MotionNet SourceCode 解读[#1]-gen_data篇(part I)

首先这边要去解读这份MotionNet中资料前处理的gen_data.py程式码

接下来会记录每个区块的函数以及变数所代表的意义

---

hyperparameters

scenes = np.load('data/split.npy', allow_pickle=True).item().get(args.split)print("Split: {}, which contains {} scenes.".format(args.split, len(scenes)))

这边读取已经存下来的场景编号'scene_37' 'scene_34' 'scene_817'

gen_data()

    res_scenes = list()    for s in scenes:        s_id = s.split('_')[1]        res_scenes.append(int(s_id))

把场景的编号存起来

for scene_idx in res_scenes:        curr_scene = nusc.scene[scene_idx] #现在场景编号                first_sample_token = curr_scene['first_sample_token'] #取出第一个sample token        curr_sample = nusc.get('sample', first_sample_token) # 取出sample的资料        curr_sample_data = nusc.get('sample_data', curr_sample['data']['LIDAR_TOP']) #取出sample中 lidar的资料        save_data_dict_list = list()  # for storing consecutive sequences; the data consists of timestamps, points, etc        save_box_dict_list = list()  # for storing box annotations in consecutive sequences        save_instance_token_list = list()        adj_seq_cnt = 0        save_seq_cnt = 0  # only used for save data file name

 while curr_sample_data['next'] != '':        # Get the synchronized point clouds        all_pc, all_times, trans_matrices = \        LidarPointCloud.from_file_multisweep_bf_sample_data            (nusc, curr_sample_data,return_trans_matrix=True,                                   nsweeps_back=nsweeps_back,nsweeps_forward=nsweeps_forward)                  # Store point cloud of each sweep        pc = all_pc.points        _, sort_idx = np.unique(all_times, return_index=True)        unique_times = all_times[np.sort(sort_idx)]  # Preserve the item order in unique_times        num_sweeps = len(unique_times)                # 如果没有足够的past 跟 future sweeps的话 要跳过一些keyframe         #===================Skipping keyframe==============================        # Make sure we have sufficient past and future sweeps        if num_sweeps != (nsweeps_back + nsweeps_forward):            # Skip some keyframes if necessary            flag = False            for _ in range(num_keyframe_skipped + 1):                if curr_sample['next'] != '':                    curr_sample = nusc.get('sample', curr_sample['next'])                else:                    flag = True                    break            if flag:  # No more keyframes                break            else:                curr_sample_data = nusc.get('sample_data', curr_sample['data']['LIDAR_TOP'])            # Reset            adj_seq_cnt = 0            save_data_dict_list = list()            save_box_dict_list = list()            save_instance_token_list = list()            continue      #===================Skipping keyframe==============================

LidarPointCloud.from_file_multisweep_bf_sample_data :
回传aggregate完的pointcloud 简单来说就是把过去的跟未来几个frame的pointcloud同步到当下的frame 回传的是很多point cloud组合而成的点云集合 可以利用unique time来把它还原成对应时间的sweep

# Prepare data dictionary for the next step (ie, generating BEV maps)            save_data_dict = dict()            box_data_dict = dict()  # for remapping the instance ids, according to class_map            curr_token_list = list()                            for tid in range(num_sweeps):                _time = unique_times[tid]                # 回传相同元素的index位置                points_idx = np.where(all_times == _time)[0]                _pc = pc[:, points_idx] # 取出对应sweep时间当下的点云(4,nbr_points)                save_data_dict['pc_' + str(tid)] = _pc            save_data_dict['times'] = unique_times            save_data_dict['num_sweeps'] = num_sweeps            save_data_dict['trans_matrices'] = trans_matrices                        # Get the synchronized bounding boxes            # First, we need to iterate all the instances, and then retrieve their corresponding bounding boxes            num_instances = 0  # The number of instances within this sample            corresponding_sample_token = curr_sample_data['sample_token']            corresponding_sample_rec = nusc.get('sample', corresponding_sample_token)                        

这边的unique time 是指每个sweep对应到的时间 (长度=backward+forward sweeps nums)all_times是把每个sweep所有的点都对应到该sweep的时间 (ex:[1,1,1,1,1...1],总共23456个点就有23456个时间)每个sample 中有每个sensor的资讯以及这个sample下的annotations以及sample当下的时间,及前跟后一个frame的token idprint(save_data_dict.keys())会有 (pc_0 - pc_44 for test split), times, num_sweeps, trans_matrices