GitLab

* 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>

* Download DeepLabV3 if not available yet

* Fix dtype issue

Fix RuntimeError: expected backend CPU and dtype Float but got backend CPU and dtype Long

* 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

If there are less than half of model_cfg.NUM_KEYPOINTS it will lead to 
RuntimeError: unsupported operation: some elements of the input tensor and the written-to tensor refer to a single memory location. 
Please clone() the tensor before performing the operation.

caused by `features` in pointnet2_backbone.py:78, which is possible to be a non-contiguous tensor, being directly passed into SA_modules without calling .contiguous()

support more flexible setting of conv head; slice inputs when batch size is too large in PFNLayer to avoid bugs (#124)

* support more flexible setting

* slice inputs of nn.Linear when batch size is too large

support more flexible setting of conv head; slice inputs when batch size is too large in PFNLayer to avoid bugs (#124)

* support more flexible setting

* slice inputs of nn.Linear when batch size is too large

all model codes refactoring for training/testing, support multiple 3D detectors (SECOND, PartA2-Net (official release), PV-RCNN (official release))