count[i] = 0. total_distance_1_count[i] = 0. last_dis[i] = None st_time = time.time() isFirstInitLastDatafolder = True estimator.eval() with torch.no_grad(): for j, data in enumerate(testdataloader, 0): if opt.dataset == 'ycb': list_points, list_choose, list_img, list_target, list_model_points, list_idx, list_filename, \ list_full_img, list_focal_length, list_principal_point, list_motion = data output_image = Image.open('{0}/{1}-color-masked-square.png'.format( opt.dataset_root, list_filename[0][0])) OUTPUT_IMAGE_PATH = '{0}/{1}-color-seg-square-output-tf.png'.format( opt.dataset_root, list_filename[0][0]) for list_index in range(len(list_points)): points, choose, img, target, model_points, idx, filename, full_img, focal_length, principal_point, motion \ = list_points[list_index], list_choose[list_index], list_img[list_index], \ list_target[list_index], list_model_points[list_index], list_idx[list_index], \ list_filename[list_index], list_full_img[list_index], list_focal_length[list_index], \ list_principal_point[list_index], list_motion[list_index] # Temporal Clean when Changing datafolder datafolder = filename[0].split('/')[1] filehead = filename[0].split('/')[2] if isFirstInitLastDatafolder: lastdatafolder = datafolder isFirstInitLastDatafolder = False if datafolder != lastdatafolder: logger.info('changing folder from {0} to {1}'.format( lastdatafolder, datafolder)) estimator.temporalClear(opt.object_max) # handle dir output for i in range(0, object_max): if dir_test_count[i] != 0: logger.info( 'Dir {0} Object {1} dis:{2} with {3} samples'. format(lastdatafolder, i, dir_test_dis[i] / dir_test_count[i], dir_test_count[i])) if dir_add_count[i] != 0: logger.info( 'Dir {0} Object {1} add:{2} with 0.02: {3}' .format( lastdatafolder, i, dir_add_count[i] / dir_test_count[i], dir_add_02_count[i] / dir_add_count[i])) else: logger.info( 'Dir {0} Object {1} add:{2} with 0.02: {3}' .format( lastdatafolder, i, dir_add_count[i] / dir_test_count[i], 0)) if dir_add_pure_count[i] != -0: logger.info( 'Dir {0} Object {1} add_pure:{2} with 0.02: {3}' .format( lastdatafolder, i, dir_add_pure_count[i] / dir_test_count[i], dir_add_pure_02_count[i] / dir_add_pure_count[i])) else: logger.info( 'Dir {0} Object {1} add_pure:{2} with 0.02: {3}' .format( lastdatafolder, i, dir_add_pure_count[i] / dir_test_count[i], 0)) if dir_add_s_count[i] != 0: logger.info( 'Dir {0} Object {1} add_s:{2} with 0.02: {3}' .format( lastdatafolder, i, dir_add_s_count[i] / dir_test_count[i], dir_add_s_02_count[i] / dir_add_s_count[i])) else: logger.info( 'Dir {0} Object {1} add_s:{2} with 0.02: {3}' .format( lastdatafolder, i, dir_add_s_count[i] / dir_test_count[i], 0)) logger.info('Dir {0} Object {1} dbd:{2}'.format( lastdatafolder, i, dir_dbd_count[i] / dir_test_count[i])) logger.info('Dir {0} Object {1} drr:{2}'.format( lastdatafolder, i, dir_drr_count[i] / dir_test_count[i])) logger.info('Dir {0} Object {1} ada:{2}'.format( lastdatafolder, i, dir_ada_count[i] / dir_test_count[i])) logger.info( 'Dir {0} Object {1} distance_1:{2}'.format( lastdatafolder, i, dir_distance_1_count[i] / dir_test_count[i])) dir_dbd = 0. dir_drr = 0. dir_ada = 0. dir_distance_1 = 0. dir_dis = 0. dir_add = 0 dir_add_s = 0 dir_add_pure = 0 dir_add_02 = 0 dir_add_s_02 = 0 dir_add_pure_02 = 0 dir_count = 0 for i in range(object_max): if total_test_count[i] != 0: dir_count += dir_test_count[i] dir_dis += dir_test_dis[i] dir_add += dir_add_count[i] dir_add_pure += dir_add_pure_count[i] dir_add_s += dir_add_s_count[i] dir_add_02 += dir_add_02_count[i] dir_add_pure_02 += dir_add_pure_02_count[i] dir_add_s_02 += dir_add_s_02_count[i] dir_dbd += dir_dbd_count[i] dir_drr += dir_drr_count[i] dir_ada += dir_ada_count[i] dir_distance_1 += dir_distance_1_count[i] dir_test_dis[i] = 0 dir_test_count[i] = 0 dir_add_count[i] = 0 dir_add_pure_count[i] = 0 dir_add_s_count[i] = 0 dir_add_02_count[i] = 0 dir_add_pure_02_count[i] = 0 dir_add_s_02_count[i] = 0 dir_dbd_count[i] = 0 dir_drr_count[i] = 0 dir_ada_count[i] = 0 dir_distance_1_count[i] = 0 last_dis[i] = None logger.info( 'Dir {0} \'s total dis:{1} with {2} samples'.format( lastdatafolder, dir_dis / dir_count, dir_count)) logger.info( 'Dir {0} \'s total add:{1} with 0.02: {2}'.format( lastdatafolder, dir_add / dir_count, dir_add_02 / dir_add)) logger.info( 'Dir {0} \'s total add_s:{1} with 0.02: {2}'.format( lastdatafolder, dir_add_s / dir_count, dir_add_s_02 / dir_add_s)) logger.info( 'Dir {0} \'s total add_pure:{1} with 0.02: {2}'.format( lastdatafolder, dir_add_pure / dir_count, dir_add_pure_02 / dir_add_pure)) logger.info('Dir {0} \'s total dbd:{1}'.format( lastdatafolder, dir_dbd / dir_count)) logger.info('Dir {0} \'s total drr:{1}'.format( lastdatafolder, dir_drr / dir_count)) logger.info('Dir {0} \'s total ada:{1}'.format( lastdatafolder, dir_ada / dir_count)) logger.info('Dir {0} \'s total distance_1:{1}'.format( lastdatafolder, dir_distance_1 / dir_count)) # end of handle dir output lastdatafolder = datafolder points, choose, img, target, model_points, idx = points.cuda(), \ choose.cuda(), \ img.cuda(), \ target.cuda(), \ model_points.cuda(), \ idx.cuda() cloud_path = "experiments/clouds/ycb/{0}/{1}/{2}/{3}_{4}".format( opt.output_dir, 1, datafolder, filehead, int(idx)) # folder to save logs pred_r, pred_t, pred_c, x_return = estimator( img, points, choose, idx, focal_length, principal_point, motion, cloud_path) # count for unseen object if pred_r is None: last_dis[int(idx)] = None total_unseen_objects[int(idx)] += 1 total_object_without_pose[int(idx)] += 1 continue pred_r_ori = copy.deepcopy(pred_r) pred_t_ori = copy.deepcopy(pred_t) pred_c_ori = copy.deepcopy(pred_c) x_return_ori = copy.deepcopy(x_return) gt_r, gt_t = get_target(opt.dataset_root, filename, idx) if gt_r is None: print('gtr is None') is_sym = int(idx) in symmetry_obj_idx dis, dis_vector, pred_cloud = calDistance( pred_r_ori, pred_t_ori, pred_c_ori, x_return_ori, gt_r, gt_t, cld[int(idx)], is_sym) dis_s, dis_vector_s, _ = calDistance(pred_r_ori, pred_t_ori, pred_c_ori, x_return_ori, gt_r, gt_t, cld[int(idx)], True) dis_pure, dis_vector_pure, _ = calDistance( pred_r_ori, pred_t_ori, pred_c_ori, x_return_ori, gt_r, gt_t, cld[int(idx)], False) if last_dis[int(idx)] is not None: dir_dbd_count[int(idx)] += torch.norm(dis_vector - last_dis[int(idx)]) total_dbd_count[int(idx)] += torch.norm(dis_vector - last_dis[int(idx)]) dir_distance_1_count[int(idx)] += torch.norm( (dis_vector / torch.norm(dis_vector)) - (last_dis[int(idx)] / torch.norm(last_dis[int(idx)]))) total_distance_1_count[int(idx)] += torch.norm( (dis_vector / torch.norm(dis_vector)) - (last_dis[int(idx)] / torch.norm(last_dis[int(idx)]))) if torch.dot(last_dis[int(idx)], dis_vector) < 0: dir_drr_count[int(idx)] += 1 total_drr_count[int(idx)] += 1 dir_ada_count[int(idx)] += torch.acos( (torch.dot(last_dis[int(idx)], dis_vector)) / (torch.norm(last_dis[int(idx)]) * torch.norm(dis_vector))) total_ada_count[int(idx)] += torch.acos( (torch.dot(last_dis[int(idx)], dis_vector)) / (torch.norm(last_dis[int(idx)]) * torch.norm(dis_vector))) last_dis[int(idx)] = dis_vector # calc adds if img.shape[1] != 0: dir_test_dis[int(idx)] += dis.item() total_test_dis[int(idx)] += dis.item() dir_test_count[int(idx)] += 1 total_test_count[int(idx)] += 1 if dis < 0.1: dir_add_count[int(idx)] += 1 total_add_count[int(idx)] += 1 if dis < 0.02: dir_add_02_count[int(idx)] += 1 total_add_02_count[int(idx)] += 1 if dis_s < 0.1: dir_add_s_count[int(idx)] += 1 total_add_s_count[int(idx)] += 1 if dis_s < 0.02: dir_add_s_02_count[int(idx)] += 1 total_add_s_02_count[int(idx)] += 1 if dis_pure < 0.1: dir_add_pure_count[int(idx)] += 1 total_add_pure_count[int(idx)] += 1 if dis_pure < 0.02: dir_add_pure_02_count[int(idx)] += 1 total_add_pure_02_count[int(idx)] += 1 else: last_dis[int(idx)] = None if dis < 0.1: dir_add_count_unseen[int(idx)] += 1 total_add_count_unseen[int(idx)] += 1 total_unseen_objects[int(idx)] += 1 if dis < 0.02: dir_add_02_count_unseen[int(idx)] += 1 total_add_02_count_unseen[int(idx)] += 1 total_unseen_objects[int(idx)] += 1 output_image = output_transformed_image( OUTPUT_IMAGE_PATH, output_image, pred_cloud, focal_length, principal_point, int(idx)) logger.info('Test time {0} Test Frame {1} {2} dis:{3}'.format( time.strftime("%Hh %Mm %Ss", time.gmtime(time.time() - st_time)), filename, idx.item(), dis)) output_image.save(OUTPUT_IMAGE_PATH) # handle dir output for i in range(0, object_max): if dir_test_count[i] != 0: logger.info( 'Dir {0} Object {1} dis:{2} with {3} samples'.format( lastdatafolder, i, dir_test_dis[i] / dir_test_count[i], dir_test_count[i])) if dir_add_count[i] != 0: logger.info( 'Dir {0} Object {1} add:{2} with 0.02: {3}'.format( lastdatafolder, i, dir_add_count[i] / dir_test_count[i], dir_add_02_count[i] / dir_add_count[i])) else: logger.info( 'Dir {0} Object {1} add:{2} with 0.02: {3}'.format( lastdatafolder, i, dir_add_count[i] / dir_test_count[i], 0)) if dir_add_pure_count[i] != -0: logger.info( 'Dir {0} Object {1} add_pure:{2} with 0.02: {3}'. format( lastdatafolder, i, dir_add_pure_count[i] / dir_test_count[i], dir_add_pure_02_count[i] / dir_add_pure_count[i])) else: logger.info( 'Dir {0} Object {1} add_pure:{2} with 0.02: {3}'. format(lastdatafolder, i, dir_add_pure_count[i] / dir_test_count[i], 0)) if dir_add_s_count[i] != 0: logger.info( 'Dir {0} Object {1} add_s:{2} with 0.02: {3}'.format( lastdatafolder, i, dir_add_s_count[i] / dir_test_count[i], dir_add_s_02_count[i] / dir_add_s_count[i])) else: logger.info( 'Dir {0} Object {1} add_s:{2} with 0.02: {3}'.format( lastdatafolder, i, dir_add_s_count[i] / dir_test_count[i], 0)) logger.info('Dir {0} Object {1} dbd:{2}'.format( lastdatafolder, i, dir_dbd_count[i] / dir_test_count[i])) logger.info('Dir {0} Object {1} drr:{2}'.format( lastdatafolder, i, dir_drr_count[i] / dir_test_count[i])) logger.info('Dir {0} Object {1} ada:{2}'.format( lastdatafolder, i, dir_ada_count[i] / dir_test_count[i])) logger.info('Dir {0} Object {1} distance_1:{2}'.format( lastdatafolder, i, dir_distance_1_count[i] / dir_test_count[i])) dir_dbd = 0. dir_drr = 0. dir_ada = 0. dir_distance_1 = 0. dir_dis = 0. dir_add = 0 dir_add_s = 0 dir_add_pure = 0 dir_add_02 = 0 dir_add_s_02 = 0 dir_add_pure_02 = 0 dir_count = 0 for i in range(object_max): if total_test_count[i] != 0: dir_count += dir_test_count[i] dir_dis += dir_test_dis[i] dir_add += dir_add_count[i] dir_add_pure += dir_add_pure_count[i] dir_add_s += dir_add_s_count[i] dir_add_02 += dir_add_02_count[i] dir_add_pure_02 += dir_add_pure_02_count[i] dir_add_s_02 += dir_add_s_02_count[i] dir_dbd += dir_dbd_count[i] dir_drr += dir_drr_count[i] dir_ada += dir_ada_count[i] dir_distance_1 += dir_distance_1_count[i] dir_test_dis[i] = 0 dir_test_count[i] = 0 dir_add_count[i] = 0 dir_add_pure_count[i] = 0 dir_add_s_count[i] = 0 dir_add_02_count[i] = 0 dir_add_pure_02_count[i] = 0 dir_add_s_02_count[i] = 0 dir_dbd_count[i] = 0 dir_drr_count[i] = 0 dir_ada_count[i] = 0 dir_distance_1_count[i] = 0 logger.info('Dir {0} \'s total dis:{1} with {2} samples'.format( lastdatafolder, dir_dis / dir_count, dir_count)) logger.info('Dir {0} \'s total add:{1} with 0.02: {2}'.format( lastdatafolder, dir_add / dir_count, dir_add_02 / dir_add)) logger.info('Dir {0} \'s total add_s:{1} with 0.02: {2}'.format( lastdatafolder, dir_add_s / dir_count, dir_add_s_02 / dir_add_s)) logger.info('Dir {0} \'s total add_pure:{1} with 0.02: {2}'.format( lastdatafolder, dir_add_pure / dir_count, dir_add_pure_02 / dir_add_pure)) logger.info('Dir {0} \'s total dbd:{1}'.format(lastdatafolder, dir_dbd / dir_count)) logger.info('Dir {0} \'s total drr:{1}'.format(lastdatafolder, dir_drr / dir_count)) logger.info('Dir {0} \'s total ada:{1}'.format(lastdatafolder, dir_ada / dir_count)) logger.info('Dir {0} \'s total distance_1:{1}'.format( lastdatafolder, dir_distance_1 / dir_count)) # end of handle dir output # handle global output total_unseen_count = 0 total_without_pose_count = 0 total_add_count_unseen_count = 0 total_add_02_count_unseen_count = 0 total_drr = 0. total_dbd = 0. total_ada = 0. total_distance_1 = 0. total_dis = 0. total_add = 0 total_add_s = 0 total_add_pure = 0 total_add_02 = 0 total_add_s_02 = 0 total_add_pure_02 = 0 total_count = 0 for i in range(object_max): if total_test_count[i] != 0: logger.info( 'Total: Object {0} dis:{1} with {2} samples'.format( i, total_test_dis[i] / total_test_count[i], total_test_count[i])) logger.info('Total: Object {0} add:{1} with 0.02: {2}'.format( i, total_add_count[i] / total_test_count[i], total_add_02_count[i] / total_add_count[i])) logger.info('Total: Object {0} drr:{1}'.format( i, total_drr_count[i] / total_test_count[i])) logger.info('Total: Object {0} ada:{1}'.format( i, total_ada_count[i] / total_test_count[i])) logger.info('Total: Object {0} distance_1:{1}'.format( i, total_distance_1_count[i] / total_test_count[i])) if total_unseen_objects[i] != 0: if total_unseen_objects[i] - total_object_without_pose[ i] != 0: logger.info( 'Total: Unseen Object {0} add:{1} with 0.02: {2} with {3} samples ' .format( i, total_add_count_unseen[i] / (total_unseen_objects[i] - total_object_without_pose[i]), total_add_02_count_unseen[i] / total_add_count_unseen[i], (total_unseen_objects[i] - total_object_without_pose[i]))) logger.info( 'Total: Object {0} unseen :{1} times, {2} of them without poses, success rate:{3}' .format(i, total_unseen_objects[i], total_object_without_pose[i], (total_unseen_objects[i] - total_object_without_pose[i]) / total_unseen_objects[i])) total_unseen_count += total_unseen_objects[i] total_without_pose_count += total_object_without_pose[i] total_count += total_test_count[i] total_dis += total_test_dis[i] total_add += total_add_count[i] total_add_count_unseen_count += total_add_count_unseen[i] total_add_02_count_unseen_count += total_add_02_count_unseen[i] total_add_s += total_add_s_count[i] total_add_pure += total_add_pure_count[i] total_add_02 += total_add_02_count[i] total_add_s_02 += total_add_s_02_count[i] total_add_pure_02 += total_add_pure_02_count[i] total_dbd += total_dbd_count[i] total_drr += total_drr_count[i] total_ada += total_ada_count[i] total_distance_1 += total_distance_1_count[i] logger.info('total dis:{0} with {1} samples'.format( total_dis / total_count, total_count)) logger.info('total add:{0} with 0.02: {1}'.format( total_add / total_count, total_add_02 / total_add)) logger.info('total unseen add:{0} with 0.02: {1}'.format( total_add_count_unseen_count / (total_unseen_count - total_without_pose_count), total_add_02_count_unseen_count / total_add_count_unseen_count)) logger.info('total add_pure:{0} with 0.02: {1}'.format( total_add_pure / total_count, total_add_pure_02 / total_add_pure)) logger.info('total add_s:{0} with 0.02: {1}'.format( total_add_s / total_count, total_add_s_02 / total_add_s)) logger.info( 'detected unseen object :{0}, failed calculate {1} poses with success rate: {2}' .format(total_unseen_count, total_without_pose_count, (total_unseen_count - total_without_pose_count) / total_unseen_count)) logger.info('Total drr:{0}'.format(total_drr / total_count)) logger.info('Total ada:{0}'.format(total_ada / total_count)) logger.info('Total distance_1:{0}'.format(total_distance_1 / total_count))
