feat: add rotated boxes

[charlesmindee]

This PR introduces a major feature: rotated bounding boxes.

Boxes were caracterized by a 4-dimension tuple: (xmin, ymin, xmax, ymax), and we introduce a new kind of rotated boxes caracterized by a 5-dimension tuple: (x, y, w, h, alpha), where (x, y) is the center of the box, (w, h) its spatial extension, and alpha the angle of rotation of the box (in degrees) to the horizontal (horizontal box: alpha = 0°).

For the moment, support is only provided for 2 quarters of the circle: only angles of rotation between -90° and +90° are supported (either up-rotated or down-rotated). As shown below, it is impossible to determine more than 1 quarter of 360° without any postprocessing tricks, however, we used the mean aspect ratio of boxes to extend this area to 180°.

However, this allows us to handle most of the rotated documents, which are usually slightly rotated with respect to the horizontal.

The following modules are modified accordingly:

• datasets (load rotated boxes for both training & eval)
• models (detection postprocessors)
• utils (geometry, metrics, visualization)
• tests
• docs (new performances, due to a new detection postprocessing)

The 2 options for boxes geometry are available in each modules, and the "non-rotated" option is activated by default everywhere.
To instantiate a predictor with rotated boxes, please use:

predictor = models.OCRPredictor(rotated_detection_predictor, recognition_predictor, rotated_bbox=True)

where:

rotated_detection_predictor is a detection predictor instantiated with an architecture trained on rotated docs ('rotated_bbox' = True in cfg). However, you can also force any architecture to predict rotated boxes, passing a kwarg "rotated_bbox"=True in the constructor:

rotated_detection_predictor = detection.DetectionPredictor(PreProcessor(output_size=(512, 512), batch_size=batch_size), detection.db_resnet50(rotated_bbox=True, input_shape=(512, 512, 3)))

To plot rotated boxes, use:
page.show(img, rotation=True) or document.show([img1, img2, ...], rotation=False)

If you want to train or evaluate a model with rotated boxes, please pass the argument rotation = True in the scripts evaluate.py and detection/train.py, it will instantiate datasets and metrics properly.

Any feedback is welcome!

[fg-mindee]

Thanks a lot for the massive PR! A few things to change, let me know if you have questions!

[fg-mindee]

Few things to handle and we're good to go!

[fg-mindee]

Almost there!

[fg-mindee]

All good!