Build model.

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

Forward and collect network outputs in a distributed manner. This function performs forward propagation and collects outputs. It can be used

Forward backbone. Args: img (Tensor): Input images of shape (N, C, H, W). Typically these should be mean centered

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

Arguments: anchors (list[Boxes]): A list of #feature level Boxes. The Boxes contain anchors of this image on the

Forward and collect network outputs. This function performs forward propagation and collects outputs. It can be used to collect results, feat

Registers a converter for the specified type. Can be used as a decorator (if converter is None), or called as a method. Args

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

The valid files will have name: <class_name>_<split>.txt. We want to remove all the other files from the input.

Args: results (OrderedDict[dict]): task_name -> {metric -> score} Returns: bool: whether the verification succeeds or not

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

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

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

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

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.

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

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`.

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

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.

Forward backbone. Args: img (Tensor): Input images of shape (N, C, H, W). Typically these should be mean centered

Returns: Boxes: tight bounding boxes around bitmasks. If a mask is empty, it's bounding box will be all zero.

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.

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

Create a list of blocks of the same type that forms one ResNet stage. Args: block_class (type): a subclass of CNNBlockBa

Find boxes that are non-empty. A box is considered empty, if either of its side is no larger than threshold. Returns:

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

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

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

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

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

Transform anchors into proposals by applying the predicted anchor deltas. Returns: proposals (list[Tensor]): A list of 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

Return the learning rate warmup factor at a specific iteration. See :paper:`ImageNet in 1h` for more details. Args: method (str)

Randomly modifies given color to produce a slightly different color than the color given. Args: color (tuple[double]): a

Parse the raw outputs (losses) of the network. Args: losses (dict): Raw output of the network, which usually contain

Parse the raw outputs (losses) of the network. Args: losses (dict): Raw output of the network, which usually contain

Rescale the output instances to the target size.

In given proto, rename all blobs with matched version

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

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

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

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

Build an optimizer from config.

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

Build a semantic segmentation head from `cfg.MODEL.SEM_SEG_HEAD.NAME`.

Performs all_gather operation on the provided tensors. *** Warning ***: torch.distributed.all_gather has no gradient.

1x1 convolution

3x3 convolution with padding

See get_caffe2_inputs() below.