from huggingface_hub import hf_hub_download
from transformers import AutoImageProcessor, TableTransformerForObjectDetection
import torch
from PIL import Image

file_path = hf_hub_download(repo_id="nielsr/example-pdf", repo_type="dataset", filename="example_pdf.png")
image = Image.open(file_path).convert("RGB")

image_processor = AutoImageProcessor.from_pretrained("microsoft/table-transformer-detection")
model = TableTransformerForObjectDetection.from_pretrained("microsoft/table-transformer-detection")

inputs = image_processor(images=image, return_tensors="pt")
outputs = model(**inputs)

# convert outputs (bounding boxes and class logits) to Pascal VOC format (xmin, ymin, xmax, ymax)
target_sizes = torch.tensor([image.size[::-1]])
results = image_processor.post_process_object_detection(outputs, threshold=0.9, target_sizes=target_sizes)[
    0
]

for score, label, box in zip(results["scores"], results["labels"], results["boxes"]):
    box = [round(i, 2) for i in box.tolist()]
    print(
        f"Detected {model.config.id2label[label.item()]} with confidence "
        f"{round(score.item(), 3)} at location {box}"
    )
Detected table with confidence 1.0 at location [202.1, 210.59, 1119.22, 385.09]