table_detr_10ep

아래 링크의 모델에 custom data를 추가해 만들었습니다. https://huggingface.co/TahaDouaji/detr-doc-table-detection

코드 예시

metrics:

import os
from transformers import DetrImageProcessor, DetrForObjectDetection
import torch
import cv2
from PIL import Image, ImageDraw, ImageFont

model = DetrForObjectDetection.from_pretrained("lms7127/table_detr_10ep")
processor = DetrImageProcessor.from_pretrained("lms7127/table_detr_10ep")

font_path = os.path.join(cv2.__path__[0],'qt','fonts','DejaVuSans.ttf')

#변환할 이미지 목록 불러오기
image_path = '/path/to/image'
save_path ="/path/to/save"

img = Image.open(image_path)
inputs = processor(images=img, return_tensors="pt")
with torch.no_grad():#추가학습 방지
  outputs = model(**inputs)

# convert outputs (bounding boxes and class logits) to COCO API
# let's only keep detections with score > 0.9
width, height = img.size
postprocessed_outputs = processor.post_process_object_detection(outputs,
                                                                target_sizes=[(height, width)],
                                                                threshold=0.7)
results = postprocessed_outputs[0]
draw = ImageDraw.Draw(img)
for score, label, box in zip(results["scores"], results["labels"], results["boxes"]):
  box = [round(i, 2) for i in box.tolist()]
  class_label = model.config.id2label[label.item()]
  confidence = round(score.item(), 3)

  # Draw rectangle
  draw.rectangle(box, outline="red",  width = 5)
  
  # Add text
  font_size=50
  font = ImageFont.truetype(font_path, font_size) 
  text = f"{class_label}: {confidence}"
  text_width, text_height = draw.textsize(text)
  text_location = [box[0], box[1] - text_height - 4]
  draw.rectangle([text_location[0], text_location[1], text_location[0] + text_width, text_location[1] + text_height], fill="red")
  draw.text(text_location, text, fill="white", font=font)
img.save(save_path,"JPEG")