Spaces:
Sleeping
Sleeping
File size: 1,502 Bytes
b816ac7 dbadeb1 1dc34dc b816ac7 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 |
from unilm.dit.object_detection.ditod import add_vit_config
import torch
import cv2
from detectron2.config import CfgNode as CN
from detectron2.config import get_cfg
from detectron2.utils.visualizer import ColorMode, Visualizer
from detectron2.data import MetadataCatalog
from detectron2.engine import DefaultPredictor
import gradio as gr
cfg = get_cfg()
add_vit_config(cfg)
cfg.merge_from_file("cascade_dit_base.yml")
cfg.MODEL.WEIGHTS = "publaynet_dit-b_cascade.pth"
cfg.MODEL.DEVICE = "cuda" if torch.cuda.is_available() else "cpu"
predictor = DefaultPredictor(cfg)
def analyze_image(img):
md = MetadataCatalog.get(cfg.DATASETS.TEST[0])
if cfg.DATASETS.TEST[0] == 'icdar2019_test':
md.set(thing_classes=["table"])
else:
md.set(thing_classes=["text", "title", "list", "table", "figure"])
output = predictor(img)["instances"]
v = Visualizer(img[:, :, ::-1],
md,
scale=1.0,
instance_mode=ColorMode.SEGMENTATION)
result = v.draw_instance_predictions(output.to("cpu"))
result_image = result.get_image()[:, :, ::-1]
return result_image
title = " Table Detection with DiT"
css = ".output-image, .input-image, .image-preview {height: 600px !important}"
iface = gr.Interface(
fn=analyze_image,
inputs=[gr.Image(type="numpy", label="document image")],
outputs=[gr.Image(type="numpy", label="detected tables")],
title=title,
css=css,
)
iface.launch(debug=True, share=True)
|