def main(): opt.manualSeed = random.randint(1, 10000) random.seed(opt.manualSeed) torch.manual_seed(opt.manualSeed) opt.num_objects = 21 opt.num_points = 1000 opt.outf = 'trained_models/ycb/' + opt.output_dir opt.log_dir = 'experiments/logs/ycb/' + opt.output_dir opt.train_dir = 'experiments/tb/ycb/' + opt.output_dir + '/train' opt.test_dir = 'experiments/tb/ycb/' + opt.output_dir + '/test' opt.repeat_epoch = 1 if not os.path.exists(opt.outf): os.makedirs(opt.outf, exist_ok=True) if not os.path.exists(opt.log_dir): os.makedirs(opt.log_dir, exist_ok=True) if not os.path.exists(opt.train_dir): os.makedirs(opt.train_dir, exist_ok=True) if not os.path.exists(opt.test_dir): os.makedirs(opt.test_dir, exist_ok=True) opt.repeat_epoch = 1 estimator = PoseNet(num_points=opt.num_points, num_obj=opt.num_objects, object_max=opt.object_max) estimator.cuda() isFirstInitLastDatafolder = True if opt.resume_posenet != '': psp_estimator = torch.load( 'trained_models/ycb/pose_model_26_0.012863246640872631.pth') pretrained_estimator = torch.load('{0}/{1}'.format( opt.outf, opt.resume_posenet)) estimator_dict = estimator.state_dict() psp_dict = { k: v for k, v in psp_estimator.items() if k.find('cnn.model') == 0 } pretrained_dict = { k: v for k, v in pretrained_estimator.items() if k.find('cnn.model') != 0 } estimator_dict.update(psp_dict) estimator_dict.update(pretrained_dict) estimator.load_state_dict(estimator_dict) else: psp_estimator = torch.load( 'trained_models/ycb/pose_model_26_0.012863246640872631.pth') psp_dict = { k: v for k, v in psp_estimator.items() if k.find('cnn.model') == 0 } estimator_dict = estimator.state_dict() estimator_dict.update(psp_dict) estimator.load_state_dict(estimator_dict) opt.decay_start = False optimizer = optim.Adam(estimator.parameters(), lr=opt.lr) dataset = PoseDataset_ycb('train', opt.num_points, False, opt.dataset_root, opt.noise_trans, 'ori', False) dataloader = torch.utils.data.DataLoader(dataset, shuffle=False, num_workers=opt.workers) test_dataset = PoseDataset_ycb('test', opt.num_points, False, opt.dataset_root, 0.0, 'ori', False) testdataloader = torch.utils.data.DataLoader(test_dataset, shuffle=False, num_workers=opt.workers) opt.sym_list = dataset.get_sym_list() opt.num_points_mesh = dataset.get_num_points_mesh() print( '>>>>>>>>----------Dataset loaded!---------<<<<<<<<\nlength of the training set: {0}\nlength of the testing set: {1}\nnumber of sample points on mesh: {2}\nsymmetry object list: {3}' .format(len(dataset), len(test_dataset), opt.num_points_mesh, opt.sym_list)) criterion = Loss(opt.num_points_mesh, opt.sym_list) dis_vector_last_map = {key: [] for key in range(0, opt.num_objects)} for i in range(0, opt.num_objects): dis_vector_last_map[i] = None best_test = np.Inf if opt.start_epoch == 1: for log in os.listdir(opt.log_dir): os.remove(os.path.join(opt.log_dir, log)) st_time = time.time() for epoch in range(opt.start_epoch, opt.nepoch): logger = setup_logger( 'epoch%d' % epoch, os.path.join(opt.log_dir, 'epoch_%d_log.txt' % epoch)) logger.info('Train time {0}'.format( time.strftime("%Hh %Mm %Ss", time.gmtime(time.time() - st_time)) + ', ' + 'Training started')) train_count = 0 train_dis_avg = 0.0 global_train_dis = 0.0 estimator.train() optimizer.zero_grad() for rep in range(opt.repeat_epoch): for i, data in enumerate(dataloader, 0): list_points, list_choose, list_img, list_target, list_model_points, list_idx, list_filename, \ list_full_img, list_focal_length, list_principal_point, list_motion = data for list_index in range(len(list_points)): if opt.dataset == 'ycb': points, choose, img, target, model_points, idx, filename, full_img, focal_length, principal_point \ , motion = list_points[list_index], list_choose[list_index], list_img[list_index], \ list_target[list_index], list_model_points[list_index], list_idx[list_index], \ list_filename[list_index], list_full_img[list_index], list_focal_length[ list_index], \ list_principal_point[list_index], list_motion[list_index] datafolder = filename[0].split('/')[1] if isFirstInitLastDatafolder: lastdatafolder = datafolder isFirstInitLastDatafolder = False if datafolder != lastdatafolder: for i in range(0, opt.num_objects): dis_vector_last_map[i] = None optimizer.step() optimizer.zero_grad() train_dis_avg = 0 estimator.temporalClear(opt.object_max, opt.mem_length) lastdatafolder = datafolder elif opt.dataset == 'linemod': list_points, list_choose, list_img, list_target, list_model_points, list_idx, list_filename = data points, choose, img, target, model_points, idx, filename = list_points[ 0] points, choose, img, target, model_points, idx = points.cuda(), \ choose.cuda(), \ img.cuda(), \ target.cuda(), \ model_points.cuda(), \ idx.cuda() pred_r, pred_t, pred_c, x_return = estimator( img, points, choose, idx, focal_length, principal_point, motion, True) loss, dis, new_points, new_target, dis_vector = criterion( pred_r, pred_t, pred_c, dis_vector_last_map[idx.item()], target, model_points, idx, x_return, opt.w, False, float(opt.loss_stable_alpha)) dis_vector_last_map[idx.item()] = dis_vector loss.backward(retain_graph=True) logger.info( 'Train time {0} Frame {1} Object {2}, Loss = {3}'. format( time.strftime("%Hh %Mm %Ss", time.gmtime(time.time() - st_time)), filename, idx.item(), dis)) train_dis_avg += dis.item() global_train_dis += dis.item() train_count += 1 if train_count % (len(list_points) * opt.batch_size) == 0: logger.info( 'Train time {0} Epoch {1} Batch {2} Frame {3} Avg_dis:{4}' .format( time.strftime( "%Hh %Mm %Ss", time.gmtime(time.time() - st_time)), epoch, int(train_count / opt.batch_size), train_count, train_dis_avg / (len(list_points) * opt.batch_size))) optimizer.step() optimizer.zero_grad() train_dis_avg = 0 if train_count != 0 and train_count % 1000 == 0: torch.save( estimator.state_dict(), '{0}/pose_model_current.pth'.format(opt.outf)) print( '>>>>>>>>----------epoch {0} train finish---------<<<<<<<<'.format( epoch)) global_train_dis = 0.0 logger = setup_logger( 'epoch%d_test' % epoch, os.path.join(opt.log_dir, 'epoch_%d_test_log.txt' % epoch)) logger.info('Test time {0}'.format( time.strftime("%Hh %Mm %Ss", time.gmtime(time.time() - st_time)) + ', ' + 'Testing started')) test_dis = 0.0 test_count = 0 estimator.eval() for i in range(0, opt.num_objects): dis_vector_last_map[i] = None with torch.no_grad(): isFirstInitLastDatafolder = True for j, data in enumerate(testdataloader, 0): if opt.dataset == 'ycb': list_points, list_choose, list_img, list_target, list_model_points, list_idx, list_filename, \ list_full_img, list_focal_length, list_principal_point, list_motion = data for list_index in range(len(list_points)): points, choose, img, target, model_points, idx, filename, full_img, focal_length, principal_point, motion \ = list_points[list_index], list_choose[list_index], list_img[list_index], \ list_target[list_index], list_model_points[list_index], list_idx[list_index], \ list_filename[list_index], list_full_img[list_index], list_focal_length[list_index], \ list_principal_point[list_index], list_motion[list_index] datafolder = filename[0].split('/')[1] filehead = filename[0].split('/')[2] if isFirstInitLastDatafolder: lastdatafolder = datafolder isFirstInitLastDatafolder = False if datafolder != lastdatafolder: train_dis_avg = 0 estimator.temporalClear(opt.object_max) lastdatafolder = datafolder points, choose, img, target, model_points, idx = points.cuda(), \ choose.cuda(), \ img.cuda(), \ target.cuda(), \ model_points.cuda(), \ idx.cuda() cloud_path = "experiments/clouds/ycb/{0}/{1}/{2}/{3}_{4}".format( opt.output_dir, epoch, datafolder, filehead, int(idx)) # folder to save logs if not os.path.exists( "experiments/clouds/ycb/{0}/{1}/{2}".format( opt.output_dir, epoch, datafolder)): os.makedirs( "experiments/clouds/ycb/{0}/{1}/{2}".format( opt.output_dir, epoch, datafolder), exist_ok=True) pred_r, pred_t, pred_c, x_return = estimator( img, points, choose, idx, focal_length, principal_point, motion, cloud_path) _, dis, new_points, new_target, dis_vector = criterion( pred_r, pred_t, pred_c, dis_vector_last_map[idx.item()], target, model_points, idx, x_return, opt.w, opt.refine_start, float(opt.loss_stable_alpha)) dis_vector_last_map[idx.item()] = dis_vector test_dis += dis.item() logger.info( 'Test time {0} Test Frame No.{1} {2} {3} dis:{4}'. format( time.strftime("%Hh %Mm %Ss", time.gmtime(time.time() - st_time)), test_count, filename, idx.item(), dis)) test_count += 1 test_dis = test_dis / test_count logger.info('Test time {0} Epoch {1} TEST FINISH Avg dis: {2}'.format( time.strftime("%d %Hh %Mm %Ss", time.gmtime(time.time() - st_time)), epoch, test_dis)) if test_dis <= best_test: best_test = test_dis torch.save( estimator.state_dict(), '{0}/pose_model_ori_{1}_{2}.pth'.format( opt.outf, epoch, test_dis)) print(epoch, '>>>>>>>>----------BEST TEST MODEL SAVED---------<<<<<<<<') if best_test < opt.decay_margin and not opt.decay_start: opt.decay_start = True opt.lr *= opt.lr_rate opt.w *= opt.w_rate optimizer = optim.Adam(estimator.parameters(), lr=opt.lr)
def main(): # opt.manualSeed = random.randint(1, 10000) # # opt.manualSeed = 1 # random.seed(opt.manualSeed) # torch.manual_seed(opt.manualSeed) torch.set_printoptions(threshold=5000) # device_ids = [0,1] cudnn.benchmark = True if opt.dataset == 'ycb': opt.num_objects = 21 #number of object classes in the dataset opt.num_points = 1000 #number of points on the input pointcloud opt.outf = 'trained_models/ycb' #folder to save trained models opt.log_dir = 'experiments/logs/ycb' #folder to save logs opt.repeat_epoch = 3 #number of repeat times for one epoch training elif opt.dataset == 'linemod': opt.num_objects = 13 opt.num_points = 500 opt.outf = 'trained_models/linemod' opt.log_dir = 'experiments/logs/linemod' opt.repeat_epoch = 20 else: print('Unknown dataset') return estimator = PoseNet(num_points=opt.num_points, num_obj=opt.num_objects) estimator.cuda() refiner = PoseRefineNet(num_points=opt.num_points, num_obj=opt.num_objects) refiner.cuda() # estimator = nn.DataParallel(estimator, device_ids=device_ids) if opt.resume_posenet != '': estimator.load_state_dict( torch.load('{0}/{1}'.format(opt.outf, opt.resume_posenet))) if opt.resume_refinenet != '': refiner.load_state_dict( torch.load('{0}/{1}'.format(opt.outf, opt.resume_refinenet))) opt.refine_start = True opt.decay_start = True opt.lr *= opt.lr_rate opt.w *= opt.w_rate opt.batch_size = int(opt.batch_size / opt.iteration) optimizer = optim.Adam(refiner.parameters(), lr=opt.lr) else: print('no refinement') opt.refine_start = False opt.decay_start = False optimizer = optim.Adam(estimator.parameters(), lr=opt.lr) # optimizer = nn.DataParallel(optimizer, device_ids=device_ids) if opt.dataset == 'ycb': dataset = PoseDataset_ycb('train', opt.num_points, False, opt.dataset_root, opt.noise_trans, opt.refine_start) # print(dataset.list) elif opt.dataset == 'linemod': dataset = PoseDataset_linemod('train', opt.num_points, True, opt.dataset_root, opt.noise_trans, opt.refine_start) dataloader = torch.utils.data.DataLoader(dataset, batch_size=1, shuffle=True, num_workers=opt.workers) if opt.dataset == 'ycb': test_dataset = PoseDataset_ycb('test', opt.num_points, False, opt.dataset_root, 0.0, opt.refine_start) elif opt.dataset == 'linemod': test_dataset = PoseDataset_linemod('test', opt.num_points, False, opt.dataset_root, 0.0, opt.refine_start) testdataloader = torch.utils.data.DataLoader(test_dataset, batch_size=1, shuffle=False, num_workers=opt.workers) opt.sym_list = dataset.get_sym_list() opt.num_points_mesh = dataset.get_num_points_mesh() # print('>>>>>>>>----------Dataset loaded!---------<<<<<<<<\nlength of the training set: {0}\nlength of the testing set: {1}\nnumber of sample points on mesh: {2}\nsymmetry object list: {3}'.format(len(dataset), len(test_dataset), opt.num_points_mesh, opt.sym_list)) criterion = Loss(opt.num_points_mesh, opt.sym_list) # criterion_refine = Loss_refine(opt.num_points_mesh, opt.sym_list) best_test = np.Inf best_epoch = 0 if opt.start_epoch == 1: for log in os.listdir(opt.log_dir): os.remove(os.path.join(opt.log_dir, log)) st_time = time.time() count_gen = 0 mode = 1 if mode == 1: for epoch in range(opt.start_epoch, opt.nepoch): logger = setup_logger( 'epoch%d' % epoch, os.path.join(opt.log_dir, 'epoch_%d_log.txt' % epoch)) logger.info('Train time {0}'.format( time.strftime("%Hh %Mm %Ss", time.gmtime(time.time() - st_time)) + ', ' + 'Training started')) train_count = 0 train_dis_avg = 0.0 if opt.refine_start: estimator.eval() refiner.train() else: estimator.train() optimizer.zero_grad() for rep in range(opt.repeat_epoch): for i, data in enumerate(dataloader, 0): points, choose, img, target_sym, target_cen, idx, file_list_idx = data if idx is 9 or idx is 16: continue # points, choose, img, target_sym, target_cen, target, idx, file_list_idx = data # generate_obj_file(target_sym, target_cen, target, idx.squeeze()) # import pdb;pdb.set_trace() points, choose, img, target_sym, target_cen, idx = Variable(points).cuda(), \ Variable(choose).cuda(), \ Variable(img).cuda(), \ Variable(target_sym).cuda(), \ Variable(target_cen).cuda(), \ Variable(idx).cuda() # points, choose, img, target_sym, target_cen, idx = Variable(points), \ # Variable(choose), \ # Variable(img), \ # Variable(target_sym), \ # Variable(target_cen), \ # Variable(idx) pred_norm, pred_on_plane, emb = estimator( img, points, choose, idx) # pred_norm_new = torch.cat((pred_norm, torch.zeros(1,pred_norm.size(1),1)),2) # for i in range(pred_norm.size(1)): # pred_norm_new[0,i,2] = torch.sqrt(1 - pred_norm[0,i,0] * pred_norm[0,i,0] - pred_norm[0,i,1] * pred_norm[0,i,1]) # if epoch % 10 == 0: # generate_obj_file_pred(pred_norm, pred_on_plane, points, count_gen, idx) # count_gen += 1 # print(pred_norm[0,0,:]) loss = criterion(pred_norm, pred_on_plane, target_sym, target_cen, idx, points, opt.w, opt.refine_start) # scene_idx = dataset.list[file_list_idx] loss.backward() # train_dis_avg += dis.item() train_count += 1 if train_count % opt.batch_size == 0: logger.info( 'Train time {0} Epoch {1} Batch {2} Frame {3}'. format( time.strftime( "%Hh %Mm %Ss", time.gmtime(time.time() - st_time)), epoch, int(train_count / opt.batch_size), train_count)) optimizer.step() # for param_lr in optimizer.module.param_groups: # param_lr['lr'] /= 2 optimizer.zero_grad() train_dis_avg = 0 if train_count % 5000 == 0: print(pred_on_plane.max()) print(pred_on_plane.mean()) if train_count != 0 and train_count % 1000 == 0: if opt.refine_start: torch.save( refiner.state_dict(), '{0}/pose_refine_model_current.pth'.format( opt.outf)) else: torch.save( estimator.state_dict(), '{0}/pose_model_current.pth'.format(opt.outf)) print('>>>>>>>>----------epoch {0} train finish---------<<<<<<<<'. format(epoch)) logger = setup_logger( 'epoch%d_test' % epoch, os.path.join(opt.log_dir, 'epoch_%d_test_log.txt' % epoch)) logger.info('Test time {0}'.format( time.strftime("%Hh %Mm %Ss", time.gmtime(time.time() - st_time)) + ', ' + 'Testing started')) test_loss = 0.0 test_count = 0 estimator.eval() # refiner.eval() # for rep in range(opt.repeat_epoch): # for j, data in enumerate(testdataloader, 0): # points, choose, img, target_sym, target_cen, idx, img_idx = data # # points, choose, img, target, model_points, idx = Variable(points).cuda(), \ # # Variable(choose).cuda(), \ # # Variable(img).cuda(), \ # # Variable(target).cuda(), \ # # Variable(model_points).cuda(), \ # # Variable(idx).cuda() # points, choose, img, target_sym, target_cen, idx = Variable(points), \ # Variable(choose), \ # Variable(img), \ # Variable(target_sym), \ # Variable(target_cen), \ # Variable(idx) # pred_norm, pred_on_plane, emb = estimator(img, points, choose, idx) # loss = criterion(pred_norm, pred_on_plane, target_sym, target_cen, idx, points, opt.w, opt.refine_start) # test_loss += loss # logger.info('Test time {0} Test Frame No.