GitLab

Passing dist_train instead of dist as the to_cpu paremeter to the loading functions.

* add voxel roi pooling

* add voxel r-cnn head

* add voxel query

* add voxel r-cnn

* add Voxel R-CNN

* add infos about Voxel R-CNN

* add voxel_rcnn_car.yaml

* add infos about Voxel R-CNN
Co-authored-by: Shaoshuai Shi <shaoshuaics@gmail.com>

* Added CaDDN detector and support for image, depth map, and 2D GT box
dataloading

* Moved image flip augmentation to augmentor_utils

* Updated default get item list to include points

* Moved utils functions into transform_utils

* Combined FFE + F2V into ImageVFE, renamed FFE to FFN, moved depth downsample into data_processor

* Updated README with updated CaDDN weights

* Updated comments for image vfe

* support SECOND-IoU

* rename file

* modify readme and fix model name in __init__.py

* automatically find unused tcp port when mgpu train or test

* fixbug: set tcp_port before set python args

* Make TensorBoard more concise

* Export only metrics using 40 recalll positions

* bugfixed: support merge_all_iters_to_one_epoch in dataloader

support merge_all_iters_to_one_epoch to avoid deadlock when switching epochs, eval last 10 epochs after training