# Load model directly
from transformers import AutoImageProcessor, AutoModelForObjectDetection
processor = AutoImageProcessor.from_pretrained("SalML/DETR-table-structure-recognition")
model = AutoModelForObjectDetection.from_pretrained("SalML/DETR-table-structure-recognition")Quick Links
The models are taken from https://github.com/microsoft/table-transformer/
Original model now on MSFT org: https://huggingface.co/microsoft/table-transformer-structure-recognition
I have built a HuggingFace Space: https://huggingface.co/spaces/SalML/TableTransformer2CSV It runs an OCR on the table-transformer output image to obtain a CSV downloadable table.
- Downloads last month
- 25
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("object-detection", model="SalML/DETR-table-structure-recognition")