thom966
thom966
Thank you so much for your reply. I have modified the two files and tried to modify the config file myself. However, it complains about `info_style` variable, with the following...
Hello, I have one more question. Since KITTI dataset has only one front view image, the view transformer receives an input as `[B, T, C, H, W]` shape of `T=1`,...
I am facing the same problem. If you solved the issue, then could you please tell me how to solve it? Thank you.
Thank you so much for your sharing. Is it possible to inference the TensorRT model to measure mIoU?
I encountered the same problem. Did anyone solved this issue??
Could you please provide the vovnet.py file that you used when loading pre-trained weights?