Plot the true positive curve for the specified class. :param md_list: DetectionMetricDataList instance. :param metrics: DetectionMetrics

r""" Load meta data of data in data_dict, and store in a .pkl with split as file name. Parameters ---------- root_path : str

Returns: plane: H, W, 3

Returns: plane: H, W, 3

Convert keys in pycls pretrained RegNet models to mmdet style.

Convert keys in pycls pretrained RegNet models to mmdet style.

Create folder for data preprocessing.

Encode bitmap mask to RLE code. Semantic Masks only Args: mask_results (list | tuple[list]): bitmap mask results. In mask scor

r""" Parameters ---------- path : str Returns ------- np.ndarray

Decode bboxes. Args: cls_scores (Tensor): Outputs from the classification head, \ shape [num_query, cls_out_channe

Initialize from serialized content.

Calculate dice loss, which is proposed in `V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation <https://arxiv

3x3 convolution with padding

Evaluation in COCO protocol. Args: results (list[list | tuple]): Testing results of the dataset. metric (str | list[st

Evaluate prediction result based on `output_format` specified by dataset. Args: results (list[Tensor]): List of prediction result

Do evaluation for a submission file and print evalution results to `logger` if specified. The submission will be aligned by tokens before eva

Extract image feaftures and sum up into one pic Args: imgs: B, n_cam, C, iH, iW Returns:

Extract features of images.

Extract features of images.

Applies filtering to boxes. Distance, bike-racks and points per box. :param nusc: An instance of the NuScenes class. :param eval_boxes: A

format result for every sample of ConcatDataset.

Forward function. Args: feats (tuple[Tensor]): Features from the upstream network, each is a 4D-tensor.

Forward function. Args: mlvl_feats (tuple[Tensor]): Features from the upstream network, each is a 4D-tensor with