Display the results of the LR grid search. Adapted from https://github.com/frgfm/Holocron/blob/master/holocron/trainer/core.py. Args:

Display the results of the LR grid search. Adapted from https://github.com/frgfm/Holocron/blob/master/holocron/trainer/core.py Args:

Read a PDF file and convert it into an image in numpy format >>> from doctr.io import read_html >>> doc = read_html("https://www.yoursite.com

Read an image file into numpy format >>> from doctr.io import read_img_as_numpy >>> page = read_img_as_numpy("path/to/your/doc.jpg") Arg

Read a PDF file and convert it into an image in numpy format >>> from doctr.io import read_pdf >>> doc = read_pdf("path/to/your/doc.pdf")

Gridsearch the optimal learning rate for the training. Adapted from https://github.com/frgfm/Holocron/blob/master/holocron/trainer/core.py

Gridsearch the optimal learning rate for the training. Adapted from https://github.com/frgfm/Holocron/blob/master/holocron/trainer/core.py

Gridsearch the optimal learning rate for the training. Adapted from https://github.com/frgfm/Holocron/blob/master/holocron/trainer/core.py

Gridsearch the optimal learning rate for the training. Adapted from https://github.com/frgfm/Holocron/blob/master/holocron/trainer/core.py

Create a matplotlib rectangular patch for the element Args: geometry: bounding box of the element page_dimensions: dimensions of

Rotate each crop of the list according to the predicted orientation: 0: already straight, no rotation 1: 90 ccw, rotate 3 times ccw 2: 180

Orient the quadrangle (Polygon4P) according to the predicted orientation, so that the points are in this order: top L, top R, bot R, bot L if the

Remaps a batch of rotated locpred (N, 4, 2) expressed for an origin_shape to a destination_shape. This does not impact the absolute shape of the b

Remove black border padding from an image Args: image: numpy tensor to remove padding from Returns: Image with padding remov

Renders the full text of the element

Renders the full text of the element

Renders the full text of the element

Renders the full text of the element

Renders the full text of the element

Renders the full text of the element

Renders the full text of the element

Build a ResNet stage

Compute enclosing bbox either from: Args: bboxes: boxes in one of the following formats: - an array of boxes: (*, 4), where

Compute enclosing rotated bbox either from: Args: rbboxes: boxes in one of the following formats: - an array of boxes: (*, 4

Rotate a batch of straight bounding boxes (xmin, ymin, xmax, ymax, c) or rotated bounding boxes (4, 2) of an angle, if angle > min_angle, around t

Runs command using run_lambda; reads and returns entire output if rc is 0

Scaled Dot-Product Attention

Display the results Args: **kwargs: additional keyword arguments to be passed to `plt.show`

Overlay the result on a given image Args: interactive: whether the display should be interactive preserve_aspect_rati

Overlay the result on a given image

Computes the aggregated metrics Returns: a tuple with the recall & precision for each class prediction and the mean IoU

Synthesize the page from the predictions Args: **kwargs: keyword arguments passed to the `synthesize_kie_page` method Re

Synthesize all pages from their predictions Args: **kwargs: keyword arguments passed to the `Page.synthesize` method Ret

Draw a the content of the element page (OCR response) on a blank page. Args: page: exported Page object to represent draw_proba:

Draw a the content of the element page (OCR response) on a blank page. Args: page: exported Page object to represent draw_proba:

Visualize a full page with predicted blocks, lines and words >>> import numpy as np >>> import matplotlib.pyplot as plt >>> from doctr.ut

Merge windowed images back to the original spatial shape. Args: img_splits_hw: A float tensor of shape (b', h_sp*w_sp, c

Call the model on the given inputs Args: inputs: the inputs to use Returns: Any: the postprocessed

Re-arrange detected words into structured blocks Args: pages: list of N elements, where each element represents the page image

Re-arrange detected words into structured predictions Args: pages: list of N elements, where each element represents the page ima

Performs decoding of raw output with CTC and decoding of CTC predictions with label_to_idx mapping dictionary Args: logit

Performs decoding of raw output with CTC and decoding of CTC predictions with label_to_idx mapping dictionary Args: logit

Performs postprocessing for a list of model outputs Args: proba_map: probability map of shape (N, H, W, C) Returns:

Prepare document data for model forwarding Args: x: list of images (np.array) or a single image (np.array) of shape (H, W, C)