Kyongjun Kim
Kyongjun Kim
Hello, i got problem when i run rendering. message is like this. I tried to change versions with `export MESA_GL_VERSION_OVERRIDE, export MESA_GLSL_VERSION_OVERRIDE, export MESA_GLES_VERSION_OVERRIDE` but it didn't work. And i...
When i run python project.py build i get above message. I reinstalled libgl1-mesa-glx and checked whether it is installed by `apt-get list --installed` but still there's no libGL.so.1.2.0 in /usr/lib/x86_64-linux-gnu...
Thanks for your great work first. And I have some questions about the camera pose data. 1. As I understand, "final_camera_rotation" and "camera_rt_matrix" should have inverse relation. But when I...
Thanks for your awesome work. I trained the model following the instruction of README. But the quality of visualization is different from your results. Left figure is result from my...
Hello, Thanks for your code first. I hope to get scene graph file(objects.json, relationships.json) for new data. But I think I can get only visualization file with --vis and --use_pretrained....
The first argument of `bbox_overlaps` is anchors and the second is targets. But I think the order is reversed on `model.py line 236.` Am I missing something??
Hi. I have a question about inference. As I understand, teacher model is more robust than student model by EMA update and it is used for supervision(pseudo label). Then why...
 Hello. I trained your model on my custom dataset and its target data size is 2048x400 (width, height). When I train it with above config (resize 2048x400), its performance...
I use RTX 2080 Ti with 11GB memory but encountered CUDA out of memory. How much memory is needed per batch size 1?