search

sshaoshuai / PointRCNN

PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud, CVPR 2019.
MIT License
1.71k stars 425 forks source link

What't the function of 'images' in training model using PointRCNN? #213

Closed OrangeSodahub closed 1 year ago

OrangeSodahub commented 2 years ago

Hello, here I want to train a model using PointRCNN but I only have pointclouds and labels files. And I occured this while training:

2022-04-25 12:35:12,630   INFO  **********************Start training**********************
epochs:   0%|                                           | 0/10 [00:01<?, ?it/s]
train:   0%|                                            | 0/26 [00:00<?, ?it/sTraceback (most recent call last):                                              
  File "train_rcnn.py", line 243, in <module>
    trainer.train(
    assert os.path.exists(img_file)
AssertionError

Is anyone could tell me why images dataset is required during this process? What's more, 'calib' file is also necessary for training but why? PointRCNN train models using only pointcloud data, right?

gehadza commented 1 year ago

Hi! I want to implement pointrcnn on Windows? how to do this please I follow the instruction but this error appear "error: command 'C:\Program Files (x86)\Microsoft Visual Studio\2017\Community\VC\Tools\MSVC\14.16.27023\bin\HostX86\x64\cl.exe' failed with exit code 2" when run execute build_and_install.sh on WIN10?