str: Return a string that describes the module.

str: Return a string that describes the module.

str: Return a string that describes the module.

str: Return a string that describes the module.

Parse bbox and mask annotation. Args: ann_info (list[dict]): Annotation info of an image. with_mask (bool): Whether t

GPU version of backward function. Args: grad_output (Tensor): Gradient of output tensor of forward.

GPU version of backward function. Args: grad_output (Tensor): Gradient of output tensor of forward.

Function: pillar pooling (backward, cuda) Args: out_grad : grad of output bev feature, FloatTensor[b, c, h_out, w_out] depth_grad

Function: pillar pooling (forward, cuda) Args: depth : input depth, FloatTensor[n, d, h, w] feat : input features, Fl

r"""A helper function for checkpointing sequential models. Sequential models execute a list of modules/functions in order (sequentially). The

Renders a detailed results table in tex. :param metrics_path: path to a serialized DetectionMetrics file. :param output_path: path to the

Plot the PR curves for different distance thresholds. :param md_list: DetectionMetricDataList instance. :param metrics: DetectionMetrics

Calls either forward_train or forward_test depending on whether return_loss=True. Note this setting will change the expected inputs. W

GPU version of multi-scale deformable attention. Args: value (Tensor): The value has shape (bs, num_keys, mum

GPU version of multi-scale deformable attention. Args: value (Tensor): The value has shape (bs, num_keys, mum

Forward Function of MultiScaleDeformAttention. Args: query (Tensor): Query of Transformer with shape (num_que

query_bbox: [B, Q, 10] [cx, cy, cz, w, h, d, rot.sin, rot.cos, vx, vy]

Transform image-view feature into bird-eye-view feature. Args: input (list(torch.tensor)): of (image-view feature, rots, trans,

Forward function.