vis4d.op.detect3d.bevformer¶

BEVFormer ops.

class BEVFormerHead(num_classes=10, embed_dims=256, num_query=900, transformer=None, num_reg_fcs=2, num_cls_fcs=2, point_cloud_range=(-51.2, -51.2, -5.0, 51.2, 51.2, 3.0), bev_h=200, bev_w=200)[source]¶

BEVFormer 3D detection head.

Initialize BEVFormerHead.

Parameters:

num_classes (int, optional) – Number of classes. Defaults to 10.
embed_dims (int, optional) – Embedding dimensions. Defaults to 256.
num_query (int, optional) – Number of queries. Defaults to 900.
transformer (PerceptionTransformer, optional) – Transformer. Defaults to None. If None, a default transformer will be created.
num_reg_fcs (int, optional) – Number of fully connected layers in regression branch. Defaults to 2.
num_cls_fcs (int, optional) – Number of fully connected layers in classification branch. Defaults to 2.
point_cloud_range (Sequence[float], optional) – Point cloud range. Defaults to (-51.2, -51.2, -5.0, 51.2, 51.2, 3.0).
bev_h (int, optional) – BEV height. Defaults to 200.
bev_w (int, optional) – BEV width. Defaults to 200.

__call__(mlvl_feats, can_bus, images_hw, cam_intrinsics, cam_extrinsics, lidar_extrinsics, prev_bev=None)[source]¶

Type definition.

Return type:: tuple[Detect3DOut, Tensor]

forward(mlvl_feats, can_bus, images_hw, cam_intrinsics, cam_extrinsics, lidar_extrinsics, prev_bev=None)[source]¶

Forward function.

Parameters:

mlvl_feats (list[Tensor]) – Features from the upstream network, each is with shape (B, N, C, H, W).
can_bus (Tensor) – CAN bus data, with shape (B, 18).
images_hw (tuple[int, int]) – Image height and width.
cam_intrinsics (list[Tensor]) – Camera intrinsics.
cam_extrinsics (list[Tensor]) – Camera extrinsics.
lidar_extrinsics (list[Tensor]) – LiDAR extrinsics.
prev_bev (Tensor, optional) – Previous BEV feature map, with shape (B, C, H, W). Defaults to None.

Returns:

Detection results and BEV feature map.

Return type:

tuple[Detect3DOut, Tensor]

class GridMask(use_h, use_w, rotate=1, offset=False, ratio=0.5, mode=0, prob=1.0)[source]¶

Grid Mask Layer.

Init.

forward(x)[source]¶

Forward.

Return type:: Tensor

Modules

`vis4d.op.detect3d.bevformer.bevformer`	BEVFormer head.
`vis4d.op.detect3d.bevformer.decoder`	BEVFormer decoder.
`vis4d.op.detect3d.bevformer.encoder`	BEVFormer Encoder.
`vis4d.op.detect3d.bevformer.grid_mask`	Grid mask for BEVFormer.
`vis4d.op.detect3d.bevformer.spatial_cross_attention`	Spatial Cross Attention Module for BEVFormer.
`vis4d.op.detect3d.bevformer.temporal_self_attention`	An attention module used in BEVFormer based on Deformable-Detr.
`vis4d.op.detect3d.bevformer.transformer`	BEVFormer transformer.