Construct the init_net from params dictionary

Convert PIL image to numpy array of target format. Args: image (PIL.Image): a PIL image format (str): the format of output i

Apply some basic name conversion to names in C2 weights. It only deals with typical backbone models. Args: original_keys (list[s

Convert all boxes in `box_lists` to the low-level format used by ROI pooling ops (see description under Returns). Args: box_list

Map Caffe2 Detectron weight names to Detectron2 names. Args: weights (dict): name -> tensor Returns: dict: detectron2 n

Converts dataset into COCO format and saves it to a json file. dataset_name must be registered in DatasetCatalog and in detectron2's standard

Given a blob object, return the Caffe2 operator that creates this blob as constant. Currently support NumPy tensor and Caffe2 Int8Tensor.

Create an extractor for the provided visualizer

Find a cropping window such that no single category occupies more than `single_category_max_area` in `sem_seg`. The function retries rand

Infer dense pose estimate based on outputs from the DensePose head and detections. The estimate for each detection instance is stored in its

Draws keypoints of an instance and follows the rules for keypoint connections to draw lines between appropriate keypoints. This follo

Args: box_coord (tuple): a tuple containing x0, y0, x1, y1 coordinates, where x0 and y0 are the coordinates of th

Args: circle_coord (list(int) or tuple(int)): contains the x and y coordinates of the center of the circle.

Args: rotated_box (tuple): a tuple containing (cnt_x, cnt_y, w, h, angle), where cnt_x and cnt_y are the center c

Save extra metadata that will be used by inference in the output protobuf.

Convert semantic segmentation to COCO stuff format with segments encoded as RLEs. See http://cocodataset.org/#format-results

Encode array data as a PNG image using the highest compression rate @param arr [in] Data stored in an array of size (3, M, N) of type

Export a caffe2-compatible Detectron2 model to caffe2 format via ONNX. Arg: model: a caffe2-compatible version of detectron2 model,

Export a detectron2 model to caffe2 format. Args: cfg (CfgNode): a detectron2 config, with extra export-related options

Trace and export a model to onnx format. Args: model (nn.Module): inputs (tuple[args]): the model will be called by `model(*

Export the model to a `torch.jit.TracedModule` by tracing. The returned object can be saved to a file by ".save()". Returns:

Call `fast_rcnn_inference_single_image_rotated` for all images. Args: boxes (list[Tensor]): A list of Tensors of predicted class-spe

Single-image inference. Return rotated bounding-box detection results by thresholding on scores and applying rotated non-maximum suppression

Filter out images with none annotations or only crowd annotations (i.e., images without non-crowd annotations). A common training-time pr

For each feature map, select the `pre_nms_topk` highest scoring proposals, apply NMS, clip proposals, and remove small boxes. Return the `pos

Flattens predictions in the batch.

Expand a hierarchical dict of scalars into a flat dict of scalars. If results[k1][k2][k3] = v, the returned dict will have the entry {"k1

See :class:`Res5ROIHeads.forward`.

Use the given boxes in `instances` to produce other (non-box) per-ROI outputs. This is useful for downstream tasks where a box is kn

Look for keys with the following patterns: 1) Starts with "fpn.inner." Example: "fpn.inner.res2.2.sum.lateral.weight"

Freeze the first several stages of the ResNet. Commonly used in fine-tuning. Layers that produce the same feature map spatia

Remove AliasWithName placeholder and rename the input/output of it

In-place fuse extra copy ops between cpu/gpu for the following case: a -CopyAToB-> b -CopyBToA> c1 -NextOp1-> d1

Generate a tensor storing canonical anchor boxes, which are all anchor boxes of different sizes and aspect_ratios centered at (0, 0).

Generate a tensor storing canonical anchor boxes, which are all anchor boxes of different sizes, aspect_ratios, angles centered at (0

Generate regular square grid of points in [0, 1] x [0, 1] coordinate space. Args: R (int): The number of grids to sample, one for ea

Returns the field called `name`.

Parse all the arguments provided from the CLI. Returns: A list of parsed arguments.

Parse all the arguments provided from the CLI. Returns: A list of parsed arguments.

Convert pytorch-style structured inputs to caffe2-style inputs that are tuples of tensors. Args: batched_inputs

Returns the URL to the model trained using the given config Args: config_path (str): config file name relative to detectron2's "conf

Returns path to a builtin config file. Args: config_path (str): config file name relative to detectron2's "configs/" dir

Get all the configuration files (relative to the base configuration directory)

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

Create evaluator(s) for a given dataset. This uses the special metadata "evaluator_type" associated with each builtin dataset. For your o

Get all the evolution configuration files (relative to the base configuration directory)