Resize image while keeping the aspect ratio. Args: img (ndarray): The input image. scale (float | tuple[int]): The scaling factor

Function used in Word Spotting that finds if the Ground Truth transcription meets the rules to enter into the dictionary. If not, the transcr

Function applied to the Ground Truth transcriptions used in Word Spotting. It removes special characters or terminations

Run inference on the given inputs. Args: batched_inputs (list[dict]): same as in :meth:`forward` detected_in

Run inference on the given inputs. Args: batched_inputs (list[dict]): same as in :meth:`forward` detected_in

Apply the inverse sigmoid operation. y = -ln(1-x/x)

Transform data back to its original space. In other words, return an input X_original whose transform would be X. Parameters ----------

Load a json file with totaltext annotation format. Currently supports text detection and recognition. Args: json_file (str): ful

Return the losses from a set of FCOS predictions and their associated ground-truth. Returns: dict[loss name -> loss valu

Return the losses from a set of FCOS predictions and their associated ground-truth. Returns: dict[loss name -> loss valu

Return the losses from a set of MEInst predictions and their associated ground-truth. Returns: dict[loss name -> loss va

Create a resnet stage by creating many blocks. Args: block_class (class): a subclass of ResNetBlockBase num_blocks (int):

:param features :param weights: [w0, w1, ...] :param bias: [b0, b1, ...] :return:

Args: label: shape (n1, n2, ..., ) depth: a scalar Returns: onehot: (n1, n2, ..., depth)

Resize the output instances. The input images are often resized when entering an object detector. As a result, we often need

Reduce loss as specified. Args: loss (Tensor): Elementwise loss tensor. reduction (str): Options are "none", "mean" and "sum".

Register a dataset in json annotation format for text detection and recognition. Args: name (str): a name that identifies the datase

Calculate the new size to be rescaled to. Args: old_size (tuple[int]): The old size (w, h) of image. scale (float | tuple[int]): T

Args: image (np.ndarray): an image of shape (H, W, C) (in BGR order). This is the format used by OpenCV.

Create configs and perform basic setups.

Create configs and perform basic setups.

Run training. Returns: OrderedDict of results, if evaluation is enabled. Otherwise None.

Args: start_iter, max_iter (int): See docs above

Apply dimensionality reduction to X. X is projected on the first principal components previously extracted from a training set. Paramet

Transform keypoint annotations of an image. Args: beziers (list[float]): Nx16 float in Detectron2 Dataset format. transforms

Validate the format of the line. If the line is not valid an exception will be raised. If maxWidth and maxHeight are specified, all points mu

Validate the format of the line. If the line is not valid an exception will be raised. If maxWidth and maxHeight are specified, all points mu

Apply element-wise weight and reduce loss. Args: loss (Tensor): Element-wise loss. weight (Tensor): Element-wise weights.

Interface for Python

Interface for Python