Jiawei-Yao0812 / NDCScene

Official implementation for the ICCV 2023 paper "NDC-Scene: Boost Monocular 3D Semantic Scene Completion in Normalized Device Coordinates Space"
31 stars 3 forks source link

train my dataset #6

Closed lzbushicai closed 4 months ago

lzbushicai commented 9 months ago

Thank you for your outstanding work. I want to use your model to train my dataset. My dataset contains RGB images and semantic information. how can process my dataset? Also, how can I use your existing model to detect my images?

Jiawei-Yao0812 commented 5 months ago

Hi @lzbushicai , sorry for the late reply as i have been busy recently. I hope your problem has been successfully solved.

If not, you could try to voxelise the LiDAR data into a voxel grid and feed into dataloader we provided (change nedd to be made according to your own dataset).

lzbushicai commented 5 months ago

I have solved my problems!!! thank you