app.py

import gradio as gr
import matplotlib.pyplot as plt
from PIL import Image
from ultralyticsplus import YOLO
import cv2
import numpy as np
from transformers import pipeline
import requests
from io import BytesIO
import os

model = YOLO('best (1).pt')
model2 = pipeline('image-classification','Kaludi/csgo-weapon-classification')
name = ['grenade','knife','pistol','rifle']
image_directory = "/home/user/app/image"
video_directory = "/home/user/app/video"

# url_example="https://drive.google.com/file/d/1bBq0bNmJ5X83tDWCzdzHSYCdg-aUL4xO/view?usp=drive_link"
# url_example='https://drive.google.com/uc?id=' + url_example.split('/')[-2]
# r = requests.get(url_example)
# im1 = Image.open(BytesIO(r.content))

# url_example="https://drive.google.com/file/d/16Z7QzvZ99fbEPj1sls_jOCJBsC0h_dYZ/view?usp=drive_link"
# url_example='https://drive.google.com/uc?id=' + url_example.split('/')[-2]
# r = requests.get(url_example)
# im2 = Image.open(BytesIO(r.content))

# url_example="https://drive.google.com/file/d/13mjTMS3eR0AKYSbV-Fpb3fTBno_T42JN/view?usp=drive_link"
# url_example='https://drive.google.com/uc?id=' + url_example.split('/')[-2]
# r = requests.get(url_example)
# im3 = Image.open(BytesIO(r.content))

# url_example="https://drive.google.com/file/d/1-XpFsa_nz506Ul6grKElVJDu_Jl3KZIF/view?usp=drive_link"
# url_example='https://drive.google.com/uc?id=' + url_example.split('/')[-2]
# r = requests.get(url_example)
# im4 = Image.open(BytesIO(r.content))
 # for i, r in enumerate(results):
      
 #    # Plot results image
 #      im_bgr = r.plot()  
 #      im_rgb = im_bgr[..., ::-1]  # Convert BGR to RGB

def response(image):
  print(image)
  results = model(image)
  text = ""
  name_weap = ""
    
  for r in results:
    conf = np.array(r.boxes.conf)
    cls = np.array(r.boxes.cls)
    cls = cls.astype(int)
    xywh = np.array(r.boxes.xywh)
    xywh = xywh.astype(int)  
      
    for con, cl, xy in zip(conf, cls, xywh):
        cone = con.astype(float)
        conef = round(cone,3)
        conef = conef * 100
        text += (f"Detected {name[cl]} with confidence {round(conef,1)}% at ({xy[0]},{xy[1]})\n")
        
        if cl == 0:
            name_weap += name[cl] + '\n'
        elif cl == 1:
            name_weap += name[cl] + '\n'
        elif cl == 2:
            out = model2(image)
            name_weap += out[0]["label"] + '\n'
        elif cl == 3:
            out = model2(image)
            name_weap += out[0]["label"] + '\n'

        
    # im_rgb = Image.fromarray(im_rgb)
    
      
    return name_weap, text



def response2(image: gr.Image = None,image_size: gr.Slider = 640, conf_threshold: gr.Slider = 0.3, iou_threshold: gr.Slider = 0.6):

    results = model.predict(image, conf=conf_threshold, iou=iou_threshold, imgsz=image_size)
    
    box = results[0].boxes

    for r in results:
        im_array = r.plot()
        im = Image.fromarray(im_array[..., ::-1])

    
    weapon_name, text_detection = response(image)
   
    
    # xywh = int(results.boxes.xywh)
    # x = xywh[0]
    # y = xywh[1]
           
    return im, text_detection, weapon_name


inputs = [
    gr.Image(type="pil",  label="Input Image"),
    gr.Slider(minimum=320, maximum=1280, value=640,
                     step=32, label="Image Size"),
    gr.Slider(minimum=0.0, maximum=1.0, value=0.3,
                     step=0.05, label="Confidence Threshold"),
    gr.Slider(minimum=0.0, maximum=1.0, value=0.6,
                     step=0.05, label="IOU Threshold"),
]

outputs = [gr.Image( type="pil", label="Output Image"),
           gr.Textbox(label="Result"),
           gr.Textbox(label="Weapon Name")
          ]

examples = [[os.path.join(image_directory, "th (5).jpg"),640, 0.3, 0.6],
            [os.path.join(image_directory, "th (8).jpg"),640, 0.3, 0.6],
            [os.path.join(image_directory, "th (11).jpg"),640, 0.3, 0.6],
            [os.path.join(image_directory, "th (3).jpg"),640, 0.3, 0.6]
           ]
title = 'Weapon Detection Finetuned YOLOv8'
description = 'Image Size: Defines the image size for inference.\nConfidence Treshold: Sets the minimum confidence threshold for detections.\nIOU Treshold: Intersection Over Union (IoU) threshold for Non-Maximum Suppression (NMS). Useful for reducing duplicates.'


def pil_to_cv2(pil_image):
    open_cv_image = cv2.cvtColor(np.array(pil_image), cv2.COLOR_RGB2BGR)
    return open_cv_image


def process_video(video_path):
    cap = cv2.VideoCapture(video_path)
    
    while cap.isOpened():
        ret, frame = cap.read()
        if not ret:
            break
        
        pil_img = Image.fromarray(frame[..., ::-1])  
        result = model.predict(source=pil_img)
        for r in result:
            im_array = r.plot()
            processed_frame = Image.fromarray(im_array[..., ::-1])  
        yield processed_frame
    cap.release()


video_iface = gr.Interface(
    fn=process_video,
    inputs=[
        gr.Video(label="Upload Video", interactive=True)
    ],
    outputs=gr.Image(type="pil",label="Result"),
    title=title,
    description="Upload video for inference.",
    examples=[[os.path.join(video_directory, "ExampleRifle.mp4")],
        [os.path.join(video_directory, "Knife.mp4")],
    ]
)


image_iface = gr.Interface(fn=response2, inputs=inputs, outputs=outputs, examples=examples, title=title, description=description)

demo = gr.TabbedInterface([image_iface, video_iface], ["Image Inference", "Video Inference"])

if __name__ == '__main__':
    demo.launch()