目录

1. 下载dataset

2. 读取并做可视化

3. 源码阅读

3.1 读取点云数据-bin格式

3.2 读取标注数据-.label文件

3.3 读取配置

3.4 test

3.5 train

---

1. 下载dataset

以SemanticKITTI为例。下载链接：http://semantic-kitti.org/dataset.html#download

把上面三个下载下来。

 

同级目录下解压

unzip data_odometry_labels.zip
unzip data_odometry_velodyne.zip
unzip data_odometry_calib.zip

解压后文件夹形式：

2. 读取并做可视化

import open3d.ml.torch as ml3d  # or open3d.ml.tf as ml3d

# construct a dataset by specifying dataset_path
dataset = ml3d.datasets.SemanticKITTI(dataset_path='/home/zxq/data/kitti')

# get the 'all' split that combines training, validation and test set
all_split = dataset.get_split('all')

# print the attributes of the first datum
print(all_split.get_attr(0))

# print the shape of the first point cloud
print(all_split.get_data(0)['point'].shape)

# show the first 100 frames using the visualizer
vis = ml3d.vis.Visualizer()
vis.visualize_dataset(dataset, 'all', indices=range(100))

3. 源码阅读

3.1 读取点云数据-bin格式

SemanticKITTI的点云和标注数据都是二进制文件。

datatsets/utils/dataprocessing.py 

    @staticmethod
    def load_pc_kitti(pc_path):  # "./000000.bin"
        scan = np.fromfile(pc_path, dtype=np.float32)  # (num_pt*4,)
        scan = scan.reshape((-1, 4))    # # (num_pt,4)
        # points = scan[:, 0:3]  # get xyz
        points = scan
        return points

3.2 读取标注数据-.label文件

    def load_label_kitti(label_path, remap_lut):
        label = np.fromfile(label_path, dtype=np.uint32)
        label = label.reshape((-1))
        sem_label = label & 0xFFFF  # semantic label in lower half 
        inst_label = label >> 16  # instance id in upper half
        assert ((sem_label + (inst_label << 16) == label).all())
        sem_label = remap_lut[sem_label]
        return sem_label.astype(np.int32)

3.3 读取配置

模型，数据集，流程配置都保存在ml3d/configs/*.yaml文件中。读取方式：

import open3d.ml as _ml3d
import open3d.ml.torch as ml3d # or open3d.ml.tf as ml3d

framework = "torch" # or tf
cfg_file = "ml3d/configs/randlanet_semantickitti.yml"
cfg = _ml3d.utils.Config.load_from_file(cfg_file)

# fetch the classes by the name
Pipeline = _ml3d.utils.get_module("pipeline", cfg.pipeline.name, framework)
Model = _ml3d.utils.get_module("model", cfg.model.name, framework)
Dataset = _ml3d.utils.get_module("dataset", cfg.dataset.name)

# use the arguments in the config file to construct the instances
cfg.dataset['dataset_path'] = "/home/zxq/data/kitti"
dataset = Dataset(cfg.dataset.pop('dataset_path', None), **cfg.dataset)
model = Model(**cfg.model)
pipeline = Pipeline(model, dataset, **cfg.pipeline)

3.4 test

import os
import open3d.ml as _ml3d
import open3d.ml.torch as ml3d

cfg_file = "ml3d/configs/randlanet_semantickitti.yml"
cfg = _ml3d.utils.Config.load_from_file(cfg_file)

model = ml3d.models.RandLANet(**cfg.model)
cfg.dataset['dataset_path'] = "/home/zxq/data/kitti"
dataset = ml3d.datasets.SemanticKITTI(cfg.dataset.pop('dataset_path', None), **cfg.dataset)
pipeline = ml3d.pipelines.SemanticSegmentation(model, dataset=dataset, device="gpu", **cfg.pipeline)

# download the weights.
ckpt_folder = "./logs/"
os.makedirs(ckpt_folder, exist_ok=True)
ckpt_path = ckpt_folder + "randlanet_semantickitti_202201071330utc.pth"
randlanet_url = "https://storage.googleapis.com/open3d-releases/model-zoo/randlanet_semantickitti_202201071330utc.pth"
if not os.path.exists(ckpt_path):
    cmd = "wget {} -O {}".format(randlanet_url, ckpt_path)
    os.system(cmd)

# load the parameters.
pipeline.load_ckpt(ckpt_path=ckpt_path)

test_split = dataset.get_split("test")

# run inference on a single example.
# returns dict with 'predict_labels' and 'predict_scores'.
data = test_split.get_data(0)
result = pipeline.run_inference(data)

# evaluate performance on the test set; this will write logs to './logs'.
pipeline.run_test()

3.5 train

import open3d.ml.torch as ml3d

from ml3d.torch import RandLANet, SemanticSegmentation

# use a cache for storing the results of the preprocessing (default path is './logs/cache')
dataset = ml3d.datasets.SemanticKITTI(dataset_path='/home/zxq/data/kitti/', use_cache=True)

# create the model with random initialization.
model = RandLANet()

pipeline = SemanticSegmentation(model=model, dataset=dataset, max_epoch=100)

# prints training progress in the console.
pipeline.run_train()