Generate 2D gaussian heatmap. Args: heatmap (Tensor): Input heatmap, the gaussian kernel will cover on it and maintain the ma

Base on the previous bboxes and regression values, we compute the regressed bboxes and generate the grids on the bboxes. :param reg:

Generate base anchors of a single level. Args: base_size (int | float): Basic size of an anchor. scales (torch.Tensor

Gen target file path. Args: target_root_path (str): The target root path. src_name (str): The source file name. suffix (s

Generate text center region mask and geometric attribute maps. Args: img_size (tuple): The image size of (height, width).

Generate crop target and make sure not to crop the polygon instances. Args: image (ndarray): The image waited to be crop.

Generate text instance kernels for one shrink ratio. Args: img_size (tuple(int, int)): The image size of (height, width).

Generate random text components and their attributes to ensure the the number of text components in an image is larger than k_hop1, which

Generate threshold map. Args: img_size (tuple(int)): The image size (h,w) polygons (list(ndarray)): The polygon list.

Get squares according to feature map sizes and guided anchors. Args: featmap_sizes (list[tuple]): Multi-level feature map sizes.

Get squares according to feature map sizes and guided anchors. Args: featmap_sizes (list[tuple]): Multi-level feature map sizes.

Get annotation by index. Args: idx (int): Index of data. Returns: dict: Annotation info of specified index.

get_bboxes() is implemented in StageCascadeRPNHead.

Get user-defined property.

Get ground truth masks and ignored masks. Args: ann_infos (list[dict]): Each dict contains annotation infos of one image, con

Only keep loading image and annotations related configuration. Args: pipeline (list[dict]): Data pipeline configs. Returns:

Get sampled approxs and inside flags according to feature map sizes. Args: featmap_sizes (list[tuple]): Multi-level feature map s

For masking out the subsequent info.

Compute corresponding GT box and classification targets for proposals. Args: proposals_list (list[list]): Multi level poi

Compute semantic segmentation targets for each image. Args: segm_pred (Tensor): Predicted semantic segmentation map

Ignore gt masks and gt_labels while padding gt_masks_ignore in results given ignore_tags. Args: results (dict): Result fo

Init module weights. We do nothing in this function because all modules we used (ConvModule, BasicBlock and etc.) have default initia

Init weights.

Initialize the weights of recognizer.

Initialize the weights of recognizer.

Are points located in bboxes. Args: points (Tensor): Points, shape: (m, 2). bboxes (Tensor): Bounding boxes, shape: (n, 4). Retu

Load the information of one ground truth in .mat format. Args: img_info(dict): The dict of only the image information gt_file(str

A combination of the func:``AnchorHead.loss`` and func:``SSDHead.loss``. When ``self.use_ohem == True``, it functions like ``SSDHead.

Compute loss of the head. Args: segm_pred (list[Tensor]): Predicted semantic segmentation map with shape (N, num_

Compute loss of the head. Args: mask_pred (list[Tensor]): Predicted prototypes with shape (num_classes, H, W).

Compute loss of the head. Args: cls_scores (list[Tensor]): Box scores for each scale level Has shape (N, num_poin

Make mask for self attention. :param src: [b, c, h, l_src] :param tgt: [b, l_tgt] :return:

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

Dictionary mapper. Renames keys according to keymap provided. Args: d (dict): old dict keymap (dict): {'old_key':'new

nn.Module: normalization layer after the second convolution layer

Change from point offset to point coordinate.

OHEM sampling for a batch of imgs. Args: text_scores (Tensor): The text scores of size NxHxW. gt_texts (Tensor): The

padding has no effect on polygons`

Prepare results dict for pipeline.

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

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

Print time spent by CPU and GPU. Useful as a temporary context manager to find sweet spots of code suitable for async implementation.

Simple version of ``kwimage.Boxes.random`` Returns: Tensor: shape (n, 4) in x1, y1, x2, y2 format. References: https://gitla

Refine bboxes through stages.

Predict bucketing estimation (cls_pred) and fine regression (offset pred) with side-aware features.

Resample n points on a line. Args: line (ndarray): The points composing a line. n (int): The resampled points number.

see :func:`BaseInstanceMasks.rescale`

The forward function that also takes the RFP features as input.

Scale RoI coordinates by scale factor. Args: rois (torch.Tensor): RoI (Region of Interest), shape (n, 5) scale_factor

Generate crop box and make sure not to crop the polygon instances. Args: img_size (tuple(int)): The image size (h, w).

Sanitizes the input coordinates so that x1 < x2, x1 != x2, x1 >= 0, and x2 <= image_size. Also converts from relative to absolute coor

Save 2d array to txt file. Args: mat (ndarray): 2d-array of shape (n, m). file_name (str): The output file name.

Test function with test time augmentation. Args: imgs (torch.Tensor): Image input tensor. img_metas (list[dict]): Lis

Test function without test time augmentation. Args: imgs (torch.Tensor): Image input tensor. img_metas (list[dict]):

Smooth L1 loss. Args: pred (torch.Tensor): The prediction. target (torch.Tensor): The learning target of the prediction.

Sort vertex with 8 points [x1 y1 x2 y2 x3 y3 x4 y4]

convert polygon masks to bitmap masks.

See :func:`BaseInstanceMasks.to_tensor`.

YoloV3 Head Config.