Sun Jiahao

Step 1 : Recompile to add new bev_nms trt op. Step 2 : Download [checkpoints](https://download.openmmlab.com/mmdetection3d/v0.1.0_models/fcos3d/fcos3d_r101_caffe_fpn_gn-head_dcn_2x8_1x_nus-mono3d_finetune/fcos3d_r101_caffe_fpn_gn-head_dcn_2x8_1x_nus-mono3d_finetune_20210717_095645-8d806dc2.pth) in mmdet3d. Step 3 : Test command ```bash python tools/deploy.py \ configs/mmdet3d/monocular-detection/monocular-detection_tensorrt_static-928x1600.py \ ${PATH_TO_MMDET3D}/configs/fcos3d/fcos3d_r101_caffe_fpn_gn-head_dcn_2x8_1x_nus-mono3d.py \...

@Isaac-xie Have you updated mmdeploy to the latest version? You can check if `MonocularDetection` in your `mmdeploy/utils/constants.py`. If not, please pull the latest version to your own repo.

Thanks for your reminder, we'll re-test on windows and fix this!

You should use new [checkpoints](https://download.openmmlab.com/mmdetection3d/v1.1.0_models/bevfusion/bevfusion_lidar-cam_voxel0075_second_secfpn_8xb4-cyclic-20e_nus-3d-5239b1af.pth) in BEVFusion README.md

We've also noticed this issue and we'll fix it later on.

Not yet, we might have this plan after the Chinese New Year.

@eezhang123 `waymo-open-dataset-tf-2-6-0` is less compatible, so we put it in option.txt you can reinstall numpy==1.23.0 after installing `waymo-open-dataset-tf-2-6-0`.

@bigsheep2018 Is the training and validation infos generated properly? And also make sure you have the test dataset under your `data/waymo/waymo_format`.

Yes, [requirements/optional.txt](https://github.com/open-mmlab/mmdetection3d/blob/main/requirements/optional.txt). In my case, I reinstall `numpy==1.23.0` and mmdet3d can work properly. But, it doesn't necessarily apply to everyone. You can omit this warning `tensorflow 2.6.0 requires numpy~=1.19.2, but...

What version of system are you using, Windows/Linux ? And check the version of open3d in your environment.