search

yinjunbo / SSDA3D

Thie repo provides the official implementation of our AAAI-2023 paper “SSDA3D: Semi-supervised Domain Adaptation for 3D Object Detection from Point Cloud”.
Apache License 2.0
44 stars 2 forks source link

How did you generate the partial_info_data #7

Open fdy61 opened 1 day ago

fdy61 commented 1 day ago

How did you generate the partial_info_data (1%, 5%, 10%, 20%)? For example, for the 1% data, did you take the first 1% of the info from the complete info.pkl file and split it into the top 1% and the last 99% of the pkl file? Or did you randomly sample 1% of the total amount of samples?

yinjunbo commented 1 day ago

Hi, we uniformly downsampled the data in a frame level, like data[::interval]

On Mon, 1 Jul 2024 at 09:49, fdy61 @.***> wrote:

How did you generate the partial_info_data (1%, 5%, 10%, 20%)? For example, for the 1% data, did you take the first 1% of the info from the complete info.pkl file and split it into the top 1% and the last 99% of the pkl file? Or did you randomly sample 1% of the total amount of samples?

— Reply to this email directly, view it on GitHub https://github.com/yinjunbo/SSDA3D/issues/7, or unsubscribe https://github.com/notifications/unsubscribe-auth/AHCPIYOI326R6JV3TXA3L5LZKD3WFAVCNFSM6AAAAABKE5O2UKVHI2DSMVQWIX3LMV43ASLTON2WKOZSGM4DEOJZGEZDAMA . You are receiving this because you are subscribed to this thread.Message ID: @.***>

fdy61 commented 1 day ago

Thanks. And What are the versions of TensorFlow and waymo-open-dataset-tf you are using? Also, what are your Python and PyTorch versions? I am encountering difficult environment issues.