search

megvii-research / PETR

[ECCV2022] PETR: Position Embedding Transformation for Multi-View 3D Object Detection & [ICCV2023] PETRv2: A Unified Framework for 3D Perception from Multi-Camera Images
Other
879 stars 132 forks source link

code for petr-e version #103

Closed jianingwangind closed 1 year ago

jianingwangind commented 1 year ago

Will you release the code for petr-e? Or could you please share some implementation details? Thanks

yingfei1016 commented 1 year ago

Hi，

For PETR-e， you can refer to https://github.com/megvii-research/PETR/blob/main/projects/configs/petr/petr_vovnet_gridmask_p4_1600x640_trainval_cbgs.py , the pretrained weights is from dd3d (https://github.com/megvii-research/PETR/blob/main/projects/configs/petr/petr_vovnet_gridmask_p4_1600x640_trainval_cbgs.py#L243)

For PETRv2, you can refer to https://github.com/megvii-research/PETR/blob/main/projects/configs/denoise/petrv2_vovnet_gridmask_p4_1600x640_dn_trainval_60epoch.py

jianingwangind commented 1 year ago

Thanks a lot.

loserhou commented 6 months ago

Hi，

For PETR-e， you can refer to https://github.com/megvii-research/PETR/blob/main/projects/configs/petr/petr_vovnet_gridmask_p4_1600x640_trainval_cbgs.py , the pretrained weights is from dd3d (https://github.com/megvii-research/PETR/blob/main/projects/configs/petr/petr_vovnet_gridmask_p4_1600x640_trainval_cbgs.py#L243)

For PETRv2, you can refer to https://github.com/megvii-research/PETR/blob/main/projects/configs/denoise/petrv2_vovnet_gridmask_p4_1600x640_dn_trainval_60epoch.py

Could you please provide your final performance on the test set, or is it the best performance given in the paper?

loserhou commented 6 months ago

Thanks a lot.

Could you please provide your final performance on the test set?thanks!