{1}'.format(time.strftime("%Hh %Mm %Ss", time.gmtime(time.time() - st_time)), test_count)) # test_count += 1 # test_loss = test_loss / test_count logger.info( 'Test time {0} Epoch {1} TEST FINISH Avg dis: {2}'.format( time.strftime("%Hh %Mm %Ss", time.gmtime(time.time() - st_time)), epoch, test_loss)) print(pred_on_plane.max()) print(pred_on_plane.mean()) bs, num_p, _ = pred_on_plane.size() # if epoch % 40 == 0: # import pdb;pdb.set_trace() best_test = test_loss best_epoch = epoch if opt.refine_start: torch.save( refiner.state_dict(), '{0}/pose_refine_model_{1}_{2}.pth'.format( opt.outf, epoch, test_loss)) else: torch.save( estimator.state_dict(), '{0}/pose_model_{1}_{2}.pth'.format( opt.outf, epoch, test_loss)) print(epoch, '>>>>>>>>----------BEST TEST MODEL SAVED---------<<<<<<<<') if best_test < opt.decay_margin and not opt.decay_start: opt.decay_start = True opt.lr *= opt.lr_rate # opt.w *= opt.w_rate optimizer = optim.Adam(estimator.parameters(), lr=opt.lr) estimator.load_state_dict( torch.load('{0}/pose_model_{1}_{2}.pth'.format( opt.outf, best_epoch, best_test))) else: estimator.load_state_dict( torch.load('{0}/pose_model_11_0.0.pth'.format(opt.outf))) product_list = [] dist_list = [] true_positives = 0 false_positives = 0 false_negatives = 0 for index in range(len(test_dataset.list)): img = Image.open('{0}/data_v1/{1}-color.png'.format( test_dataset.root, test_dataset.list[index])) depth = np.array( Image.open('{0}/data_v1/{1}-depth.png'.format( test_dataset.root, test_dataset.list[index]))) label = np.array( Image.open('{0}/data_v1/{1}-label.png'.format( test_dataset.root, test_dataset.list[index]))) meta = scio.loadmat('{0}/data_v1/{1}-meta.mat'.format( test_dataset.root, test_dataset.list[index])) cam_cx = test_dataset.cam_cx_1 cam_cy = test_dataset.cam_cy_1 cam_fx = test_dataset.cam_fx_1 cam_fy = test_dataset.cam_fy_1 mask_back = ma.getmaskarray(ma.masked_equal(label, 0)) obj = meta['cls_indexes'].flatten().astype(np.int32) for idx in range(0, len(obj)): print('object index: ', obj[idx]) mask_depth = ma.getmaskarray(ma.masked_not_equal(depth, 0)) mask_label = ma.getmaskarray(ma.masked_equal(label, obj[idx])) mask = mask_label * mask_depth if not (len(mask.nonzero()[0]) > test_dataset.minimum_num_pt and len(test_dataset.symmetry[obj[idx]]['mirror']) > 0): continue rmin, rmax, cmin, cmax = get_bbox(mask_label) img_temp = np.transpose(np.array(img)[:, :, :3], (2, 0, 1))[:, rmin:rmax, cmin:cmax] img_masked = img_temp target_r = meta['poses'][:, :, idx][:, 0:3] target_t = np.array(meta['poses'][:, :, idx][:, 3:4].flatten()) add_t = np.array([ random.uniform(-test_dataset.noise_trans, test_dataset.noise_trans) for i in range(3) ]) choose = mask[rmin:rmax, cmin:cmax].flatten().nonzero()[0] if len(choose) > test_dataset.num_pt: c_mask = np.zeros(len(choose), dtype=int) c_mask[:test_dataset.num_pt] = 1 np.random.shuffle(c_mask) choose = choose[c_mask.nonzero()] else: choose = np.pad(choose, (0, test_dataset.num_pt - len(choose)), 'wrap') depth_masked = depth[ rmin:rmax, cmin:cmax].flatten()[choose][:, np.newaxis].astype(np.float32) xmap_masked = test_dataset.xmap[ rmin:rmax, cmin:cmax].flatten()[choose][:, np.newaxis].astype(np.float32) ymap_masked = test_dataset.ymap[ rmin:rmax, cmin:cmax].flatten()[choose][:, np.newaxis].astype(np.float32) choose = np.array([choose]) cam_scale = meta['factor_depth'][0][0] pt2 = depth_masked / cam_scale pt0 = (ymap_masked - cam_cx) * pt2 / cam_fx pt1 = (xmap_masked - cam_cy) * pt2 / cam_fy cloud = np.concatenate((pt0, pt1, pt2), axis=1) dellist = [j for j in range(0, len(test_dataset.cld[obj[idx]]))] # dellist = random.sample(dellist, len(test_dataset.cld[obj[idx]]) - test_dataset.num_pt_mesh_small) # model_points = np.delete(test_dataset.cld[obj[idx]], dellist, axis=0) model_points = test_dataset.cld[obj[idx]] target_sym = [] for sym in test_dataset.symmetry[obj[idx]]['mirror']: target_sym.append(np.dot(sym, target_r.T)) target_sym = np.array(target_sym) target_cen = np.add(test_dataset.symmetry[obj[idx]]['center'], target_t) target = np.dot(model_points, target_r.T) target = np.add(target, target_t) print('ground truth norm: ', target_sym) print('ground truth center: ', target_cen) points_ten, choose_ten, img_ten, target_sym_ten, target_cen_ten, target_ten, idx_ten = \ torch.from_numpy(cloud.astype(np.float32)).unsqueeze(0), \ torch.LongTensor(choose.astype(np.int32)).unsqueeze(0), \ test_dataset.norm(torch.from_numpy(img_masked.astype(np.float32))).unsqueeze(0), \ torch.from_numpy(target_sym.astype(np.float32)).unsqueeze(0), \ torch.from_numpy(target_cen.astype(np.float32)).unsqueeze(0), \ torch.from_numpy(target.astype(np.float32)).unsqueeze(0), \ torch.LongTensor([obj[idx]-1]).unsqueeze(0) # print(img_ten.size()) # print(points_ten.size()) # print(choose_ten.size()) # print(idx_ten.size()) points_ten, choose_ten, img_ten, target_sym_ten, target_cen_ten, idx_ten = Variable(points_ten).cuda(), \ Variable(choose_ten).cuda(), \ Variable(img_ten).cuda(), \ Variable(target_sym_ten).cuda(), \ Variable(target_cen_ten).cuda(), \ Variable(idx_ten).cuda() pred_norm, pred_on_plane, emb = estimator(img_ten, points_ten, choose_ten, idx_ten) # import pdb;pdb.set_trace() bs, num_p, _ = pred_on_plane.size() # pred_norm = torch.cat((pred_norm, torch.zeros(1,pred_norm.size(1),1)),2) # for i in range(pred_norm.size(1)): # pred_norm[0,i,2] = torch.sqrt(1 - pred_norm[0,i,0] * pred_norm[0,i,0] - pred_norm[0,i,1] * pred_norm[0,i,1]) # pred_norm = pred_norm / (torch.norm(pred_norm, dim=2).view(bs, num_p, 1)) generate_obj_file_norm_pred( pred_norm / (torch.norm(pred_norm, dim=2).view(bs, num_p, 1)), pred_on_plane, points_ten, test_dataset.list[index].split('/')[0], test_dataset.list[index].split('/')[1], obj[idx]) loss = criterion(pred_norm, pred_on_plane, target_sym_ten, target_cen_ten, idx, points_ten, opt.w, opt.refine_start) # print('test loss: ', loss) # bs, num_p, _ = pred_on_plane.size() pred_norm = pred_norm / (torch.norm(pred_norm, dim=2).view( bs, num_p, 1)) pred_norm = pred_norm.cpu().detach().numpy() pred_on_plane = pred_on_plane.cpu().detach().numpy() points = points_ten.cpu().detach().numpy() clustering_points_idx = np.where( pred_on_plane > pred_on_plane.max() * PRED_ON_PLANE_FACTOR + pred_on_plane.mean() * (1 - PRED_ON_PLANE_FACTOR))[1] clustering_norm = pred_norm[0, clustering_points_idx, :] clustering_points = points[0, clustering_points_idx, :] num_points = len(clustering_points_idx) # import pdb;pdb.set_trace() close_thresh = 5e-3 broad_thresh = 7e-3 sym_flag = [0 for i in range(target_sym.shape[0])] sym_max_product = [0.0 for i in range(target_sym.shape[0])] sym_dist = [0.0 for i in range(target_sym.shape[0])] count_pred = 0 while True: if num_points == 0: break count_pred += 1 if count_pred > target_sym.shape[0]: break best_fit_num = 0 count_try = 0 while True: if count_try > 3 or num_points <= 1: break pick_idx = np.random.randint(0, num_points - 1) pick_point = clustering_points[pick_idx] # proposal_norm = np.array(Plane(Point3D(pick_points[0]),Point3D(pick_points[1]),Point3D(pick_points[2])).normal_vector).astype(np.float32) proposal_norm = clustering_norm[pick_idx] proposal_norm = proposal_norm[:, np.newaxis] # import pdb;pdb.set_trace() proposal_point = pick_point # highest_pred_idx = np.argmax(pred_on_plane[0,clustering_points_idx,:]) # highest_pred_loc = clustering_points[highest_pred_idx] # proposal_norm = clustering_norm[highest_pred_idx][:,np.newaxis] clustering_diff = clustering_points - proposal_point clustering_dist = np.abs( np.matmul(clustering_diff, proposal_norm)) broad_inliers = np.where(clustering_dist < broad_thresh)[0] broad_inlier_num = len(broad_inliers) close_inliers = np.where(clustering_dist < close_thresh)[0] close_inlier_num = len(close_inliers) if broad_inlier_num > num_points / (5 - count_pred): best_fit_num = close_inlier_num best_fit_norm = proposal_norm best_fit_cen = clustering_points[close_inliers].mean(0) best_fit_idx = clustering_points_idx[close_inliers] scrub_idx = clustering_points_idx[broad_inliers] break else: count_try += 1 # else: # np.delete(clustering_points_idx, highest_pred_idx) # num_points -= 1 if count_try > 3 or num_points <= 1: break for i in range(2): def f(x): dist = 0 x = x / LA.norm(x) for point in clustering_points[broad_inliers]: dist += np.abs(point[0] * x[0] + point[1] * x[1] + point[2] * np.sqrt(1 - x[0] * x[0] - x[1] * x[1]) + x[2]) return dist start_point = np.copy(proposal_norm) start_point[2] = (-proposal_point * proposal_norm[:, 0]).sum() min_point = fmin(f, start_point) new_pred_loc = np.array([ 0, 0, -min_point[2] / np.sqrt(1 - min_point[0] * min_point[0] - min_point[1] * min_point[1]) ]) min_point[2] = np.sqrt(1 - min_point[0] * min_point[0] - min_point[1] * min_point[1]) new_proposal_norm = min_point clustering_diff = clustering_points - new_pred_loc clustering_dist = np.abs( np.matmul(clustering_diff, new_proposal_norm)) close_inliers = np.where(clustering_dist < close_thresh)[0] new_close_inlier_num = len(close_inliers) broad_inliers = np.where(clustering_dist < broad_thresh)[0] new_broad_inlier_num = len(broad_inliers) # import pdb;pdb.set_trace() if new_close_inlier_num > close_inlier_num: best_fit_num = new_close_inlier_num # proposal_point = clustering_points_idx[clustering_dist.argmin()] proposal_point = new_pred_loc best_fit_norm = new_proposal_norm[:, np.newaxis] best_fit_idx = clustering_points_idx[close_inliers] scrub_idx = clustering_points_idx[broad_inliers] best_fit_cen = new_pred_loc inlier_num = new_inlier_num proposal_norm = best_fit_norm # other_idx_pick = other_idx[other_idx_pick] # if len(other_idx_pick) > num_points//6: # pick_idx = np.concatenate((pick_idx, other_idx_pick), 0) # norm_proposal_new = clustering_norm[pick_idx,:].mean(0) # norm_proposal_new = norm_proposal_new / LA.norm(norm_proposal_new) # inlier_num_new = len(np.where(np.abs(clustering_norm-norm_proposal_new).sum(1) < thresh)[0]) # if inlier_num_new > inlier_num: # best_fit_num = inlier_num_new # best_fit_idx = np.where(np.abs(clustering_norm-norm_proposal_new).sum(1) < thresh_scrap) # best_fit_norm = norm_proposal_new # best_fit_cen = clustering_points[best_fit_idx].mean(0) if best_fit_num == 0: break else: print('predicted norm:{}, predicted point:{}'.format( best_fit_norm, best_fit_cen)) max_idx = np.argmax(np.matmul(target_sym, best_fit_norm)) sym_flag[max_idx] += 1 sym_product = np.abs((target_sym[max_idx] * (best_fit_cen - target_cen)).sum()) if sym_max_product[max_idx] < sym_product: sym_max_product[max_idx] = sym_product sym_dist[max_idx] = np.matmul(target_sym, best_fit_norm)[max_idx] # generate_obj_file_sym_pred(best_fit_norm, best_fit_cen, target_ten, test_dataset.list[index].split('/')[0], test_dataset.list[index].split('/')[1], obj[idx], count_pred) # import pdb;pdb.set_trace() clustering_points_idx = np.setdiff1d( clustering_points_idx, scrub_idx) clustering_norm = pred_norm[0, clustering_points_idx, :] clustering_points = points[0, clustering_points_idx, :] num_points = len(clustering_points_idx) for i in range(target_sym.shape[0]): if sym_flag[i] >= 1: dist_list.append(sym_dist[i]) product_list.append(sym_max_product[i]) false_positives += sym_flag[i] - 1 else: false_negatives += 1 product_list = np.array(product_list) dist_list = np.array(dist_list) # import pdb;pdb.set_trace() total_num = len(product_list) prec = [] recall = [] for t in range(1000): good_ones = len( np.logical_and(dist_list < 0.5 * t / 1000, product_list > math.cos(math.pi * 0.25 * t / 1000))) prec.append(good_ones * 1.0 / (false_positives + total_num)) recall.append(good_ones * 1.0 / (good_ones + false_negatives)) print(prec) print(recall) plt.plot(recall, prec, 'r') plt.axis([0, 1, 0, 1]) plt.savefig('prec-recall.png')
