app.py

import torch
import cv2
import numpy as np
import gradio as gr
from sahi.prediction import ObjectPrediction
from sahi.utils.cv import visualize_object_predictions, read_image


model = torch.hub.load('ultralytics/yolov5', 'yolov5s', pretrained=True)


model.conf = 0.25  
model.iou = 0.45  
model.agnostic = False  
model.multi_label = False  
model.max_det = 1000


def detect(img):


    results = model.predict(image, imgsz=image_size, return_outputs=True)

    
    object_prediction_list = []
    for _, image_results in enumerate(results):
        if len(image_results)!=0:
            image_predictions_in_xyxy_format = image_results['det']
            for pred in image_predictions_in_xyxy_format:
                x1, y1, x2, y2 = (
                    int(pred[0]),
                    int(pred[1]),
                    int(pred[2]),
                    int(pred[3]),
                )
                bbox = [x1, y1, x2, y2]
                score = pred[4]
                category_name = model.model.names[int(pred[5])]
                category_id = pred[5]
                object_prediction = ObjectPrediction(
                    bbox=bbox,
                    category_id=int(category_id),
                    score=score,
                    category_name=category_name,
                )
                object_prediction_list.append(object_prediction)

    image = read_image(image)
    output_image = visualize_object_predictions(image=image, object_prediction_list=object_prediction_list)
    return output_image['image']

def drawRectangles(image, dfResults):
    for index, row in dfResults.iterrows():
      print( (row['xmin'], row['ymin']))
      image = cv2.rectangle(image, (row['xmin'], row['ymin']), (row['xmax'], row['ymax']), (255, 0, 0), 2)
    return image    


img = gr.inputs.Image(shape=(192, 192))

intf = gr.Interface(fn=detect, inputs=img, outputs='image')
intf.launch(inline=False)