import os
os.system('pip install detectron2 -f https://dl.fbaipublicfiles.com/detectron2/wheels/cu102/torch1.9/index.html')
os.system("git clone https://github.com/microsoft/unilm.git")

import sys
sys.path.append("unilm")

import cv2

from unilm.dit.object_detection.ditod import add_vit_config

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


# Step 1: instantiate config
cfg = get_cfg()
add_vit_config(cfg)
cfg.merge_from_file("cascade_dit_base.yml")

# Step 2: add model weights URL to config
cfg.MODEL.WEIGHTS = "https://layoutlm.blob.core.windows.net/dit/dit-fts/publaynet_dit-b_cascade.pth"

# Step 3: set device
# TODO also support GPU
cfg.MODEL.DEVICE='cpu'

# Step 4: define model
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 = "Interactive demo: Document Layout Analysis with DiT"
description = "Demo for Microsoft's DiT, the Document Image Transformer for state-of-the-art document understanding tasks. This particular model is fine-tuned on PubLayNet, a large dataset for document layout analysis. To use it, simply upload an image or use the example image below and click 'Submit'. Results will show up in a few seconds. If you want to make the output bigger, right-click on it and select 'Open image in new tab'."
article = "<p style='text-align: center'><a href='https://arxiv.org/abs/2203.02378' target='_blank'>DiT: Self-supervised Pre-training for Document Image Transformer</a> | <a href='https://github.com/microsoft/unilm/dit' target='_blank'>Github Repo</a></p>"
examples =[['publaynet_example.jpeg']]
css = ".output-image, .input-image, .image-preview {height: 600px !important}"

iface = gr.Interface(fn=analyze_image, 
                     inputs=gr.inputs.Image(type="numpy", label="document image"), 
                     outputs=gr.outputs.Image(type="numpy", label="annotated document"),
                     title=title,
                     description=description,
                     examples=examples,
                     css=css,
                     enable_queue=True)
iface.launch(debug=True)