PV-RCNN training results

Question

PV-RCNN training results

Opened this issue a year ago · 3 comments

I want to replicate your work, but the experimental results on the PV-RCNN model differ significantly, especially on pedestrians and bicycles. Can you provide me with your pre trained weight model or guide me on where I went wrong

Answer 1 · 2023-12-18T03:55:29.000Z

Hi @JunjieWang0528, thanks for your attention.
Do you use the lastest code and could you show me the training log of your experiment for analysis?

Answer 2 · 2023-12-21T02:09:27.000Z

I am using the latest code. Below is the training log of HSSDA under 1% data. There is a significant discrepancy between the results of pedestrian and bicycle inspections and your report

log_train_20231218-093958.txt

Answer 3 · 2023-12-25T10:49:27.000Z

Hi @JunjieWang0528
Following the 3DIoUMatch, the results reported in the paper are the averages of three different splits.
If you only conduct experiments on one split, generating different results is normal.