Get box regression transformation deltas (dx, dy, dw, dh) that can be used to transform the `src_boxes` into the `target_boxes`. That

Arguments: box_cls, box_delta: Same as the output of :meth:`RetinaNetHead.forward` anchors (list[Boxes]): A list of #

nanmean compatible with generators.

Args: rgb (bool): whether to return RGB colors or BGR colors. maximum (int): either 255 or 1 Returns: ndarray: a vec

Register hooks to the trainer. The hooks are executed in the order they are registered. Args: hooks (list[Option

Preparation for a new round of evaluation. Should be called before starting a round of evaluation.

Makes a function retry itself after encountering pytorch's CUDA OOM error. It will first retry after calling `torch.cuda.empty_cache()`.

Given a list of N Instances (for N images), each containing a `gt_classes` field, return a list of Instances that contain only instances with

Compute and display summary metrics for evaluation results. Note this function can *only* be applied on the default parameter setting

Args: stem (nn.Module): a stem module stages (list[list[CNNBlockBase]]): several (typically 4) stages,

Depending on the brightness_factor, gives a lighter or darker color i.e. a color with less or more saturation than the original color

Create a grayscale version of the original image. The colors in masked area, if given, will be kept.

RoiAlignRotated with scale 1.0 and 0 sample ratio.

Accumulate per image evaluation results and store the result in self.eval :param p: input params for evaluation :return: None

Run all_gather on arbitrary picklable data (not necessarily tensors). Args: data: any picklable object group: a torch proces

coords should be a N * 2 array-like, containing N couples of (x, y) points

demo should be a numpy array, formatted as Height * Width * Nchannels

Computes the area of all the boxes. Returns: torch.Tensor: a vector with areas of each box.

Performs non-maximum suppression in a batched fashion. Each index value correspond to a category, and NMS will not be applied between el

Built an anchor generator from `cfg.MODEL.ANCHOR_GENERATOR.NAME`.

Build ROIHeads defined by `cfg.MODEL.ROI_HEADS.NAME`.

Clip (in place) the boxes by limiting x coordinates to the range [0, width] and y coordinates to the range [0, height]. For

Crop each bitmask by the given box, and resize results to (mask_size, mask_size). This can be used to prepare training targets for Ma

Args: x_data (list[int]): a list containing x values of all the points being drawn. Length of list should match t

Draw semantic segmentation predictions/labels. Args: sem_seg (Tensor or ndarray): the segmentation of shape (H, W).

Args: input: NCHW images rois: Bx5 boxes. First column is the index into N. The other 4 columns are xyxy.

Returns: bool: whether the field called `name` exists.

Returns: HistoryBuffer: the scalar history for name

A wrapper around :func:`torch.nn.functional.interpolate` to support zero-size tensor.

Load a json file with COCO's instances annotation format. Currently supports instance detection, instance segmentation, and person keypoi

Compute the default losses for box head in Fast(er) R-CNN, with softmax cross entropy loss and smooth L1 loss. Returns:

Args: For `gt_class_info`, `gt_delta_info`, `gt_mask_info` and `num_fg` parameters, see :meth:`TensorMask.get_gro

Args: polygons (list[ndarray]): each array has shape (Nx2,) height, width (int) Returns: ndarray: a bool mask of sha

Deprecated

Put multiple scalars from keyword arguments. Examples: storage.put_scalars(loss=my_loss, accuracy=my_accuracy, smoothin

Compute the smooth L1 loss for box regression. Returns: scalar Tensor

Args: cfg (CfgNode): torch_model (nn.Module): the detectron2 model (meta_arch) to be converted.

Execute inference on a list of inputs, using batch size = self.batch_size, instead of the length of the list. Inputs & outpu

Caffe2 implementation of preprocess_image, which is called inside each MetaArch's forward. It normalizes the input images, and the fi

Collect all configuration files (i.e. densepose_*.yaml) directly in the specified directory

Args: classes (list[int] or None): scores (list[float] or None): class_names (list[str] or None): Returns: l

Returns: str: module name of the caller tuple: a hashable key to be used to identify different callers

Forward logic of the keypoint prediction branch. Args: features (dict[str, Tensor]): mapping from feature map names to t

Forward logic of the mask prediction branch. Args: features (dict[str, Tensor]): mapping from feature map names to tenso

Rescale the output instances to the target size.

In given proto, rename all blobs with matched version

Add config for densepose head.

Args: cfg (CfgNode): a detectron2 config Returns: CfgNode: an updated config with new options that will be used

Apply transform deltas to boxes. Similar to `box2box_transform.apply_deltas`, but allow broadcasting boxes when the second dimension of delta

Computes area of the mask. Only works with Polygons, using the shoelace formula: https://stackoverflow.com/questions/24467972

Build a box head defined by `cfg.MODEL.ROI_BOX_HEAD.NAME`.

A data loader is created in a way similar to that of Detectron2. The main differences are: - it allows to combine data with different bu

Build a mask head defined by `cfg.MODEL.ROI_MASK_HEAD.NAME`.

Build an optimizer from config.

Check that the data have consistent metadata. Args: key (str): a metadata key dataset_names (list[str]): a list of dataset n

3x3 convolution with padding

3x3 convolution with padding

See get_caffe2_inputs() below.

Decode array data from a string that contains PNG-compressed data @param Base64-encoded string containing PNG-compressed data

Args: binary_mask (ndarray): numpy array of shape (H, W), where H is the image height and W is the image width. E

Args: text (str): class label position (tuple): a tuple of the x and y coordinates to place text on image.

Evaluate/summarize the performance, after processing all input/output pairs. Returns: dict: A new evalua