def main(): opt.manualSeed = random.randint(1, 10000) random.seed(opt.manualSeed) torch.manual_seed(opt.manualSeed) opt.num_objects = 21 #number of object classes in the dataset opt.num_points = 1000 #number of points on the input pointcloud opt.outf = 'trained_models/ycb_rot' #folder to save trained models opt.log_dir = 'experiments/logs/ycb_rot' #folder to save logs opt.repeat_epoch = 1 #number of repeat times for one epoch training estimator = PoseNet(num_points=opt.num_points, num_obj=opt.num_objects) estimator.cuda() refiner = PoseRefineNet(num_points=opt.num_points, num_obj=opt.num_objects) refiner.cuda() if opt.resume_posenet != '': estimator.load_state_dict( torch.load('{0}/{1}'.format(opt.outf, opt.resume_posenet))) if opt.resume_refinenet != '': refiner.load_state_dict( torch.load('{0}/{1}'.format(opt.outf, opt.resume_refinenet))) opt.refine_start = True opt.decay_start = True opt.lr *= opt.lr_rate opt.w *= opt.w_rate opt.batch_size = int(opt.batch_size / opt.iteration) optimizer = optim.Adam(refiner.parameters(), lr=opt.lr) else: opt.refine_start = False opt.decay_start = False optimizer = optim.Adam(estimator.parameters(), lr=opt.lr) object_list = list(range(1, 22)) output_format = [ otypes.DEPTH_POINTS_MASKED_AND_INDEXES, otypes.IMAGE_CROPPED, otypes.MODEL_POINTS_TRANSFORMED, otypes.MODEL_POINTS, otypes.OBJECT_LABEL, ] dataset = YCBDataset(opt.dataset_root, mode='train_syn_grid_valid', object_list=object_list, output_data=output_format, resample_on_error=True, preprocessors=[ YCBOcclusionAugmentor(opt.dataset_root), ColorJitter(), InplaneRotator() ], postprocessors=[ImageNormalizer(), PointShifter()], refine=opt.refine_start, image_size=[640, 480], num_points=1000) dataloader = torch.utils.data.DataLoader(dataset, batch_size=1, shuffle=True, num_workers=opt.workers - 1) test_dataset = YCBDataset(opt.dataset_root, mode='valid', object_list=object_list, output_data=output_format, resample_on_error=True, preprocessors=[], postprocessors=[ImageNormalizer()], refine=opt.refine_start, image_size=[640, 480], num_points=1000) testdataloader = torch.utils.data.DataLoader(test_dataset, shuffle=True, batch_size=1, num_workers=1) opt.sym_list = [12, 15, 18, 19, 20] opt.num_points_mesh = dataset.num_pt_mesh_small print( '>>>>>>>>----------Dataset loaded!---------<<<<<<<<\nlength of the training set: {0}\nlength of the testing set: {1}\nnumber of sample points on mesh: {2}\nsymmetry object list: {3}' .format(len(dataset), len(test_dataset), opt.num_points_mesh, opt.sym_list)) criterion = Loss(opt.num_points_mesh, opt.sym_list) criterion_refine = Loss_refine(opt.num_points_mesh, opt.sym_list) best_test = np.Inf if opt.start_epoch == 1: for log in os.listdir(opt.log_dir): os.remove(os.path.join(opt.log_dir, log)) st_time = time.time() for epoch in range(opt.start_epoch, opt.nepoch): logger = setup_logger( 'epoch%d' % epoch, os.path.join(opt.log_dir, 'epoch_%d_log.txt' % epoch)) logger.info('Train time {0}'.format( time.strftime("%Hh %Mm %Ss", time.gmtime(time.time() - st_time)) + ', ' + 'Training started')) train_count = 0 train_dis_avg = 0.0 if opt.refine_start: estimator.eval() refiner.train() else: estimator.train() optimizer.zero_grad() for rep in range(opt.repeat_epoch): for i, data in enumerate(dataloader, 0): points, choose, img, target, model_points, idx = data idx = idx - 1 points, choose, img, target, model_points, idx = Variable(points).cuda(), \ Variable(choose).cuda(), \ Variable(img).cuda(), \ Variable(target).cuda(), \ Variable(model_points).cuda(), \ Variable(idx).cuda() pred_r, pred_t, pred_c, emb = estimator( img, points, choose, idx) loss, dis, new_points, new_target = criterion( pred_r, pred_t, pred_c, target, model_points, idx, points, opt.w, opt.refine_start) if opt.refine_start: for ite in range(0, opt.iteration): pred_r, pred_t = refiner(new_points, emb, idx) dis, new_points, new_target = criterion_refine( pred_r, pred_t, new_target, model_points, idx, new_points) dis.backward() else: loss.backward() train_dis_avg += dis.item() train_count += 1 if train_count % opt.batch_size == 0: logger.info( 'Train time {0} Epoch {1} Batch {2} Frame {3} Avg_dis:{4}' .format( time.strftime("%Hh %Mm %Ss", time.gmtime(time.time() - st_time)), epoch, int(train_count / opt.batch_size), train_count, train_dis_avg / opt.batch_size)) optimizer.step() optimizer.zero_grad() train_dis_avg = 0 if train_count != 0 and train_count % 1000 == 0: if opt.refine_start: torch.save( refiner.state_dict(), '{0}/pose_refine_model_current.pth'.format( opt.outf)) else: torch.save( estimator.state_dict(), '{0}/pose_model_current.pth'.format(opt.outf)) if (train_count >= 100000): break print( '>>>>>>>>----------epoch {0} train finish---------<<<<<<<<'.format( epoch)) logger = setup_logger( 'epoch%d_test' % epoch, os.path.join(opt.log_dir, 'epoch_%d_test_log.txt' % epoch)) logger.info('Test time {0}'.format( time.strftime("%Hh %Mm %Ss", time.gmtime(time.time() - st_time)) + ', ' + 'Testing started')) test_dis = 0.0 test_count = 0 estimator.eval() refiner.eval() for j, data in enumerate(testdataloader, 0): points, choose, img, target, model_points, idx = data idx = idx - 1 points, choose, img, target, model_points, idx = Variable(points).cuda(), \ Variable(choose).cuda(), \ Variable(img).cuda(), \ Variable(target).cuda(), \ Variable(model_points).cuda(), \ Variable(idx).cuda() pred_r, pred_t, pred_c, emb = estimator(img, points, choose, idx) _, dis, new_points, new_target = criterion(pred_r, pred_t, pred_c, target, model_points, idx, points, opt.w, opt.refine_start) if opt.refine_start: for ite in range(0, opt.iteration): pred_r, pred_t = refiner(new_points, emb, idx) dis, new_points, new_target = criterion_refine( pred_r, pred_t, new_target, model_points, idx, new_points) test_dis += dis.item() logger.info('Test time {0} Test Frame No.{1} dis:{2}'.format( time.strftime("%Hh %Mm %Ss", time.gmtime(time.time() - st_time)), test_count, dis)) test_count += 1 if (test_count >= 3000): break test_dis = test_dis / test_count logger.info('Test time {0} Epoch {1} TEST FINISH Avg dis: {2}'.format( time.strftime("%Hh %Mm %Ss", time.gmtime(time.time() - st_time)), epoch, test_dis)) if test_dis <= best_test: best_test = test_dis if opt.refine_start: torch.save( refiner.state_dict(), '{0}/pose_refine_model_{1}_{2}.pth'.format( opt.outf, epoch, test_dis)) else: torch.save( estimator.state_dict(), '{0}/pose_model_{1}_{2}.pth'.format( opt.outf, epoch, test_dis)) print(epoch, '>>>>>>>>----------BEST TEST MODEL SAVED---------<<<<<<<<') if best_test < opt.decay_margin and not opt.decay_start: opt.decay_start = True opt.lr *= opt.lr_rate opt.w *= opt.w_rate optimizer = optim.Adam(estimator.parameters(), lr=opt.lr) if best_test < opt.refine_margin and not opt.refine_start: opt.refine_start = True opt.batch_size = int(opt.batch_size / opt.iteration) optimizer = optim.Adam(refiner.parameters(), lr=opt.lr) dataset = YCBDataset( opt.dataset_root, mode='train_syn_grid', object_list=object_list, output_data=output_format, resample_on_error=True, preprocessors=[ YCBOcclusionAugmentor(opt.dataset_root), ColorJitter(), InplaneRotator() ], postprocessors=[ImageNormalizer(), PointShifter()], refine=opt.refine_start, image_size=[640, 480], num_points=1000) dataloader = torch.utils.data.DataLoader(dataset, batch_size=1, shuffle=True, num_workers=opt.workers) test_dataset = YCBDataset(opt.dataset_root, mode='valid', object_list=object_list, output_data=output_format, resample_on_error=True, preprocessors=[], postprocessors=[ImageNormalizer()], refine=opt.refine_start, image_size=[640, 480], num_points=1000) testdataloader = torch.utils.data.DataLoader( test_dataset, batch_size=1, shuffle=False, num_workers=opt.workers) opt.num_points_mesh = dataset.num_pt_mesh_large print( '>>>>>>>>----------Dataset loaded!---------<<<<<<<<\nlength of the training set: {0}\nlength of the testing set: {1}\nnumber of sample points on mesh: {2}\nsymmetry object list: {3}' .format(len(dataset), len(test_dataset), opt.num_points_mesh, opt.sym_list)) criterion = Loss(opt.num_points_mesh, opt.sym_list) criterion_refine = Loss_refine(opt.num_points_mesh, opt.sym_list)
def main(): # opt.manualSeed = random.randint(1, 10000) # # opt.manualSeed = 1 # random.seed(opt.manualSeed) # torch.manual_seed(opt.manualSeed) torch.set_printoptions(threshold=5000) # device_ids = [0,1] cudnn.benchmark = True if opt.dataset == 'ycb': opt.num_objects = 21 #number of object classes in the dataset opt.num_points = 1000 #number of points on the input pointcloud opt.outf = 'trained_models/ycb' #folder to save trained models opt.log_dir = 'experiments/logs/ycb' #folder to save logs opt.repeat_epoch = 3 #number of repeat times for one epoch training elif opt.dataset == 'linemod': opt.num_objects = 13 opt.num_points = 500 opt.outf = 'trained_models/linemod' opt.log_dir = 'experiments/logs/linemod' opt.repeat_epoch = 20 else: print('Unknown dataset') return estimator = PoseNet(num_points=opt.num_points, num_obj=opt.num_objects) estimator.cuda() refiner = PoseRefineNet(num_points=opt.num_points, num_obj=opt.num_objects) # refiner.cuda() # estimator = nn.DataParallel(estimator, device_ids=device_ids) if opt.resume_posenet != '': estimator.load_state_dict( torch.load('{0}/{1}'.format(opt.outf, opt.resume_posenet))) print('LOADED!!') if opt.resume_refinenet != '': refiner.load_state_dict( torch.load('{0}/{1}'.format(opt.outf, opt.resume_refinenet))) opt.refine_start = True opt.decay_start = True opt.lr *= opt.lr_rate opt.w *= opt.w_rate opt.batch_size = int(opt.batch_size / opt.iteration) optimizer = optim.Adam(refiner.parameters(), lr=opt.lr) else: print('no refinement') opt.refine_start = False opt.decay_start = False optimizer = optim.Adam(estimator.parameters(), lr=opt.lr) # optimizer = nn.DataParallel(optimizer, device_ids=device_ids) if opt.dataset == 'ycb': dataset = PoseDataset_ycb('train', opt.num_points, False, opt.dataset_root, opt.noise_trans, opt.refine_start) # print(dataset.list) elif opt.dataset == 'linemod': dataset = PoseDataset_linemod('train', opt.num_points, True, opt.dataset_root, opt.noise_trans, opt.refine_start) dataloader = torch.utils.data.DataLoader(dataset, batch_size=1, shuffle=True, num_workers=opt.workers) if opt.dataset == 'ycb': test_dataset = PoseDataset_ycb('test', opt.num_points, False, opt.dataset_root, 0.0, opt.refine_start) elif opt.dataset == 'linemod': test_dataset = PoseDataset_linemod('test', opt.num_points, False, opt.dataset_root, 0.0, opt.refine_start) testdataloader = torch.utils.data.DataLoader(test_dataset, batch_size=1, shuffle=False, num_workers=opt.workers) opt.sym_list = dataset.get_sym_list() opt.num_points_mesh = dataset.get_num_points_mesh() # print('>>>>>>>>----------Dataset loaded!---------<<<<<<<<\nlength of the training set: {0}\nlength of the testing set: {1}\nnumber of sample points on mesh: {2}\nsymmetry object list: {3}'.format(len(dataset), len(test_dataset), opt.num_points_mesh, opt.sym_list)) criterion = Loss(opt.num_points_mesh, opt.sym_list) # criterion_refine = Loss_refine(opt.num_points_mesh, opt.sym_list) best_test = np.Inf best_epoch = 0 if opt.start_epoch == 1: for log in os.listdir(opt.log_dir): os.remove(os.path.join(opt.log_dir, log)) st_time = time.time() count_gen = 0 mode = 1 if mode == 1: for epoch in range(opt.start_epoch, opt.nepoch): logger = setup_logger( 'epoch%d' % epoch, os.path.join(opt.log_dir, 'epoch_%d_log.txt' % epoch)) logger.info('Train time {0}'.format( time.strftime("%Hh %Mm %Ss", time.gmtime(time.time() - st_time)) + ', ' + 'Training started')) train_count = 0 train_dis_avg = 0.0 if opt.refine_start: estimator.eval() refiner.train() else: estimator.train() optimizer.zero_grad() for rep in range(opt.repeat_epoch): for i, data in enumerate(dataloader, 0): points, choose, img, target_sym, target_cen, idx, file_list_idx = data if idx is 9 or idx is 16: continue points, choose, img, target_sym, target_cen, idx = Variable(points).cuda(), \ Variable(choose).cuda(), \ Variable(img).cuda(), \ Variable(target_sym).cuda(), \ Variable(target_cen).cuda(), \ Variable(idx).cuda() pred_norm, pred_on_plane, emb = estimator( img, points, choose, idx) loss = criterion(pred_norm, pred_on_plane, target_sym, target_cen, idx, points, opt.w, opt.refine_start) # scene_idx = dataset.list[file_list_idx] loss.backward() # train_dis_avg += dis.item() train_count += 1 if train_count % opt.batch_size == 0: logger.info( 'Train time {0} Epoch {1} Batch {2} Frame {3}'. format( time.strftime( "%Hh %Mm %Ss", time.gmtime(time.time() - st_time)), epoch, int(train_count / opt.batch_size), train_count)) optimizer.step() # for param_lr in optimizer.module.param_groups: # param_lr['lr'] /= 2 optimizer.zero_grad() train_dis_avg = 0 if train_count % 8 == 0: print(pred_on_plane.max()) print(pred_on_plane.mean()) print(idx) if train_count != 0 and train_count % 1000 == 0: if opt.refine_start: torch.save( refiner.state_dict(), '{0}/pose_refine_model_current.pth'.format( opt.outf)) else: torch.save( estimator.state_dict(), '{0}/pose_model_current.pth'.format(opt.outf)) print('>>>>>>>>----------epoch {0} train finish---------<<<<<<<<'. format(epoch)) logger = setup_logger( 'epoch%d_test' % epoch, os.path.join(opt.log_dir, 'epoch_%d_test_log.txt' % epoch)) logger.info('Test time {0}'.format( time.strftime("%Hh %Mm %Ss", time.gmtime(time.time() - st_time)) + ', ' + 'Testing started')) test_loss = 0.0 test_count = 0 estimator.eval() logger.info( 'Test time {0} Epoch {1} TEST FINISH Avg dis: {2}'.format( time.strftime("%Hh %Mm %Ss", time.gmtime(time.time() - st_time)), epoch, test_loss)) print(pred_on_plane.max()) print(pred_on_plane.mean()) bs, num_p, _ = pred_on_plane.size() # if epoch % 40 == 0: # import pdb;pdb.set_trace() best_test = test_loss best_epoch = epoch if opt.refine_start: torch.save( refiner.state_dict(), '{0}/pose_refine_model_{1}_{2}.pth'.format( opt.outf, epoch, test_loss)) else: torch.save( estimator.state_dict(), '{0}/pose_model_{1}_{2}.pth'.format( opt.outf, epoch, test_loss)) print(epoch, '>>>>>>>>----------BEST TEST MODEL SAVED---------<<<<<<<<') if best_test < opt.decay_margin and not opt.decay_start: opt.decay_start = True opt.lr *= opt.lr_rate # opt.w *= opt.w_rate optimizer = optim.Adam(estimator.parameters(), lr=opt.lr) estimator.load_state_dict( torch.load('{0}/pose_model_{1}_{2}.pth'.format( opt.outf, best_epoch, best_test))) else: estimator.load_state_dict( torch.load('{0}/pose_model_45_0.0.pth'.format(opt.outf), map_location='cpu'))
parser.add_argument('--refine_model', type=str, default='', help='resume PoseRefineNet model') opt = parser.parse_args() num_objects = 13 objlist = [1, 2, 4, 5, 6, 8, 9, 10, 11, 12, 13, 14, 15] num_points = 500 iteration = 4 bs = 1 dataset_config_dir = 'datasets/linemod/dataset_config' output_result_dir = 'experiments/eval_result/linemod' knn = KNearestNeighbor(1) model = PoseNet(num_points=num_points, num_obj=num_objects) model.cuda() refiner = PoseRefineNet(num_points=num_points, num_obj=num_objects) refiner.cuda() model.load_state_dict(torch.load(opt.model)) refiner.load_state_dict(torch.load(opt.refine_model)) model.eval() refiner.eval() testdataset = PoseDataset_linemod('eval', num_points, False, opt.dataset_root, 0.0, True) testdataloader = torch.utils.data.DataLoader(testdataset, batch_size=1, shuffle=False, num_workers=10)
def __init__(self, exp, env): super().__init__() self._mode = 'init' # check experiment cfg for errors check_exp(exp) # logging h-params exp_config_flatten = flatten_dict(copy.deepcopy(exp)) for k in exp_config_flatten.keys(): if exp_config_flatten[k] is None: exp_config_flatten[k] = 'is None' self.hparams = exp_config_flatten self.hparams['lr'] = exp['training']['lr'] self.test_size = exp['training']['test_size'] self.env, self.exp = env, exp # number of input points to the network num_points_small = exp['d_train']['num_pt_mesh_small'] num_points_large = exp['d_train']['num_pt_mesh_large'] num_obj = exp['d_train']['objects'] self.df_pose_estimator = PoseNet( num_points=exp['d_test']['num_points'], num_obj=num_obj) self.df_refiner = PoseRefineNet( num_points=exp['d_test']['num_points'], num_obj=num_obj) if exp.get('model', {}).get('df_load', False): self.df_pose_estimator.load_state_dict( torch.load(exp['model']['df_pose_estimator'])) if exp.get('model', {}).get('df_refine', False): self.df_refiner.load_state_dict( torch.load(exp['model']['df_refiner'])) sl = exp['d_train']['obj_list_sym'] self.df_criterion = Loss( num_points_large, sl) self.df_criterion_refine = Loss_refine( num_points_large, sl) self.criterion_adds = LossAddS(sym_list=sl) self.visualizer = Visualizer(self.exp['model_path'] + '/visu/', None) self._dict_track = {} self.number_images_log_test = self.exp.get( 'visu', {}).get('number_images_log_test', 1) self.counter_images_logged = 0 self.init_train_vali_split = False mp = exp['model_path'] fh = logging.FileHandler(f'{mp}/Live_Logger_Lightning.log') fh.setLevel(logging.DEBUG) logging.getLogger("lightning").addHandler(fh) self.start = time.time() self.best_val_loss = 999 # optional, set the logging level if self.exp.get('visu', {}).get('log_to_file', False): console = logging.StreamHandler() console.setLevel(logging.DEBUG) logging.getLogger("lightning").addHandler(console) log = open(f'{mp}/Live_Logger_Lightning.log', "a") sys.stdout = log logging.info('Logging to File')
