Benchmark between async and synchronous inference interfaces. Sample runs for 20 demo images on K80 GPU, model - mask_rcnn_r50_fpn_1x: async

Pack all blocks in a stage into a ``ResLayer`` for DetectoRS.

Map rois to corresponding feature levels by scales. - scale < finest_scale * 2: level 0 - finest_scale * 2 <= scale < finest_scale *

Compute mask target for positive proposals in multiple images. Args: pos_proposals_list (list[Tensor]): Positive proposals in multiple

Merge augmented proposals (multiscale, flip, etc.) Args: aug_proposals (list[Tensor]): proposals from different testing schem

Merge augmented detection bboxes and scores. Args: aug_bboxes (list[Tensor]): shape (n, 4*#class) aug_scores (list[Te

Warpper of mse loss.

Compute negative bag loss. :math:`FL((1 - P_{a_{j} \in A_{+}}) * (1 - P_{j}^{bg}))`. :math:`P_{a_{j} \in A_{+}}`: Box_probability of

Suppress bounding boxes according to their IoUs and confidence scores. Args: bbox (array): Bounding boxes to be transformed. The shape is

nn.Module: normalization layer after the first convolution layer

nn.Module: the normalization layer named "norm1"

nn.Module: the normalization layer named "norm2"

nn.Module: normalization layer after the second convolution layer

Parse information from a line in a requirements text file.

Patch the forward method of a module. Args: func (callable): The original forward method. src_type (torch.dtype): Type of input a

Recursively convert normalization layers from FP16 to FP32. Args: module (nn.Module): The modules to be converted in FP16. Returns:

Convert masks from the form of polygons to bitmaps. Args: polygons (list[ndarray]): masks in polygon representation height (int):

Compute positive bag loss. :math:`-log( Mean-max(P_{ij}^{cls} * P_{ij}^{loc}) )`. :math:`P_{ij}^{cls}`: matched_cls_prob, classifica

Get testing data after pipeline. Args: idx (int): Index of data. Returns: dict: Testing data after pipeline

Get training data and annotations after pipeline. Args: idx (int): Index of data. Returns: dict: Training da

Print mAP and results of each class. A table will be printed to show the gts/dets/recall/AP of each class and the mAP. Args: mea

Print recalls in a table. Args: recalls (ndarray): calculated from `bbox_recalls` proposal_nums (ndarray or list): top N proposal

Convert polygons to list of ndarray and filter invalid polygons. Args: polygons (list[list]): Polygons of one instance.

r"""Quality Focal Loss (QFL) is from `Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection <ht

Converts a float to closest non-zero int divisible by divior. Args: number (int): Original number to be quantized. di

Randomly select some elements from the gallery. If `gallery` is a Tensor, the returned indices will be a Tensor; If `gallery` is a nd

Randomly sample an img_scale when ``ratio_range`` is specified. A ratio will be randomly sampled from the range specified by ``ratio_

Randomly select an img_scale from given candidates. Args: img_scales (list[tuple]): Images scales for selection. Returns

Reduce loss as specified. Args: loss (Tensor): Elementwise loss tensor. reduction (str): Options are "none", "mean" and "sum".

Dump the detection results to a txt file. Args: results (list[list | tuple]): Testing results of the dataset.

Round number of filters based on depth multiplier.

Sample according to the iou interval. Args: max_overlaps (torch.Tensor): IoU between bounding boxes and ground tr

Set user-defined new property.

Check proposal_nums and iou_thrs and set correct format.

Sets swish function as memory efficient (for training) or standard (for export)

Visualize the detection results on the image. Args: model (nn.Module): The loaded detector. img (str or np.ndarray): Image filena

r"""A warpper of cuda version `Focal Loss <https://arxiv.org/abs/1708.02002>`_. Args: pred (torch.Tensor): The prediction with shape

Test function without test time augmentation. Args: imgs (list[torch.Tensor]): List of multiple images img_metas (lis

Generate grid anchors of a single level. Note: This function is usually called by method ``self.grid_anchors``. Args:

Generate the valid flags of anchor in a single feature map. Args: featmap_size (tuple[int]): The size of feature maps.

Slice ``src`` as ``dst`` Note: ``src`` should have the same or larger size than ``dst``. Args: src (torch.Te

Decode tblr outputs to prediction boxes. The process includes 3 steps: 1) De-normalize tblr coordinates by multiplying it with `normalizer`;

Add tensors ``a`` and ``b`` that might have different sizes.

Update hyperparameters like IoU thresholds for assigner and beta for SmoothL1 loss based on the training statistics. Returns: