app.py

import numpy as np
import gradio as gr
import cv2
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

# Setup detectron2 logger
import detectron2
from detectron2.utils.logger import setup_logger
setup_logger()

def detect_objects(input_img):
    # Load image
    im = input_img.copy()

    # Configuration
    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 = 0.5
    cfg.MODEL.WEIGHTS = model_zoo.get_checkpoint_url("COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml")

    # Prediction
    predictor = DefaultPredictor(cfg)
    outputs = predictor(im)

    # Visualization
    v = Visualizer(im[:, :, ::-1], MetadataCatalog.get(cfg.DATASETS.TRAIN[0]), scale=1.9)
    out = v.draw_instance_predictions(outputs["instances"].to("cpu"))
    result_image = out.get_image()[:, :, ::-1]

    return result_image

# Interface
image = gr.Image()
output_image = gr.Image()

title = "Object Detection using Mask R-CNN"
description = "This app detects objects in the input image using Mask R-CNN."
examples = [["./input.png"]]

gr.Interface(detect_objects, [image], output_image, title=title, description=description, examples=examples).launch()