table_detector.py

from img2table.ocr import DocTR
from torchvision import transforms
from transformers import AutoModelForObjectDetection

import torch

def box_cxcywh_to_xyxy(x):
    x_c, y_c, w, h = x.unbind(-1)
    b = [(x_c - 0.5 * w), (y_c - 0.5 * h), (x_c + 0.5 * w), (y_c + 0.5 * h)]
    return torch.stack(b, dim=1)

def rescale_bboxes(out_bbox, size):
    width, height = size
    boxes = box_cxcywh_to_xyxy(out_bbox)
    boxes = boxes * torch.tensor(
        [width, height, width, height], dtype=torch.float32
    )
    return boxes

def outputs_to_objects(outputs, img_size, id2label):
    m = outputs.logits.softmax(-1).max(-1)
    pred_labels = list(m.indices.detach().cpu().numpy())[0]
    pred_scores = list(m.values.detach().cpu().numpy())[0]
    pred_bboxes = outputs["pred_boxes"].detach().cpu()[0]
    pred_bboxes = [
        elem.tolist() for elem in rescale_bboxes(pred_bboxes, img_size)
    ]

    objects = []
    for label, score, bbox in zip(pred_labels, pred_scores, pred_bboxes):
        class_label = id2label[int(label)]
        if not class_label == "no object":
            objects.append(
                {
                    "label": class_label,
                    "score": float(score),
                    "bbox": [float(elem) for elem in bbox],
                }
            )

    return objects

class MaxResize(object):
    def __init__(self, max_size=800):
        self.max_size = max_size

    def __call__(self, image):
        width, height = image.size
        current_max_size = max(width, height)
        scale = self.max_size / current_max_size
        resized_image = image.resize(
            (int(round(scale * width)), int(round(scale * height)))
        )

        return resized_image

detection_transform = transforms.Compose(
    [
        MaxResize(800),
        transforms.ToTensor(),
        transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225]),
    ]
)

device = "cuda" if torch.cuda.is_available() else "cpu"
model = AutoModelForObjectDetection.from_pretrained("microsoft/table-transformer-detection", revision="no_timm").to(device)

ocr = DocTR()