fundamentalvision / BEVFormer

[ECCV 2022] This is the official implementation of BEVFormer, a camera-only framework for autonomous driving perception, e.g., 3D object detection and semantic map segmentation.
https://arxiv.org/abs/2203.17270
Apache License 2.0
3.4k stars 550 forks source link

Calculate G_FLOPs #69

Open AnnieYu0401 opened 2 years ago

AnnieYu0401 commented 2 years ago

Hi, could you share your code to calculate the GFLOPs. I try to use get_flops.py from mmdet3d to calculate, however, it doesn't work.

zhiqi-li commented 2 years ago

You should provide a dummy_metas for forward_dummy in https://github.com/zhiqi-li/BEVFormer/blob/master/projects/mmdet3d_plugin/bevformer/detectors/bevformer.py#L140.

admyxs commented 11 months ago

Hello, thank for your work, but i want to know what the input_shape is, or which command do you run? can you show it for me? thx