app.py

try:
    import detectron2
except:
    import os 
    os.system('pip install git+https://github.com/facebookresearch/detectron2.git')

from matplotlib.pyplot import axis
import gradio as gr
import requests
import numpy as np
from torch import nn
import requests

import torch
import detectron2
from detectron2 import model_zoo
from detectron2.engine import DefaultPredictor
from detectron2.config import get_cfg
from detectron2.utils.visualizer import Visualizer
from detectron2.data import MetadataCatalog
from detectron2.utils.visualizer import ColorMode

model_path = 'model_final.pth'

cfg = get_cfg()
cfg.merge_from_file(model_zoo.get_config_file("COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml"))
cfg.MODEL.ROI_HEADS.SCORE_THRESH_TEST = 0.6
cfg.MODEL.ROI_HEADS.NUM_CLASSES = 1
cfg.MODEL.WEIGHTS = model_path

if not torch.cuda.is_available():
    cfg.MODEL.DEVICE='cpu'

predictor = DefaultPredictor(cfg)
my_metadata = MetadataCatalog.get("car_dataset_val")
my_metadata.thing_classes = ["damage"]

def merge_segment(pred_segm):
    merge_dict = {}
    for i in range(len(pred_segm)):
        merge_dict[i] = []
        for j in range(i+1,len(pred_segm)):
            if torch.sum(pred_segm[i]*pred_segm[j])>0:
                merge_dict[i].append(j)
    
    to_delete = []
    for key in merge_dict:
        for element in merge_dict[key]:
            to_delete.append(element)
    
    for element in to_delete:
        merge_dict.pop(element,None)
        
    empty_delete = []
    for key in merge_dict:
        if merge_dict[key] == []:
            empty_delete.append(key)
    
    for element in empty_delete:
        merge_dict.pop(element,None)
        
    for key in merge_dict:
        for element in merge_dict[key]:
            pred_segm[key]+=pred_segm[element]
            
    except_elem = list(set(to_delete))
    
    new_indexes = list(range(len(pred_segm)))
    for elem in except_elem:
        new_indexes.remove(elem)
        
    return pred_segm[new_indexes]

def inference(image):
    print(image.height)

    height = image.height

    # img = np.array(image.resize((500, height)))
    img = np.array(image)
    outputs = predictor(img)
    out_dict = outputs["instances"].to("cpu").get_fields()
    new_inst = detectron2.structures.Instances((1024,1024))
    new_inst.set('pred_masks',merge_segment(out_dict['pred_masks']))
    v = Visualizer(img[:, :, ::-1],
                   metadata=my_metadata, 
                   scale=0.5, 
                   instance_mode=ColorMode.SEGMENTATION   # remove the colors of unsegmented pixels. This option is only available for segmentation models
    )
    # v = Visualizer(img,scale=1.2)
    #print(outputs["instances"].to('cpu'))
    out = v.draw_instance_predictions(new_inst)
    
    return out.get_image()[:, :, ::-1]
    
title = "Detectron2 Car damage Detection"
description = "This demo introduces an interactive playground for our trained Detectron2 model."

gr.Interface(
    inference, 
    [gr.inputs.Image(type="pil", label="Input")], 
    gr.outputs.Image(type="numpy", label="Output"),
    title=title,
    description=description,
    examples=[]).launch()