def main(): if opt.dataset == 'ycb': opt.num_obj = 21 opt.sym_list = [12, 15, 18, 19, 20] opt.num_points = 1000 writer = SummaryWriter('experiments/runs/ycb/{0}'.format(opt.experiment_name)) opt.outf = 'trained_models/ycb/{0}'.format(opt.experiment_name) opt.log_dir = 'experiments/logs/ycb/{0}'.format(opt.experiment_name) opt.repeat_num = 1 if not os.path.exists(opt.outf): os.mkdir(opt.outf) if not os.path.exists(opt.log_dir): os.mkdir(opt.log_dir) else: print('Unknown dataset') return estimator = PoseNet(num_points = opt.num_points, num_vote = 9, num_obj = opt.num_obj) estimator.cuda() refiner = PoseRefineNet(num_points = opt.num_points, num_obj = opt.num_obj) refiner.cuda() if opt.resume_posenet != '': estimator.load_state_dict(torch.load('{0}/{1}'.format(opt.outf, opt.resume_posenet))) if opt.resume_refinenet != '': refiner.load_state_dict(torch.load('{0}/{1}'.format(opt.outf, opt.resume_refinenet))) opt.refine_start = True opt.lr = opt.lr_refine opt.batch_size = int(opt.batch_size / opt.iteration) optimizer = optim.Adam(refiner.parameters(), lr=opt.lr) else: opt.refine_start = False optimizer = optim.Adam(estimator.parameters(), lr=opt.lr) dataset = PoseDataset_ycb('train', opt.num_points, True, opt.dataset_root) dataloader = torch.utils.data.DataLoader(dataset, batch_size=1, shuffle=True, num_workers=opt.workers) test_dataset = PoseDataset_ycb('test', opt.num_points, False, opt.dataset_root) testdataloader = torch.utils.data.DataLoader(test_dataset, batch_size=1, shuffle=False, num_workers=opt.workers) print('>>>>>>>>----------Dataset loaded!---------<<<<<<<<\nlength of the training set: {0}\nlength of the testing set: {1}\nnumber of sample points on mesh: {2}'.format(len(dataset), len(test_dataset), opt.num_points)) criterion = Loss(opt.num_points, opt.sym_list) criterion_refine = Loss_refine(opt.num_points, opt.sym_list) best_test = np.Inf if opt.start_epoch == 1: for log in os.listdir(opt.log_dir): os.remove(os.path.join(opt.log_dir, log)) st_time = time.time() train_scalar = 0 for epoch in range(opt.start_epoch, opt.nepoch): logger = setup_logger('epoch%d' % epoch, os.path.join(opt.log_dir, 'epoch_%d_log.txt' % epoch)) logger.info('Train time {0}'.format(time.strftime("%Hh %Mm %Ss", time.gmtime(time.time() - st_time)) + ', ' + 'Training started')) train_count = 0 train_loss_avg = 0.0 train_loss = 0.0 train_dis_avg = 0.0 train_dis = 0.0 if opt.refine_start: estimator.eval() refiner.train() else: estimator.train() optimizer.zero_grad() for rep in range(opt.repeat_num): for i, data in enumerate(dataloader, 0): points, choose, img, target, model_points, model_kp, vertex_gt, idx, target_r, target_t = data points, choose, img, target, model_points, model_kp, vertex_gt, idx, target_r, target_t = points.cuda(), choose.cuda(), img.cuda(), target.cuda(), model_points.cuda(), model_kp.cuda(), vertex_gt.cuda(), idx.cuda(), target_r.cuda(), target_t.cuda() vertex_pred, c_pred, emb = estimator(img, points, choose, idx) vertex_loss, pose_loss, dis, new_points, new_target = criterion(vertex_pred, vertex_gt, c_pred, points, target, model_points, model_kp, idx, target_r, target_t) loss = 10 * vertex_loss + pose_loss if opt.refine_start: for ite in range(0, opt.iteration): pred_r, pred_t = refiner(new_points, emb, idx) dis, new_points, new_target = criterion_refine(pred_r, pred_t, new_points, new_target, model_points, idx) dis.backward() else: loss.backward() train_loss_avg += loss.item() train_loss += loss.item() train_dis_avg += dis.item() train_dis += dis.item() train_count += 1 train_scalar += 1 if train_count % opt.batch_size == 0: logger.info('Train time {0} Epoch {1} Batch {2} Frame {3} Avg_loss:{4} Avg_diss:{5}'.format(time.strftime("%Hh %Mm %Ss", time.gmtime(time.time() - st_time)), epoch, int(train_count / opt.batch_size), train_count, train_loss_avg / opt.batch_size, train_dis_avg / opt.batch_size)) writer.add_scalar('ycb training loss', train_loss_avg / opt.batch_size, train_scalar) writer.add_scalar('ycb training dis', train_dis_avg / opt.batch_size, train_scalar) optimizer.step() optimizer.zero_grad() train_loss_avg = 0 train_dis_avg = 0 if train_count != 0 and train_count % 1000 == 0: if opt.refine_start: torch.save(refiner.state_dict(), '{0}/pose_refine_model_current.pth'.format(opt.outf)) else: torch.save(estimator.state_dict(), '{0}/pose_model_current.pth'.format(opt.outf)) print('>>>>>>>>----------epoch {0} train finish---------<<<<<<<<'.format(epoch)) train_loss = train_loss / train_count train_dis = train_dis / train_count logger.info('Train time {0} Epoch {1} TRAIN FINISH Avg loss: {2} Avg dis: {3}'.format(time.strftime("%Hh %Mm %Ss", time.gmtime(time.time() - st_time)), epoch, train_loss, train_dis)) logger = setup_logger('epoch%d_test' % epoch, os.path.join(opt.log_dir, 'epoch_%d_test_log.txt' % epoch)) logger.info('Test time {0}'.format(time.strftime("%Hh %Mm %Ss", time.gmtime(time.time() - st_time)) + ', ' + 'Testing started')) test_loss = 0.0 test_vertex_loss = 0.0 test_pose_loss = 0.0 test_dis = 0.0 test_count = 0 success_count = 0 estimator.eval() refiner.eval() for j, data in enumerate(testdataloader, 0): points, choose, img, target, model_points, model_kp, vertex_gt, idx, target_r, target_t = data points, choose, img, target, model_points, model_kp, vertex_gt, idx, target_r, target_t = points.cuda(), choose.cuda(), img.cuda(), target.cuda(), model_points.cuda(), model_kp.cuda(), vertex_gt.cuda(), idx.cuda(), target_r.cuda(), target_t.cuda() vertex_pred, c_pred, emb = estimator(img, points, choose, idx) vertex_loss, pose_loss, dis, new_points, new_target = criterion(vertex_pred, vertex_gt, c_pred, points, target, model_points, model_kp, idx, target_r, target_t) loss = 10 * vertex_loss + pose_loss if opt.refine_start: for ite in range(0, opt.iteration): pred_r, pred_t = refiner(new_points, emb, idx) dis, new_points, new_target = criterion_refine(pred_r, pred_t, new_points, new_target, model_points, idx) test_loss += loss.item() test_vertex_loss += vertex_loss.item() test_pose_loss += pose_loss.item() test_dis += dis.item() logger.info('Test time {0} Test Frame No.{1} loss:{2} dis:{3}'.format(time.strftime("%Hh %Mm %Ss", time.gmtime(time.time() - st_time)), test_count, loss, dis)) test_count += 1 if dis.item() < 0.02: success_count += 1 test_loss = test_loss / test_count test_vertex_loss = test_vertex_loss / test_count test_pose_loss = test_pose_loss / test_count test_dis = test_dis / test_count logger.info('Test time {0} Epoch {1} TEST FINISH Avg loss: {2} Avg dis: {3}'.format(time.strftime("%Hh %Mm %Ss", time.gmtime(time.time() - st_time)), epoch, test_loss, test_dis)) logger.info('Success rate: {}'.format(float(success_count) / test_count)) writer.add_scalar('ycb test loss', test_loss, epoch) writer.add_scalar('ycb test vertex loss', test_vertex_loss, epoch) writer.add_scalar('ycb test pose loss', test_pose_loss, epoch) writer.add_scalar('ycb test dis', test_dis, epoch) writer.add_scalar('ycb success rate', float(success_count) / test_count, epoch) writer.add_scalar('lr', optimizer.param_groups[0]['lr'], epoch) if test_dis <= best_test: best_test = test_dis if opt.refine_start: torch.save(refiner.state_dict(), '{0}/pose_refine_model_{1}_{2}.pth'.format(opt.outf, epoch, test_dis)) else: torch.save(estimator.state_dict(), '{0}/pose_model_{1}_{2}.pth'.format(opt.outf, epoch, test_dis)) print(epoch, '>>>>>>>>----------MODEL SAVED---------<<<<<<<<') if best_test < opt.refine_margin and not opt.refine_start: opt.refine_start = True opt.lr = opt.lr_refine opt.batch_size = int(opt.batch_size / opt.iteration) optimizer = optim.Adam(refiner.parameters(), lr=opt.lr) print('>>>>>>>>----------Refine started---------<<<<<<<<') writer.close()
def main(): opt.manualSeed = random.randint(1, 10000) random.seed(opt.manualSeed) torch.manual_seed(opt.manualSeed) if opt.dataset == 'ycb': opt.dataset_root = 'datasets/ycb/YCB_Video_Dataset' opt.num_objects = 21 opt.num_points = 1000 opt.result_dir = 'results/ycb' opt.repeat_epoch = 1 elif opt.dataset == 'linemod': opt.dataset_root = 'datasets/linemod/Linemod_preprocessed' opt.num_objects = 13 opt.num_points = 500 opt.result_dir = 'results/linemod' opt.repeat_epoch = 1 else: print('unknown dataset') return if opt.dataset == 'ycb': dataset = PoseDataset_ycb('train', opt.num_points, True, opt.dataset_root, opt.noise_trans) test_dataset = PoseDataset_ycb('test', opt.num_points, False, opt.dataset_root, 0.0) elif opt.dataset == 'linemod': dataset = PoseDataset_linemod('train', opt.num_points, True, opt.dataset_root, opt.noise_trans) test_dataset = PoseDataset_linemod('test', opt.num_points, False, opt.dataset_root, 0.0) dataloader = torch.utils.data.DataLoader(dataset, batch_size=1, shuffle=True, num_workers=opt.workers) testdataloader = torch.utils.data.DataLoader(test_dataset, batch_size=1, shuffle=False, num_workers=opt.workers) opt.sym_list = dataset.get_sym_list() opt.num_points_mesh = dataset.get_num_points_mesh() opt.diameters = dataset.get_diameter() print('>>>>>>>>----------Dataset loaded!---------<<<<<<<<') print('length of the training set: {0}'.format(len(dataset))) print('length of the testing set: {0}'.format(len(test_dataset))) print('number of sample points on mesh: {0}'.format(opt.num_points_mesh)) print('symmetrical object list: {0}'.format(opt.sym_list)) if not os.path.exists(opt.result_dir): os.makedirs(opt.result_dir) tb_writer = tf.summary.FileWriter(opt.result_dir) os.environ['CUDA_VISIBLE_DEVICES'] = opt.gpu_id # network estimator = PoseNet(num_points=opt.num_points, num_obj=opt.num_objects, num_rot=opt.num_rot) estimator.cuda() # loss criterion = Loss(opt.sym_list, estimator.rot_anchors) knn = KNearestNeighbor(1) # learning rate decay best_test = np.Inf opt.first_decay_start = False opt.second_decay_start = False # if resume training if opt.resume_posenet != '': estimator.load_state_dict(torch.load(opt.resume_posenet)) model_name_parsing = (opt.resume_posenet.split('.')[0]).split('_') best_test = float(model_name_parsing[-1]) opt.start_epoch = int(model_name_parsing[-2]) + 1 if best_test < 0.016 and not opt.first_decay_start: opt.first_decay_start = True opt.lr *= 0.6 if best_test < 0.013 and not opt.second_decay_start: opt.second_decay_start = True opt.lr *= 0.5 # optimizer optimizer = torch.optim.Adam(estimator.parameters(), lr=opt.lr) global_step = (len(dataset) // opt.batch_size) * opt.repeat_epoch * (opt.start_epoch - 1) # train st_time = time.time() for epoch in range(opt.start_epoch, opt.nepoch): logger = setup_logger( 'epoch%02d' % epoch, os.path.join(opt.result_dir, 'epoch_%02d_train_log.txt' % epoch)) logger.info('Train time {0}'.format( time.strftime("%Hh %Mm %Ss", time.gmtime(time.time() - st_time)) + ', ' + 'Training started')) train_count = 0 train_loss_avg = 0.0 train_loss_r_avg = 0.0 train_loss_t_avg = 0.0 train_loss_reg_avg = 0.0 estimator.train() optimizer.zero_grad() for rep in range(opt.repeat_epoch): for i, data in enumerate(dataloader, 0): points, choose, img, target_t, target_r, model_points, idx, gt_t = data obj_diameter = opt.diameters[idx] points, choose, img, target_t, target_r, model_points, idx = Variable(points).cuda(), \ Variable(choose).cuda(), \ Variable(img).cuda(), \ Variable(target_t).cuda(), \ Variable(target_r).cuda(), \ Variable(model_points).cuda(), \ Variable(idx).cuda() pred_r, pred_t, pred_c = estimator(img, points, choose, idx) loss, loss_r, loss_t, loss_reg = criterion( pred_r, pred_t, pred_c, target_r, target_t, model_points, idx, obj_diameter) loss.backward() train_loss_avg += loss.item() train_loss_r_avg += loss_r.item() train_loss_t_avg += loss_t.item() train_loss_reg_avg += loss_reg.item() train_count += 1 if train_count % opt.batch_size == 0: global_step += 1 lr = opt.lr optimizer.step() optimizer.zero_grad() # write results to tensorboard summary = tf.Summary(value=[ tf.Summary.Value(tag='learning_rate', simple_value=lr), tf.Summary.Value(tag='loss', simple_value=train_loss_avg / opt.batch_size), tf.Summary.Value(tag='loss_r', simple_value=train_loss_r_avg / opt.batch_size), tf.Summary.Value(tag='loss_t', simple_value=train_loss_t_avg / opt.batch_size), tf.Summary.Value(tag='loss_reg', simple_value=train_loss_reg_avg / opt.batch_size) ]) tb_writer.add_summary(summary, global_step) logger.info( 'Train time {0} Epoch {1} Batch {2} Frame {3} Avg_loss:{4:f}' .format( time.strftime("%Hh %Mm %Ss", time.gmtime(time.time() - st_time)), epoch, int(train_count / opt.batch_size), train_count, train_loss_avg / opt.batch_size)) train_loss_avg = 0.0 train_loss_r_avg = 0.0 train_loss_t_avg = 0.0 train_loss_reg_avg = 0.0 print( '>>>>>>>>----------epoch {0} train finish---------<<<<<<<<'.format( epoch)) logger = setup_logger( 'epoch%02d_test' % epoch, os.path.join(opt.result_dir, 'epoch_%02d_test_log.txt' % epoch)) logger.info('Test time {0}'.format( time.strftime("%Hh %Mm %Ss", time.gmtime(time.time() - st_time)) + ', ' + 'Testing started')) test_dis = 0.0 test_count = 0 save_model = False estimator.eval() success_count = [0 for i in range(opt.num_objects)] num_count = [0 for i in range(opt.num_objects)] for j, data in enumerate(testdataloader, 0): points, choose, img, target_t, target_r, model_points, idx, gt_t = data obj_diameter = opt.diameters[idx] points, choose, img, target_t, target_r, model_points, idx = Variable(points).cuda(), \ Variable(choose).cuda(), \ Variable(img).cuda(), \ Variable(target_t).cuda(), \ Variable(target_r).cuda(), \ Variable(model_points).cuda(), \ Variable(idx).cuda() pred_r, pred_t, pred_c = estimator(img, points, choose, idx) loss, _, _, _ = criterion(pred_r, pred_t, pred_c, target_r, target_t, model_points, idx, obj_diameter) test_count += 1 # evalaution how_min, which_min = torch.min(pred_c, 1) pred_r = pred_r[0][which_min[0]].view(-1).cpu().data.numpy() pred_r = quaternion_matrix(pred_r)[:3, :3] pred_t, pred_mask = ransac_voting_layer(points, pred_t) pred_t = pred_t.cpu().data.numpy() model_points = model_points[0].cpu().detach().numpy() pred = np.dot(model_points, pred_r.T) + pred_t target = target_r[0].cpu().detach().numpy() + gt_t[0].cpu( ).data.numpy() if idx[0].item() in opt.sym_list: pred = torch.from_numpy(pred.astype( np.float32)).cuda().transpose(1, 0).contiguous() target = torch.from_numpy(target.astype( np.float32)).cuda().transpose(1, 0).contiguous() inds = knn(target.unsqueeze(0), pred.unsqueeze(0)) target = torch.index_select(target, 1, inds.view(-1) - 1) dis = torch.mean(torch.norm( (pred.transpose(1, 0) - target.transpose(1, 0)), dim=1), dim=0).item() else: dis = np.mean(np.linalg.norm(pred - target, axis=1)) logger.info( 'Test time {0} Test Frame No.