Save ndarray to local numpy file. Args: array (ndarray): Ndarray to save. temp_file_name (str): Numpy file name. If 'temp_file_na

Change from point offset to point coordinate.

Test without augmentation.

Convert palette to matplotlib palette. Args: palette List[tuple]: A list of color tuples. Returns: List[tuple[float]]: A lis

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

Collect eval result from each iteration. Args: preds (list[torch.Tensor] | torch.Tensor): the segmentation logit

Randomly sample an img_scale when ``multiscale_mode=='range'``. Args: img_scales (list[tuple]): Images scale range for sampling.

Randomly sample an img_scale when ``multiscale_mode=='range'``. Args: img_scales (list[tuple]): Images scale range for sampling.

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

Refine bboxes through stages.

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

Resize pos_embed weights. Resize pos_embed using bicubic interpolate method. Args: pos_embed (torch.Tensor): Position emb

Resize relative pos_embed weights. This function is modified from https://github.com/microsoft/unilm/blob/master/beit/semantic_segmen

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

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

Update a dict to `data_fields`. Args: data (dict): A dict contains annotations of image or model predictions. Def

Set random seed. Args: seed (int): Seed to be used. deterministic (bool): Whether to set the deterministic option for

Setup multi-processing environment variables.

Setup multi-processing environment variables.

Draw `result` over `img`. Args: img (str or Tensor): The image to be displayed. result (Tensor): The semantic segment

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

Visualize the segmentation results on the image. Args: model (nn.Module): The loaded segmentor. img (str or np.ndarray): Image fi

Test det bboxes without test-time augmentation. Args: feats (tuple[torch.Tensor]): Multi-level features from the

Simple test for mask head without augmentation.

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

See :func:`BaseInstanceMasks.to_ndarray`.

Convert masks to the format of ndarray.

Calculate evaluation metrics Args: total_area_intersect (ndarray): The intersection of prediction and ground truth histogram o

Args: x: (B, H, W, C) window_size (int): window size Returns: windows: (num_windows*B, window_size, window_size, C)

Args: x: (B, H, W, C) window_size (int): window size Returns: windows: (num_windows*B, window_size, window_size, C)

Args: x: (B, H, W, C) window_size (int): window size Returns: windows: (num_windows*B, window_size, window_size, C)

Args: x: (B, H, W, C) window_size (int): window size Returns: windows: (num_windows*B, window_size, window_size, C)

Args: x: (B, H, W, C) Returns: windows: (num_windows*B, window_size, window_size, C)

Args: x: (B, H, W, C) Returns: windows: (num_windows*B, window_size, window_size, C)

img_splits_hw: B' H W C

L2 normalization layer. Args: n_dims (int): Number of dimensions to be normalized scale (float, optional): Defaults t

Bottleneck block for ResNeXt. If style is "pytorch", the stride-two layer is the 3x3 conv layer, if it is "caffe", the stride-two lay