Abhinav Kumar | अभिनव कुमार

icon indicating a website link https://sites.google.com/view/abhinavkumar icon indicating an email [email protected]

icon company Samsung Research America icon location San Francisco Bay Area, CA icon location 3D Computer Vision Researcher

Results 14 comments of Abhinav Kumar | अभिनव कुमार

nan loss after 5 epochs on custom dataset

> Hi,I have the same problem as you. How do you solve it > Hi, I set batch size = 1, but the issue of nan loss is still after...

nan loss after 5 epochs on custom dataset

@15171452351 @zhaowei0315 The GUPNet codebase does not compute 2D and 3D losses when there are empty images (no foreground objects) in a batch. We fix this bug with this [commit](https://github.com/abhi1kumar/DEVIANT/commit/3d1f31509848232a1325546985081da82a87162b)....

Testing HoP with nuScenes mini Split

Hi @MangoDragon Thank you for your interest in SeaBird. > Is it possible to test HoP without using the full (very large) dataset from nuscenes or training it? I would...

Testing HoP with nuScenes mini Split

> What should I use for the pkl? The `nuscenes_data_prep()` function should get the pkl files. The `add_ann_adj_info()` function in the [converter file](https://github.com/abhi1kumar/SeaBird/blob/main/HoP/tools/create_data_bevdet.py) works on pkl files created by the...