Pretrained model could not detect 3d objects in my own point cloud data

[ArtashesH]

HI All, I have captured point cloud data from the zivid camera in ply format, from which I converted a .bin format by this code.

import numpy as np import pandas as pd from plyfile import PlyData

def convert_ply(input_path, output_path): plydata = PlyData.read(input_path) # read file data = plydata.elements[0].data # read data data_pd = pd.DataFrame(data) # convert to DataFrame data_np = np.zeros(data_pd.shape, dtype=np.float) # initialize array to store data property_names = data[0].dtype.names # read names of properties for i, name in enumerate( property_names): # read data by property data_np[:, i] = data_pd[name] data_np.astype(np.float32).tofile(output_path)

Then I gave generated file- test.bin to the pretrained model based on votenet.

python3 demo/pcd_demo.py test.bin configs/votenet/votenet_iouloss_8x8_scannet-3d-18class.py checkpoints/votenet_8x8_scannet-3d-18class_20210823_234503-cf8134fa.pth --show

After running the model cannot detect any object in the given point cloud. So is there any mistake, I am making while converting ply to bin, or the problem is in somewhere else?

[Tai-Wang]

Maybe you can compare your converted data with our provided demo data? It might be related to the different coordinate systems or points' coordinate scales?