{1} loss:{2:f} confidence:{3:f} distance:{4:f}' .format( time.strftime("%Hh %Mm %Ss", time.gmtime(time.time() - st_time)), test_count, loss, how_min[0].item(), dis)) if dis < 0.1 * opt.diameters[idx[0].item()]: success_count[idx[0].item()] += 1 num_count[idx[0].item()] += 1 test_dis += dis # compute accuracy accuracy = 0.0 for i in range(opt.num_objects): accuracy += float(success_count[i]) / num_count[i] logger.info('Object {0} success rate: {1}'.format( test_dataset.objlist[i], float(success_count[i]) / num_count[i])) accuracy = accuracy / opt.num_objects test_dis = test_dis / test_count # log results logger.info( 'Test time {0} Epoch {1} TEST FINISH Avg dis: {2:f}, Accuracy: {3:f}' .format( time.strftime("%Hh %Mm %Ss", time.gmtime(time.time() - st_time)), epoch, test_dis, accuracy)) # tensorboard summary = tf.Summary(value=[ tf.Summary.Value(tag='accuracy', simple_value=accuracy), tf.Summary.Value(tag='test_dis', simple_value=test_dis) ]) tb_writer.add_summary(summary, global_step) # save model if test_dis < best_test: best_test = test_dis torch.save( estimator.state_dict(), '{0}/pose_model_{1:02d}_{2:06f}.pth'.format( opt.result_dir, epoch, best_test)) # adjust learning rate if necessary if best_test < 0.016 and not opt.first_decay_start: opt.first_decay_start = True opt.lr *= 0.6 optimizer = torch.optim.Adam(estimator.parameters(), lr=opt.lr) if best_test < 0.013 and not opt.second_decay_start: opt.second_decay_start = True opt.lr *= 0.5 optimizer = torch.optim.Adam(estimator.parameters(), lr=opt.lr) print( '>>>>>>>>----------epoch {0} test finish---------<<<<<<<<'.format( epoch))
def main(): if opt.dataset == 'linemod': opt.num_obj = 1 opt.list_obj = [1, 2, 4, 5, 6, 8, 9, 10, 11, 12, 13, 14, 15] opt.occ_list_obj = [1, 5, 6, 8, 9, 10, 11, 12] opt.list_name = ['ape', 'benchvise', 'cam', 'can', 'cat', 'driller', 'duck', 'eggbox', 'glue', 'holepuncher', 'iron', 'lamp', 'phone'] obj_name = opt.list_name[opt.list_obj.index(opt.obj_id)] opt.sym_list = [10, 11] opt.num_points = 500 meta_file = open('{0}/models/models_info.yml'.format(opt.dataset_root), 'r') meta = yaml.load(meta_file) diameter = meta[opt.obj_id]['diameter'] / 1000.0 * 0.1 if opt.render: opt.repeat_num = 1 elif opt.fuse: opt.repeat_num = 1 else: opt.repeat_num = 5 writer = SummaryWriter('experiments/runs/linemod/{}{}'.format(obj_name, opt.experiment_name)) opt.outf = 'trained_models/linemod/{}{}'.format(obj_name, opt.experiment_name) opt.log_dir = 'experiments/logs/linemod/{}{}'.format(obj_name, opt.experiment_name) if not os.path.exists(opt.outf): os.mkdir(opt.outf) if not os.path.exists(opt.log_dir): os.mkdir(opt.log_dir) else: print('Unknown dataset') return estimator = PoseNet(num_points = opt.num_points, num_vote = 9, num_obj = opt.num_obj) estimator.cuda() refiner = PoseRefineNet(num_points = opt.num_points, num_obj = opt.num_obj) refiner.cuda() if opt.resume_posenet != '': estimator.load_state_dict(torch.load('{0}/{1}'.format(opt.outf, opt.resume_posenet))) if opt.resume_refinenet != '': refiner.load_state_dict(torch.load('{0}/{1}'.format(opt.outf, opt.resume_refinenet))) opt.refine_start = True opt.lr = opt.lr_refine opt.batch_size = int(opt.batch_size / opt.iteration) optimizer = optim.Adam(refiner.parameters(), lr=opt.lr) else: opt.refine_start = False optimizer = optim.Adam(estimator.parameters(), lr=opt.lr) dataset = PoseDataset_linemod('train', opt.num_points, opt.dataset_root, opt.real, opt.render, opt.fuse, opt.obj_id) dataloader = torch.utils.data.DataLoader(dataset, batch_size=1, shuffle=True, num_workers=opt.workers) test_dataset = PoseDataset_linemod('test', opt.num_points, opt.dataset_root, True, False, False, opt.obj_id) testdataloader = torch.utils.data.DataLoader(test_dataset, batch_size=1, shuffle=False, num_workers=opt.workers) print('>>>>>>>>----------Dataset loaded!---------<<<<<<<<\nlength of the training set: {0}\nlength of the testing set: {1}\nnumber of sample points on mesh: {2}'.format(len(dataset), len(test_dataset), opt.num_points)) if opt.obj_id in opt.occ_list_obj: occ_test_dataset = PoseDataset_occ('test', opt.num_points, opt.occ_dataset_root, opt.obj_id) occtestdataloader = torch.utils.data.DataLoader(occ_test_dataset, batch_size=1, shuffle=False, num_workers=opt.workers) print('length of the occ testing set: {}'.format(len(occ_test_dataset))) criterion = Loss(opt.num_points, opt.sym_list) criterion_refine = Loss_refine(opt.num_points, opt.sym_list) best_test = np.Inf if opt.start_epoch == 1: for log in os.listdir(opt.log_dir): os.remove(os.path.join(opt.log_dir, log)) st_time = time.time() train_scalar = 0 for epoch in range(opt.start_epoch, opt.nepoch): logger = setup_logger('epoch%d' % epoch, os.path.join(opt.log_dir, 'epoch_%d_log.txt' % epoch)) logger.info('Train time {0}'.format(time.strftime("%Hh %Mm %Ss", time.gmtime(time.time() - st_time)) + ', ' + 'Training started')) train_count = 0 train_loss_avg = 0.0 train_loss = 0.0 train_dis_avg = 0.0 train_dis = 0.0 if opt.refine_start: estimator.eval() refiner.train() else: estimator.train() optimizer.zero_grad() for rep in range(opt.repeat_num): for i, data in enumerate(dataloader, 0): points, choose, img, target, model_points, model_kp, vertex_gt, idx, target_r, target_t = data if len(points.size()) == 2: print('pass') continue points, choose, img, target, model_points, model_kp, vertex_gt, idx, target_r, target_t = points.cuda(), choose.cuda(), img.cuda(), target.cuda(), model_points.cuda(), model_kp.cuda(), vertex_gt.cuda(), idx.cuda(), target_r.cuda(), target_t.cuda() vertex_pred, c_pred, emb = estimator(img, points, choose, idx) vertex_loss, pose_loss, dis, new_points, new_target = criterion(vertex_pred, vertex_gt, c_pred, points, target, model_points, model_kp, opt.obj_id, target_r, target_t) loss = 10 * vertex_loss + pose_loss if opt.refine_start: for ite in range(0, opt.iteration): pred_r, pred_t = refiner(new_points, emb, idx) dis, new_points, new_target = criterion_refine(pred_r, pred_t, new_points, new_target, model_points, opt.obj_id) dis.backward() else: loss.backward() train_loss_avg += loss.item() train_loss += loss.item() train_dis_avg += dis.item() train_dis += dis.item() train_count += 1 train_scalar += 1 if train_count % opt.batch_size == 0: logger.info('Train time {0} Epoch {1} Batch {2} Frame {3} Avg_loss:{4} Avg_diss:{5}'.format(time.strftime("%Hh %Mm %Ss", time.gmtime(time.time() - st_time)), epoch, int(train_count / opt.batch_size), train_count, train_loss_avg / opt.batch_size, train_dis_avg / opt.batch_size)) writer.add_scalar('linemod training loss', train_loss_avg / opt.batch_size, train_scalar) writer.add_scalar('linemod training dis', train_dis_avg / opt.batch_size, train_scalar) optimizer.step() optimizer.zero_grad() train_loss_avg = 0 train_dis_avg = 0 if train_count != 0 and train_count % 1000 == 0: if opt.refine_start: torch.save(refiner.state_dict(), '{0}/pose_refine_model_current.pth'.format(opt.outf)) else: torch.save(estimator.state_dict(), '{0}/pose_model_current.pth'.format(opt.outf)) print('>>>>>>>>----------epoch {0} train finish---------<<<<<<<<'.format(epoch)) train_loss = train_loss / train_count train_dis = train_dis / train_count logger.info('Train time {0} Epoch {1} TRAIN FINISH Avg loss: {2} Avg dis: {3}'.format(time.strftime("%Hh %Mm %Ss", time.gmtime(time.time() - st_time)), epoch, train_loss, train_dis)) logger = setup_logger('epoch%d_test' % epoch, os.path.join(opt.log_dir, 'epoch_%d_test_log.txt' % epoch)) logger.info('Test time {0}'.format(time.strftime("%Hh %Mm %Ss", time.gmtime(time.time() - st_time)) + ', ' + 'Testing started')) test_loss = 0.0 test_vertex_loss = 0.0 test_pose_loss = 0.0 test_dis = 0.0 test_count = 0 success_count = 0 estimator.eval() refiner.eval() for j, data in enumerate(testdataloader, 0): points, choose, img, target, model_points, model_kp, vertex_gt, idx, target_r, target_t = data if len(points.size()) == 2: logger.info('Test time {0} Lost detection!'.format(time.strftime("%Hh %Mm %Ss", time.gmtime(time.time() - st_time)))) continue points, choose, img, target, model_points, model_kp, vertex_gt, idx, target_r, target_t = points.cuda(), choose.cuda(), img.cuda(), target.cuda(), model_points.cuda(), model_kp.cuda(), vertex_gt.cuda(), idx.cuda(), target_r.cuda(), target_t.cuda() vertex_pred, c_pred, emb = estimator(img, points, choose, idx) vertex_loss, pose_loss, dis, new_points, new_target = criterion(vertex_pred, vertex_gt, c_pred, points, target, model_points, model_kp, opt.obj_id, target_r, target_t) loss = 10 * vertex_loss + pose_loss if opt.refine_start: for ite in range(0, opt.iteration): pred_r, pred_t = refiner(new_points, emb, idx) dis, new_points, new_target = criterion_refine(pred_r, pred_t, new_points, new_target, model_points, opt.obj_id) test_loss += loss.item() test_vertex_loss += vertex_loss.item() test_pose_loss += pose_loss.item() test_dis += dis.item() logger.info('Test time {0} Test Frame No.{1} loss:{2} dis:{3}'.format(time.strftime("%Hh %Mm %Ss", time.gmtime(time.time() - st_time)), test_count, loss, dis)) if dis.item() < diameter: success_count += 1 test_count += 1 test_loss = test_loss / test_count test_vertex_loss = test_vertex_loss / test_count test_pose_loss = test_pose_loss / test_count test_dis = test_dis / test_count success_rate = float(success_count) / test_count logger.info('Test time {0} Epoch {1} TEST FINISH Avg loss: {2} Avg dis: {3} Success rate: {4}'.format(time.strftime("%Hh %Mm %Ss", time.gmtime(time.time() - st_time)), epoch, test_loss, test_dis, success_rate)) writer.add_scalar('linemod test loss', test_loss, epoch) writer.add_scalar('linemod test vertex loss', test_vertex_loss, epoch) writer.add_scalar('linemod test pose loss', test_pose_loss, epoch) writer.add_scalar('linemod test dis', test_dis, epoch) writer.add_scalar('linemod success rate', success_rate, epoch) writer.add_scalar('lr', optimizer.param_groups[0]['lr'], epoch) if test_dis <= best_test: best_test = test_dis if opt.refine_start: torch.save(refiner.state_dict(), '{0}/pose_refine_model_{1}_{2}.pth'.format(opt.outf, epoch, test_dis)) else: torch.save(estimator.state_dict(), '{0}/pose_model_{1}_{2}.pth'.format(opt.outf, epoch, test_dis)) print(epoch, '>>>>>>>>----------MODEL SAVED---------<<<<<<<<') if opt.obj_id in opt.occ_list_obj: logger = setup_logger('epoch%d_occ_test' % epoch, os.path.join(opt.log_dir, 'epoch_%d_occ_test_log.txt' % epoch)) logger.info('Occ test time {0}'.format(time.strftime("%Hh %Mm %Ss", time.gmtime(time.time() - st_time)) + ', ' + 'Testing started')) occ_test_dis = 0.0 occ_test_count = 0 occ_success_count = 0 estimator.eval() refiner.eval() for j, data in enumerate(occtestdataloader, 0): points, choose, img, target, model_points, model_kp, vertex_gt, idx, target_r, target_t = data if len(points.size()) == 2: logger.info('Occ test time {0} Lost detection!'.format(time.strftime("%Hh %Mm %Ss", time.gmtime(time.time() - st_time)))) continue points, choose, img, target, model_points, model_kp, vertex_gt, idx, target_r, target_t = points.cuda(), choose.cuda(), img.cuda(), target.cuda(), model_points.cuda(), model_kp.cuda(), vertex_gt.cuda(), idx.cuda(), target_r.cuda(), target_t.cuda() vertex_pred, c_pred, emb = estimator(img, points, choose, idx) vertex_loss, pose_loss, dis, new_points, new_target = criterion(vertex_pred, vertex_gt, c_pred, points, target, model_points, model_kp, opt.obj_id, target_r, target_t) if opt.refine_start: for ite in range(0, opt.iteration): pred_r, pred_t = refiner(new_points, emb, idx) dis, new_points, new_target = criterion_refine(pred_r, pred_t, new_points, new_target, model_points, opt.obj_id) occ_test_dis += dis.item() logger.info('Occ test time {0} Test Frame No.{1} dis:{2}'.format(time.strftime("%Hh %Mm %Ss", time.gmtime(time.time() - st_time)), occ_test_count, dis)) if dis.item() < diameter: occ_success_count += 1 occ_test_count += 1 occ_test_dis = occ_test_dis / occ_test_count occ_success_rate = float(occ_success_count) / occ_test_count logger.info('Occ test time {0} Epoch {1} TEST FINISH Avg dis: {2} Success rate: {3}'.format(time.strftime("%Hh %Mm %Ss", time.gmtime(time.time() - st_time)), epoch, occ_test_dis, occ_success_rate)) writer.add_scalar('occ test dis', occ_test_dis, epoch) writer.add_scalar('occ success rate', occ_success_rate, epoch) if best_test < opt.refine_margin and not opt.refine_start: opt.refine_start = True opt.lr = opt.lr_refine opt.batch_size = int(opt.batch_size / opt.iteration) optimizer = optim.Adam(refiner.parameters(), lr=opt.lr) print('>>>>>>>>----------Refine started---------<<<<<<<<') writer.close()
