from transformers import AutoImageProcessor

processor = AutoImageProcessor.from_pretrained("microsoft/table-transformer-detection")
print(type(processor))

from torchvision import transforms

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

# this is required for the table detection models
detection_transform = transforms.Compose([
    MaxResize(800),
    transforms.ToTensor(),
    transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
])

# this is required for the table structure recognition models
structure_transform = transforms.Compose([
    MaxResize(1000),
    transforms.ToTensor(),
    transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
])