网站建设应重视后期的服务和维护,怎么做班级网站,用自己的手机做网站,秦皇岛吧 百度贴吧目录
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#xff1a;http://semantic-kitti.org/dataset.html#download 把上面三…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, indicesrange(100)) 点云分割数据集SemanticKITTI 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 staticmethoddef load_pc_kitti(pc_path): # ./000000.binscan np.fromfile(pc_path, dtypenp.float32) # (num_pt*4,)scan scan.reshape((-1, 4)) # # (num_pt,4)# points scan[:, 0:3] # get xyzpoints scanreturn 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, dtypenp.uint32)label label.reshape((-1))sem_label label 0xFFFF # semantic label in lower half inst_label label 16 # instance id in upper halfassert ((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 ml3dframework 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 ml3dcfg_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, datasetdataset, devicegpu, **cfg.pipeline)# download the weights.
ckpt_folder ./logs/
os.makedirs(ckpt_folder, exist_okTrue)
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_pathckpt_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 ml3dfrom 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_cacheTrue)# create the model with random initialization.
model RandLANet()pipeline SemanticSegmentation(modelmodel, datasetdataset, max_epoch100)# prints training progress in the console.
pipeline.run_train()