def main(): opt.manualSeed = random.randint(1, 10000) random.seed(opt.manualSeed) torch.manual_seed(opt.manualSeed) if opt.dataset == 'ycb': opt.num_objects = 21 #number of object classes in the dataset opt.num_points = 1000 #number of points on the input pointcloud opt.outf = 'trained_models/ycb' #folder to save trained models opt.log_dir = 'experiments/logs/ycb' #folder to save logs opt.repeat_epoch = 1 #number of repeat times for one epoch training elif opt.dataset == 'linemod': opt.num_objects = 13 opt.num_points = 500 opt.outf = 'trained_models/linemod' opt.log_dir = 'experiments/logs/linemod' opt.repeat_epoch = 20 else: print('Unknown dataset') return estimator = PoseNet(num_points=opt.num_points, num_obj=opt.num_objects) estimator.cuda() refiner = PoseRefineNet(num_points=opt.num_points, num_obj=opt.num_objects) refiner.cuda() if opt.resume_posenet != '': estimator.load_state_dict( torch.load('{0}/{1}'.format(opt.outf, opt.resume_posenet))) if opt.resume_refinenet != '': refiner.load_state_dict( torch.load('{0}/{1}'.format(opt.outf, opt.resume_refinenet))) opt.refine_start = True opt.decay_start = True opt.lr *= opt.lr_rate opt.w *= opt.w_rate opt.batch_size = int(opt.batch_size / opt.iteration) optimizer = optim.Adam(refiner.parameters(), lr=opt.lr) else: opt.refine_start = False opt.decay_start = False optimizer = optim.Adam(estimator.parameters(), lr=opt.lr) if opt.dataset == 'ycb': dataset = PoseDataset_ycb('train', opt.num_points, True, opt.dataset_root, opt.noise_trans, opt.refine_start) elif opt.dataset == 'linemod': dataset = PoseDataset_linemod('train', opt.num_points, True, opt.dataset_root, opt.noise_trans, opt.refine_start) dataloader = torch.utils.data.DataLoader(dataset, batch_size=1, shuffle=True, num_workers=opt.workers) if opt.dataset == 'ycb': test_dataset = PoseDataset_ycb('test', opt.num_points, False, opt.dataset_root, 0.0, opt.refine_start) elif opt.dataset == 'linemod': test_dataset = PoseDataset_linemod('test', opt.num_points, False, opt.dataset_root, 0.0, opt.refine_start) testdataloader = torch.utils.data.DataLoader(test_dataset, batch_size=1, shuffle=False, num_workers=opt.workers) opt.sym_list = dataset.get_sym_list() opt.num_points_mesh = dataset.get_num_points_mesh() print( '>>>>>>>>----------Dataset loaded!---------<<<<<<<<\nlength of the training set: {0}\nlength of the testing set: {1}\nnumber of sample points on mesh: {2}\nsymmetry object list: {3}' .format(len(dataset), len(test_dataset), opt.num_points_mesh, opt.sym_list)) criterion = Loss(opt.num_points_mesh, opt.sym_list) criterion_refine = Loss_refine(opt.num_points_mesh, opt.sym_list) best_test = np.Inf if opt.start_epoch == 1: for log in os.listdir(opt.log_dir): os.remove(os.path.join(opt.log_dir, log)) st_time = time.time() for epoch in range(opt.start_epoch, opt.nepoch): logger = setup_logger( 'epoch%d' % epoch, os.path.join(opt.log_dir, 'epoch_%d_log.txt' % epoch)) logger.info('Train time {0}'.format( time.strftime("%Hh %Mm %Ss", time.gmtime(time.time() - st_time)) + ', ' + 'Training started')) train_count = 0 train_dis_avg = 0.0 if opt.refine_start: estimator.eval() refiner.train() else: estimator.train() optimizer.zero_grad() for rep in range(opt.repeat_epoch): for i, data in enumerate(dataloader, 0): points, choose, img, target, model_points, idx = data points, choose, img, target, model_points, idx = Variable(points).cuda(), \ Variable(choose).cuda(), \ Variable(img).cuda(), \ Variable(target).cuda(), \ Variable(model_points).cuda(), \ Variable(idx).cuda() pred_r, pred_t, pred_c, emb = estimator( img, points, choose, idx) loss, dis, new_points, new_target = criterion( pred_r, pred_t, pred_c, target, model_points, idx, points, opt.w, opt.refine_start) if opt.refine_start: for ite in range(0, opt.iteration): pred_r, pred_t = refiner(new_points, emb, idx) dis, new_points, new_target = criterion_refine( pred_r, pred_t, new_target, model_points, idx, new_points) dis.backward() else: loss.backward() train_dis_avg += dis.item() train_count += 1 if train_count % opt.batch_size == 0: logger.info( 'Train time {0} Epoch {1} Batch {2} Frame {3} Avg_dis:{4}' .format( time.strftime("%Hh %Mm %Ss", time.gmtime(time.time() - st_time)), epoch, int(train_count / opt.batch_size), train_count, train_dis_avg / opt.batch_size)) optimizer.step() optimizer.zero_grad() train_dis_avg = 0 if train_count != 0 and train_count % 1000 == 0: if opt.refine_start: torch.save( refiner.state_dict(), '{0}/pose_refine_model_current.pth'.format( opt.outf)) else: torch.save( estimator.state_dict(), '{0}/pose_model_current.pth'.format(opt.outf)) print( '>>>>>>>>----------epoch {0} train finish---------<<<<<<<<'.format( epoch)) logger = setup_logger( 'epoch%d_test' % epoch, os.path.join(opt.log_dir, 'epoch_%d_test_log.txt' % epoch)) logger.info('Test time {0}'.format( time.strftime("%Hh %Mm %Ss", time.gmtime(time.time() - st_time)) + ', ' + 'Testing started')) test_dis = 0.0 test_count = 0 estimator.eval() refiner.eval() for j, data in enumerate(testdataloader, 0): points, choose, img, target, model_points, idx = data points, choose, img, target, model_points, idx = Variable(points).cuda(), \ Variable(choose).cuda(), \ Variable(img).cuda(), \ Variable(target).cuda(), \ Variable(model_points).cuda(), \ Variable(idx).cuda() pred_r, pred_t, pred_c, emb = estimator(img, points, choose, idx) _, dis, new_points, new_target = criterion(pred_r, pred_t, pred_c, target, model_points, idx, points, opt.w, opt.refine_start) if opt.refine_start: for ite in range(0, opt.iteration): pred_r, pred_t = refiner(new_points, emb, idx) dis, new_points, new_target = criterion_refine( pred_r, pred_t, new_target, model_points, idx, new_points) test_dis += dis.item() logger.info('Test time {0} Test Frame No.{1} dis:{2}'.format( time.strftime("%Hh %Mm %Ss", time.gmtime(time.time() - st_time)), test_count, dis)) test_count += 1 test_dis = test_dis / test_count logger.info('Test time {0} Epoch {1} TEST FINISH Avg dis: {2}'.format( time.strftime("%Hh %Mm %Ss", time.gmtime(time.time() - st_time)), epoch, test_dis)) if test_dis <= best_test: best_test = test_dis if opt.refine_start: torch.save( refiner.state_dict(), '{0}/pose_refine_model_{1}_{2}.pth'.format( opt.outf, epoch, test_dis)) else: torch.save( estimator.state_dict(), '{0}/pose_model_{1}_{2}.pth'.format( opt.outf, epoch, test_dis)) print(epoch, '>>>>>>>>----------BEST TEST MODEL SAVED---------<<<<<<<<') if best_test < opt.decay_margin and not opt.decay_start: opt.decay_start = True opt.lr *= opt.lr_rate opt.w *= opt.w_rate optimizer = optim.Adam(estimator.parameters(), lr=opt.lr) if best_test < opt.refine_margin and not opt.refine_start: opt.refine_start = True opt.batch_size = int(opt.batch_size / opt.iteration) optimizer = optim.Adam(refiner.parameters(), lr=opt.lr) if opt.dataset == 'ycb': dataset = PoseDataset_ycb('train', opt.num_points, True, opt.dataset_root, opt.noise_trans, opt.refine_start) elif opt.dataset == 'linemod': dataset = PoseDataset_linemod('train', opt.num_points, True, opt.dataset_root, opt.noise_trans, opt.refine_start) dataloader = torch.utils.data.DataLoader(dataset, batch_size=1, shuffle=True, num_workers=opt.workers) if opt.dataset == 'ycb': test_dataset = PoseDataset_ycb('test', opt.num_points, False, opt.dataset_root, 0.0, opt.refine_start) elif opt.dataset == 'linemod': test_dataset = PoseDataset_linemod('test', opt.num_points, False, opt.dataset_root, 0.0, opt.refine_start) testdataloader = torch.utils.data.DataLoader( test_dataset, batch_size=1, shuffle=False, num_workers=opt.workers) opt.sym_list = dataset.get_sym_list() opt.num_points_mesh = dataset.get_num_points_mesh() print( '>>>>>>>>----------Dataset loaded!---------<<<<<<<<\nlength of the training set: {0}\nlength of the testing set: {1}\nnumber of sample points on mesh: {2}\nsymmetry object list: {3}' .format(len(dataset), len(test_dataset), opt.num_points_mesh, opt.sym_list)) criterion = Loss(opt.num_points_mesh, opt.sym_list) criterion_refine = Loss_refine(opt.num_points_mesh, opt.sym_list)
obj_name_list = [ 'ape', 'benchvise', 'cam', 'can', 'cat', 'driller', 'duck', 'eggbox', 'glue', 'holepuncher', 'iron', 'lamp', 'phone' ] output_result_dir = 'experiments/eval_result/linemod' for id, obj_id in enumerate(obj_list): obj_name = obj_name_list[all_obj_list.index(obj_id)] fw = open('{0}/{1}.txt'.format(output_result_dir, obj_name), 'w') model_list = sorted( os.listdir('trained_checkpoints/linemod/{}'.format(obj_name))) trained_model = 'trained_checkpoints/linemod/{}/{}'.format( obj_name, model_list[0]) refine_model = 'trained_checkpoints/linemod/{}/{}'.format( obj_name, model_list[1]) estimator = PoseNet(num_points=num_points, num_vote=num_vote, num_obj=1) estimator.cuda() estimator.load_state_dict(torch.load(trained_model)) estimator.eval() refiner = PoseRefineNet(num_points=num_points, num_obj=1) refiner.cuda() refiner.load_state_dict(torch.load(refine_model)) refiner.eval() testdataset = PoseDataset_linemod('eval', num_points, opt.dataset_root, True, False, False, obj_id) testdataloader = torch.utils.data.DataLoader(testdataset, batch_size=1, shuffle=False, num_workers=1) for i, data in enumerate(testdataloader, 0):
def main(): # opt.manualSeed = random.randint(1, 10000) # # opt.manualSeed = 1 # random.seed(opt.manualSeed) # torch.manual_seed(opt.manualSeed) torch.set_printoptions(threshold=5000) if opt.dataset == 'ycb': opt.num_objects = 21 #number of object classes in the dataset opt.num_points = 1000 #number of points on the input pointcloud opt.outf = 'trained_models/ycb' #folder to save trained models opt.log_dir = 'experiments/logs/ycb' #folder to save logs opt.repeat_epoch = 3 #number of repeat times for one epoch training elif opt.dataset == 'linemod': opt.num_objects = 13 opt.num_points = 500 opt.outf = 'trained_models/linemod' opt.log_dir = 'experiments/logs/linemod' opt.repeat_epoch = 20 else: print('Unknown dataset') return opt.estimator = PoseNet(num_points=opt.num_points, num_obj=opt.num_objects) # estimator.cuda() refiner = PoseRefineNet(num_points=opt.num_points, num_obj=opt.num_objects) # refiner.cuda() class_id = 1 opt.symmetry = {} with open('symmetries_ordered.txt', 'r') as f: while 1: line = f.readline() line = line[:-1] if not line: break opt.symmetry[class_id] = {} opt.symmetry[class_id]['center'] = list( map(lambda x: float(x), line.split(' '))) opt.symmetry[class_id]['mirror'] = [] for i in range(3): line = f.readline() line = line[:-1] x, y, z = list(map(lambda x: float(x), line.split(' '))) if not (x == 0 and y == 0 and z == 0): opt.symmetry[class_id]['mirror'].append((x, y, z)) f.readline() f.readline() class_id += 1 opt.norm = transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]) criterion = Loss(opt.num_points, opt.symmetry) opt.estimator.load_state_dict( torch.load('{0}/pose_model_64_0.0.pth'.format(opt.outf), map_location='cpu')) # import pdb;pdb.set_trace() print('start parallelization') pool = Pool(4) results = [ pool.apply_async(printCurve, [take_idx, criterion]) for take_idx in range(3) ] for take_idx in range(3): prec, recall = results[take_idx].get() # prec,recall = printCurve(take_idx, criterion) for dist_idx in range(5): plt.plot(recall[dist_idx], prec[dist_idx], label='dis={:.2f}'.format((dist_idx + 1) * 0.01)) plt.axis([0, 1, 0, 1]) plt.xlabel('Recall') plt.ylabel('Precision') plt.title(title_list[take_idx]) plt.legend() plt.savefig('prec-recall-{}.png'.format(title_list[take_idx])) plt.clf()
def main(): # g13: parameter setting ------------------- ''' posemodel is trained_checkpoints/linemod/pose_model_9_0.01310166542980859.pth refine model is trained_checkpoints/linemod/pose_refine_model_493_0.006761023565178073.pth ''' objlist = [1, 2, 4, 5, 6, 8, 9, 10, 11, 12, 13, 14, 15] knn = KNearestNeighbor(1) opt.dataset ='linemod' opt.dataset_root = './datasets/linemod/Linemod_preprocessed' estimator_path = 'trained_checkpoints/linemod/pose_model_9_0.01310166542980859.pth' refiner_path = 'trained_checkpoints/linemod/pose_refine_model_493_0.006761023565178073.pth' opt.model = estimator_path opt.refine_model = refiner_path dataset_config_dir = 'datasets/linemod/dataset_config' output_result_dir = 'experiments/eval_result/linemod' opt.refine_start = True bs = 1 #fixed because of the default setting in torch.utils.data.DataLoader opt.iteration = 2 #default is 4 in eval_linemod.py t1_start = True t1_idx = 0 t1_total_eval_num = 3 t2_start = False t2_target_list = [22, 30, 172, 187, 267, 363, 410, 471, 472, 605, 644, 712, 1046, 1116, 1129, 1135, 1263] #t2_target_list = [0, 1] axis_range = 0.1 # the length of X, Y, and Z axis in 3D vimg_dir = 'verify_img' diameter = [] meta_file = open('{0}/models_info.yml'.format(dataset_config_dir), 'r') meta_d = yaml.load(meta_file) for obj in objlist: diameter.append(meta_d[obj]['diameter'] / 1000.0 * 0.1) print(diameter) if not os.path.exists(vimg_dir): os.makedirs(vimg_dir) #------------------------------------------- if opt.dataset == 'ycb': opt.num_objects = 21 #number of object classes in the dataset opt.num_points = 1000 #number of points on the input pointcloud opt.outf = 'trained_models/ycb' #folder to save trained models opt.log_dir = 'experiments/logs/ycb' #folder to save logs opt.repeat_epoch = 1 #number of repeat times for one epoch training elif opt.dataset == 'linemod': opt.num_objects = 13 opt.num_points = 500 opt.outf = 'trained_models/linemod' opt.log_dir = 'experiments/logs/linemod' opt.repeat_epoch = 20 else: print('Unknown dataset') return estimator = PoseNet(num_points = opt.num_points, num_obj = opt.num_objects) estimator.cuda() refiner = PoseRefineNet(num_points = opt.num_points, num_obj = opt.num_objects) refiner.cuda() estimator.load_state_dict(torch.load(estimator_path)) refiner.load_state_dict(torch.load(refiner_path)) opt.refine_start = True test_dataset = PoseDataset_linemod('test', opt.num_points, False, opt.dataset_root, 0.0, opt.refine_start) testdataloader = torch.utils.data.DataLoader(test_dataset, batch_size=1, shuffle=False, num_workers=opt.workers) opt.sym_list = test_dataset.get_sym_list() opt.num_points_mesh = test_dataset.get_num_points_mesh() print('>>>>>>>>----------Dataset loaded!---------<<<<<<<<\n\ length of the testing set: {0}\nnumber of sample points on mesh: {1}\n\ symmetry object list: {2}'\ .format( len(test_dataset), opt.num_points_mesh, opt.sym_list)) #load pytorch model estimator.eval() refiner.eval() criterion = Loss(opt.num_points_mesh, opt.sym_list) criterion_refine = Loss_refine(opt.num_points_mesh, opt.sym_list) fw = open('{0}/t1_eval_result_logs.txt'.format(output_result_dir), 'w') #Pose estimation for j, data in enumerate(testdataloader, 0): # g13: modify this part for evaluation target-------------------- if t1_start and j == t1_total_eval_num: break if t2_start and not (j in t2_target_list): continue #---------------------------------------------------------------- points, choose, img, target, model_points, idx = data if len(points.size()) == 2: print('No.{0} NOT Pass! Lost detection!'.format(j)) fw.write('No.{0} NOT Pass! Lost detection!\n'.format(j)) continue points, choose, img, target, model_points, idx = Variable(points).cuda(), \ Variable(choose).cuda(), \ Variable(img).cuda(), \ Variable(target).cuda(), \ Variable(model_points).cuda(), \ Variable(idx).cuda() pred_r, pred_t, pred_c, emb = estimator(img, points, choose, idx) _, dis, new_points, new_target = criterion(pred_r, pred_t, pred_c, target, model_points, idx, points, opt.w, opt.refine_start) #if opt.refine_start: #iterative poserefinement # for ite in range(0, opt.iteration): # pred_r, pred_t = refiner(new_points, emb, idx) # dis, new_points, new_target = criterion_refine(pred_r, pred_t, new_target, model_points, idx, new_points) pred_r = pred_r / torch.norm(pred_r, dim=2).view(1, opt.num_points, 1) pred_c = pred_c.view(bs, opt.num_points) how_max, which_max = torch.max(pred_c, 1) pred_t = pred_t.view(bs * opt.num_points, 1, 3) my_r = pred_r[0][which_max[0]].view(-1).cpu().data.numpy() my_t = (points.view(bs * opt.num_points, 1, 3) + pred_t)[which_max[0]].view(-1).cpu().data.numpy() my_pred = np.append(my_r, my_t) for ite in range(0, opt.iteration): T = Variable(torch.from_numpy(my_t.astype(np.float32))).cuda().view(1, 3).repeat(opt.num_points, 1).contiguous().view(1, opt.num_points, 3) my_mat = quaternion_matrix(my_r) R = Variable(torch.from_numpy(my_mat[:3, :3].astype(np.float32))).cuda().view(1, 3, 3) my_mat[0:3, 3] = my_t new_points = torch.bmm((points - T), R).contiguous() pred_r, pred_t = refiner(new_points, emb, idx) pred_r = pred_r.view(1, 1, -1) pred_r = pred_r / (torch.norm(pred_r, dim=2).view(1, 1, 1)) my_r_2 = pred_r.view(-1).cpu().data.numpy() my_t_2 = pred_t.view(-1).cpu().data.numpy() my_mat_2 = quaternion_matrix(my_r_2) my_mat_2[0:3, 3] = my_t_2 my_mat_final = np.dot(my_mat, my_mat_2) my_r_final = copy.deepcopy(my_mat_final) my_r_final[0:3, 3] = 0 my_r_final = quaternion_from_matrix(my_r_final, True) my_t_final = np.array([my_mat_final[0][3], my_mat_final[1][3], my_mat_final[2][3]]) my_pred = np.append(my_r_final, my_t_final) my_r = my_r_final my_t = my_t_final # Here 'my_pred' is the final pose estimation result after refinement ('my_r': quaternion, 'my_t': translation) #g13: checking the dis value success_count = [0 for i in range(opt.num_objects)] num_count = [0 for i in range(opt.num_objects)] model_points = model_points[0].cpu().detach().numpy() my_r = quaternion_matrix(my_r)[:3, :3] pred = np.dot(model_points, my_r.T) + my_t target = target[0].cpu().detach().numpy() if idx[0].item() in opt.sym_list: pred = torch.from_numpy(pred.astype(np.float32)).cuda().transpose(1, 0).contiguous() target = torch.from_numpy(target.astype(np.float32)).cuda().transpose(1, 0).contiguous() inds = knn(target.unsqueeze(0), pred.unsqueeze(0)) target = torch.index_select(target, 1, inds.view(-1) - 1) dis = torch.mean(torch.norm((pred.transpose(1, 0) - target.transpose(1, 0)), dim=1), dim=0).item() else: dis = np.mean(np.linalg.norm(pred - target, axis=1)) if dis < diameter[idx[0].item()]: success_count[idx[0].item()] += 1 print('No.{0} Pass! Distance: {1}'.format(j, dis)) fw.write('No.{0} Pass! Distance: {1}\n'.format(j, dis)) else: print('No.{0} NOT Pass! Distance: {1}'.format(j, dis)) fw.write('No.{0} NOT Pass! Distance: {1}\n'.format(j, dis)) num_count[idx[0].item()] += 1 # g13: start drawing pose on image------------------------------------ # pick up image print('{0}:\nmy_r is {1}\nmy_t is {2}\ndis:{3}'.format(j, my_r, my_t, dis.item())) print("index {0}: {1}".format(j, test_dataset.list_rgb[j])) img = Image.open(test_dataset.list_rgb[j]) # pick up center position by bbox meta_file = open('{0}/data/{1}/gt.yml'.format(opt.dataset_root, '%02d' % test_dataset.list_obj[j]), 'r') meta = {} meta = yaml.load(meta_file) which_item = test_dataset.list_rank[j] which_obj = test_dataset.list_obj[j] which_dict = 0 dict_leng = len(meta[which_item]) #print('get meta[{0}][{1}][obj_bb]'.format(which_item, which_obj)) k_idx = 0 while 1: if meta[which_item][k_idx]['obj_id'] == which_obj: which_dict = k_idx break k_idx = k_idx+1 bbx = meta[which_item][which_dict]['obj_bb'] draw = ImageDraw.Draw(img) # draw box (ensure this is the right object) draw.line((bbx[0],bbx[1], bbx[0], bbx[1]+bbx[3]), fill=(255,0,0), width=5) draw.line((bbx[0],bbx[1], bbx[0]+bbx[2], bbx[1]), fill=(255,0,0), width=5) draw.line((bbx[0],bbx[1]+bbx[3], bbx[0]+bbx[2], bbx[1]+bbx[3]), fill=(255,0,0), width=5) draw.line((bbx[0]+bbx[2],bbx[1], bbx[0]+bbx[2], bbx[1]+bbx[3]), fill=(255,0,0), width=5) #get center c_x = bbx[0]+int(bbx[2]/2) c_y = bbx[1]+int(bbx[3]/2) draw.point((c_x,c_y), fill=(255,255,0)) print('center:({0},{1})'.format(c_x, c_y)) #get the 3D position of center cam_intrinsic = np.zeros((3,3)) cam_intrinsic.itemset(0, test_dataset.cam_fx) cam_intrinsic.itemset(4, test_dataset.cam_fy) cam_intrinsic.itemset(2, test_dataset.cam_cx) cam_intrinsic.itemset(5, test_dataset.cam_cy) cam_intrinsic.itemset(8, 1) cam_extrinsic = my_mat_final[0:3, :] cam2d_3d = np.matmul(cam_intrinsic, cam_extrinsic) cen_3d = np.matmul(np.linalg.pinv(cam2d_3d), [[c_x],[c_y],[1]]) # replace img.show() with plt.imshow(img) #transpose three 3D axis point into 2D x_3d = cen_3d + [[axis_range],[0],[0],[0]] y_3d = cen_3d + [[0],[axis_range],[0],[0]] z_3d = cen_3d + [[0],[0],[axis_range],[0]] x_2d = np.matmul(cam2d_3d, x_3d) y_2d = np.matmul(cam2d_3d, y_3d) z_2d = np.matmul(cam2d_3d, z_3d) #draw the axis on 2D draw.line((c_x, c_y, x_2d[0], x_2d[1]), fill=(255,255,0), width=5) draw.line((c_x, c_y, y_2d[0], y_2d[1]), fill=(0,255,0), width=5) draw.line((c_x, c_y, z_2d[0], z_2d[1]), fill=(0,0,255), width=5) #g13: draw the estimate pred obj for pti in pred: pti.transpose() pti_2d = np.matmul(cam_intrinsic, pti) #print('({0},{1})\n'.format(int(pti_2d[0]),int(pti_2d[1]))) draw.point([int(pti_2d[0]),int(pti_2d[1])], fill=(255,255,0)) #g13: show image #img.show() #save file under file img_file_name = '{0}/batch{1}_pred_obj{2}_pic{3}.png'.format(vimg_dir, j, test_dataset.list_obj[j], which_item) img.save( img_file_name, "PNG" ) img.close() # plot ground true ---------------------------- img = Image.open(test_dataset.list_rgb[j]) draw = ImageDraw.Draw(img) draw.line((bbx[0],bbx[1], bbx[0], bbx[1]+bbx[3]), fill=(255,0,0), width=5) draw.line((bbx[0],bbx[1], bbx[0]+bbx[2], bbx[1]), fill=(255,0,0), width=5) draw.line((bbx[0],bbx[1]+bbx[3], bbx[0]+bbx[2], bbx[1]+bbx[3]), fill=(255,0,0), width=5) draw.line((bbx[0]+bbx[2],bbx[1], bbx[0]+bbx[2], bbx[1]+bbx[3]), fill=(255,0,0), width=5) target_r = np.resize(np.array(meta[which_item][k_idx]['cam_R_m2c']), (3, 3)) target_t = np.array(meta[which_item][k_idx]['cam_t_m2c']) target_t = target_t[np.newaxis, :] cam_extrinsic_GT = np.concatenate((target_r, target_t.T), axis=1) #get center 3D cam2d_3d_GT = np.matmul(cam_intrinsic, cam_extrinsic_GT) cen_3d_GT = np.matmul(np.linalg.pinv(cam2d_3d_GT), [[c_x],[c_y],[1]]) #transpose three 3D axis point into 2D x_3d = cen_3d_GT + [[axis_range],[0],[0],[0]] y_3d = cen_3d_GT + [[0],[axis_range],[0],[0]] z_3d = cen_3d_GT + [[0],[0],[axis_range],[0]] x_2d = np.matmul(cam2d_3d_GT, x_3d) y_2d = np.matmul(cam2d_3d_GT, y_3d) z_2d = np.matmul(cam2d_3d_GT, z_3d) #draw the axis on 2D draw.line((c_x, c_y, x_2d[0], x_2d[1]), fill=(255,255,0), width=5) draw.line((c_x, c_y, y_2d[0], y_2d[1]), fill=(0,255,0), width=5) draw.line((c_x, c_y, z_2d[0], z_2d[1]), fill=(0,0,255), width=5) print('pred:\n{0}\nGT:\n{1}\n'.format(cam_extrinsic,cam_extrinsic_GT)) print('pred 3D:{0}\nGT 3D:{1}\n'.format(cen_3d, cen_3d_GT)) img_file_name = '{0}/batch{1}_pred_obj{2}_pic{3}_gt.png'.format(vimg_dir, j, test_dataset.list_obj[j], which_item) img.save( img_file_name, "PNG" ) img.close() meta_file.close() print('\nplot_result_img.py completed the task\n')
#idx = 0 # object model points model_points_list = [] for idx in range(0, 2): model_points = posenet_deploy.get_model_points(idx) model_points = model_points[0].cpu().detach().numpy() model_points_list.append(model_points) model = "/home/tomo/densefusion/trained_models/tomo_blisters_2/pose_model_1_0.005430417195209802.pth" refine_model = "/home/tomo/densefusion/trained_models/tomo_blisters_2/pose_refine_model_63_0.0005920357997828468.pth" #model = "/home/tomo/densefusion/trained_models/tomo_blisters_invert/pose_model_1_0.005256925600131684.pth" #refine_model = "/home/tomo/densefusion/trained_models/tomo_blisters_invert/pose_refine_model_29_0.0005998273272780352.pth" estimator = PoseNet(num_points=num_points, num_obj=num_objects) estimator.cuda() refiner = PoseRefineNet(num_points=num_points, num_obj=num_objects) refiner.cuda() estimator.load_state_dict(torch.load(model)) refiner.load_state_dict(torch.load(refine_model)) estimator.eval() refiner.eval() def setup_config(): model_path = "/home/tomo/densefusion/MASK_RCNN_TOMO/trained_models/model_final_new.pth" cfg = get_cfg() cfg.merge_from_file( model_zoo.get_config_file( "COCO-InstanceSegmentation/mask_rcnn_R_101_FPN_3x.yaml"))
def main(): opt.manualSeed = random.randint(1, 10000) random.seed(opt.manualSeed) torch.manual_seed(opt.manualSeed) opt.num_objects = 3 opt.num_points = 500 opt.outf = 'trained_models' opt.log_dir = 'experiments/logs' opt.repeat_epoch = 20 estimator = PoseNet(num_points=opt.num_points, num_obj=opt.num_objects) estimator.cuda() refiner = PoseRefineNet(num_points=opt.num_points, num_obj=opt.num_objects) refiner.cuda() if opt.resume_posenet != '': estimator.load_state_dict( torch.load('{0}/{1}'.format(opt.outf, opt.resume_posenet))) if opt.resume_refinenet != '': refiner.load_state_dict( torch.load('{0}/{1}'.format(opt.outf, opt.resume_refinenet))) opt.refine_start = True opt.decay_start = True opt.lr *= opt.lr_rate opt.w *= opt.w_rate opt.batch_size = int(opt.batch_size / opt.iteration) optimizer = optim.Adam(refiner.parameters(), lr=opt.lr) else: opt.refine_start = False opt.decay_start = False optimizer = optim.Adam(estimator.parameters(), lr=opt.lr) dataset = PoseDataset('train', opt.num_points, True, opt.dataset_root, opt.noise_trans, opt.refine_start) dataloader = torch.utils.data.DataLoader(dataset, batch_size=1, shuffle=True, num_workers=opt.workers) test_dataset = PoseDataset('test', opt.num_points, False, opt.dataset_root, 0.0, opt.refine_start) testdataloader = torch.utils.data.DataLoader(test_dataset, batch_size=1, shuffle=False, num_workers=opt.workers) opt.sym_list = dataset.get_sym_list() opt.num_points_mesh = dataset.get_num_points_mesh() print( '>>>>>>>>----------Dataset loaded!---------<<<<<<<<\nlength of the training set: {0}\nlength of the testing set: {1}\nnumber of sample points on mesh: {2}' .format(len(dataset), len(test_dataset), opt.num_points_mesh)) criterion = Loss(opt.num_points_mesh, opt.sym_list) criterion_refine = Loss_refine(opt.num_points_mesh, opt.sym_list) best_test = np.Inf if opt.start_epoch == 1: for log in os.listdir(opt.log_dir): os.remove(os.path.join(opt.log_dir, log)) st_time = time.time() for epoch in range(opt.start_epoch, opt.nepoch): logger = setup_logger( 'epoch%d' % epoch, os.path.join(opt.log_dir, 'epoch_%d_log.txt' % epoch)) logger.info('Train time {0}'.format( time.strftime("%Hh %Mm %Ss", time.gmtime(time.time() - st_time)) + ', ' + 'Training started')) train_count = 0 train_dis_avg = 0.0 if opt.refine_start: estimator.eval() # affects dropout and batch normalization refiner.train() else: estimator.train() optimizer.zero_grad() for rep in range(opt.repeat_epoch): for i, data in enumerate(dataloader, 0): points, choose, img, target, model_points, idx = data #points ->torch.Size([500, 3]) ->在crop出来的像素区域随机选取500个点,利用相机内参结合深度值算出来的点云cloud #choose ->torch.Size([1, 500]) #img ->torch.Size([3, 80, 80]) #target ->torch.Size([500, 3]) ->真实模型上随机选取的mesh点进行ground truth pose变换后得到的点 #model_points ->torch.Size([500, 3]) ->真实模型上随机选取的mesh点在进行pose变换前的点 #idx ->torch.Size([1]) #tensor([4], device='cuda:0') #img和points对应rgb和点云信息,需要在网络内部fusion points, choose, img, target, model_points, idx = Variable(points).cuda(), \ Variable(choose).cuda(), \ Variable(img).cuda(), \ Variable(target).cuda(), \ Variable(model_points).cuda(), \ Variable(idx).cuda() pred_r, pred_t, pred_c, emb = estimator( img, points, choose, idx) loss, dis, new_points, new_target = criterion( pred_r, pred_t, pred_c, target, model_points, idx, points, opt.w, opt.refine_start) if opt.refine_start: for ite in range(0, opt.iteration): pred_r, pred_t = refiner(new_points, emb, idx) dis, new_points, new_target = criterion_refine( pred_r, pred_t, new_target, model_points, idx, new_points) dis.backward() else: loss.backward() train_dis_avg += dis.item() train_count += 1 if train_count % opt.batch_size == 0: logger.info( 'Train time {0} Epoch {1} Batch {2} Frame {3} Avg_dis:{4}' .format( time.strftime("%Hh %Mm %Ss", time.gmtime(time.time() - st_time)), epoch, int(train_count / opt.batch_size), train_count, train_dis_avg / opt.batch_size)) optimizer.step() optimizer.zero_grad() train_dis_avg = 0 if train_count != 0 and train_count % 1000 == 0: if opt.refine_start: torch.save( refiner.state_dict(), '{0}/pose_refine_model_current.pth'.format( opt.outf)) else: torch.save( estimator.state_dict(), '{0}/pose_model_current.pth'.format(opt.outf)) print( '>>>>>>>>----------epoch {0} train finish---------<<<<<<<<'.format( epoch)) logger = setup_logger( 'epoch%d_test' % epoch, os.path.join(opt.log_dir, 'epoch_%d_test_log.txt' % epoch)) logger.info('Test time {0}'.format( time.strftime("%Hh %Mm %Ss", time.gmtime(time.time() - st_time)) + ', ' + 'Testing started')) test_dis = 0.0 test_count = 0 estimator.eval() refiner.eval() for j, data in enumerate(testdataloader, 0): points, choose, img, target, model_points, idx = data points, choose, img, target, model_points, idx = Variable(points).cuda(), \ Variable(choose).cuda(), \ Variable(img).cuda(), \ Variable(target).cuda(), \ Variable(model_points).cuda(), \ Variable(idx).cuda() pred_r, pred_t, pred_c, emb = estimator(img, points, choose, idx) _, dis, new_points, new_target = criterion(pred_r, pred_t, pred_c, target, model_points, idx, points, opt.w, opt.refine_start) if opt.refine_start: for ite in range(0, opt.iteration): pred_r, pred_t = refiner(new_points, emb, idx) dis, new_points, new_target = criterion_refine( pred_r, pred_t, new_target, model_points, idx, new_points) test_dis += dis.item() logger.info('Test time {0} Test Frame No.{1} dis:{2}'.format( time.strftime("%Hh %Mm %Ss", time.gmtime(time.time() - st_time)), test_count, dis)) test_count += 1 test_dis = test_dis / test_count logger.info('Test time {0} Epoch {1} TEST FINISH Avg dis: {2}'.format( time.strftime("%Hh %Mm %Ss", time.gmtime(time.time() - st_time)), epoch, test_dis)) if test_dis <= best_test: best_test = test_dis if opt.refine_start: torch.save( refiner.state_dict(), '{0}/pose_refine_model_{1}_{2}.pth'.format( opt.outf, epoch, test_dis)) else: torch.save( estimator.state_dict(), '{0}/pose_model_{1}_{2}.pth'.format( opt.outf, epoch, test_dis)) print(epoch, '>>>>>>>>----------BEST TEST MODEL SAVED---------<<<<<<<<') if best_test < opt.decay_margin and not opt.decay_start: opt.decay_start = True opt.lr *= opt.lr_rate opt.w *= opt.w_rate optimizer = optim.Adam(estimator.parameters(), lr=opt.lr) if best_test < opt.refine_margin and not opt.refine_start: opt.refine_start = True opt.batch_size = int(opt.batch_size / opt.iteration) optimizer = optim.Adam(refiner.parameters(), lr=opt.lr) dataset = PoseDataset('train', opt.num_points, True, opt.dataset_root, opt.noise_trans, opt.refine_start) dataloader = torch.utils.data.DataLoader(dataset, batch_size=1, shuffle=True, num_workers=opt.workers) test_dataset = PoseDataset('test', opt.num_points, False, opt.dataset_root, 0.0, opt.refine_start) testdataloader = torch.utils.data.DataLoader( test_dataset, batch_size=1, shuffle=False, num_workers=opt.workers) opt.sym_list = dataset.get_sym_list() opt.num_points_mesh = dataset.get_num_points_mesh() print( '>>>>>>>>----------Dataset loaded!---------<<<<<<<<\nlength of the training set: {0}\nlength of the testing set: {1}\nnumber of sample points on mesh: {2}' .format(len(dataset), len(test_dataset), opt.num_points_mesh)) criterion = Loss(opt.num_points_mesh, opt.sym_list) criterion_refine = Loss_refine(opt.num_points_mesh, opt.sym_list)