detect_custom.py

import argparse
import time
from pathlib import Path

import cv2
import torch
import torch.backends.cudnn as cudnn
from numpy import random
import PySimpleGUI as sg

from models.experimental import attempt_load
from utils.datasets import LoadStreams, LoadImages
from utils.general import check_img_size, check_requirements, check_imshow, non_max_suppression, apply_classifier, \
    scale_coords, xyxy2xywh, strip_optimizer, set_logging, increment_path
from utils.plots import plot_one_box
from utils.torch_utils import select_device, load_classifier, time_synchronized, TracedModel
import time
import threading
from collections import deque





def null(x):
    pass

def gather_video_frame(video_frames, im0):
    video_frames.append(cv2.imencode('.png', im0)[1].tobytes())

def update_video(windows, frame):
    windows[-3].update(data=frame)

def update_text(windows, fps, start):
    sec = int(time.time() - start)
    hr = sec//3600
    min = (sec%3600)//60
    sec = (sec%3600)%60
    windows[-2].update(f'{fps} FPS')
    windows[-1].update(f'Uptime : {hr} Hours {min} Minutes and {sec} Seconds')

def detect(windows, window, save_img=True):
    start = time.time()
    # cv2.namedWindow("image", cv2.WINDOW_NORMAL)
    # cv2.moveWindow("image", 20, 30)
    # cv2.resizeWindow("image", 1460, 1080)
    # cv2.createTrackbar("Threshold", "image", 10, 90, null)
    source, weights, view_img, save_txt, imgsz, trace = opt.source, opt.weights, opt.view_img, opt.save_txt, opt.img_size, not opt.no_trace
    save_img = not opt.nosave and not source.endswith('.txt')  # save inference images
    webcam = source.isnumeric() or source.endswith('.txt') or source.lower().startswith(
        ('rtsp://', 'rtmp://', 'http://', 'https://'))

    # Directories
    save_dir = Path(increment_path(Path(opt.project) / opt.name, exist_ok=opt.exist_ok))  # increment run
    (save_dir / 'labels' if save_txt else save_dir).mkdir(parents=True, exist_ok=True)  # make dir

    # Initialize
    set_logging()
    device = select_device(opt.device)
    half = device.type != 'cpu'  # half precision only supported on CUDA

    # Load model
    model = attempt_load(weights, map_location=device)  # load FP32 model
    stride = int(model.stride.max())  # model stride
    imgsz = check_img_size(imgsz, s=stride)  # check img_size

    if trace:
        model = TracedModel(model, device, opt.img_size)

    if half:
        model.half()  # to FP16

    # Second-stage classifier
    classify = False
    if classify:
        modelc = load_classifier(name='resnet101', n=2)  # initialize
        modelc.load_state_dict(torch.load('weights/resnet101.pt', map_location=device)['model']).to(device).eval()

    # Set Dataloader
    vid_path, vid_writer = None, None
    if webcam:
        view_img = check_imshow()
        cudnn.benchmark = True  # set True to speed up constant image size inference
        dataset = LoadStreams(source, img_size=imgsz, stride=stride)
    else:
        dataset = LoadImages(source, img_size=imgsz, stride=stride)

    # Get names and colors
    names = model.module.names if hasattr(model, 'module') else model.names
    colors = [[random.randint(0, 255) for _ in range(3)] for _ in names]

    # Run inference
    if device.type != 'cpu':
        model(torch.zeros(1, 3, imgsz, imgsz).to(device).type_as(next(model.parameters())))  # run once
    old_img_w = old_img_h = imgsz
    old_img_b = 1

    t0 = time.time()
    video_frames = deque(maxlen=50)

    for path, img, im0s, vid_cap in dataset:
        img = torch.from_numpy(img).to(device)
        img = img.half() if half else img.float()  # uint8 to fp16/32
        img /= 255.0  # 0 - 255 to 0.0 - 1.0
        if img.ndimension() == 3:
            img = img.unsqueeze(0)

        # Warmup
        if device.type != 'cpu' and (old_img_b != img.shape[0] or old_img_h != img.shape[2] or old_img_w != img.shape[3]):
            old_img_b = img.shape[0]
            old_img_h = img.shape[2]
            old_img_w = img.shape[3]
            for i in range(3):
                model(img, augment=opt.augment)[0]

        # Inference
        t1 = time_synchronized()
        with torch.no_grad():   # Calculating gradients would cause a GPU memory leak
            pred = model(img, augment=opt.augment)[0]
        t2 = time_synchronized()

        # Apply NMS
        pred = non_max_suppression(pred, opt.conf_thres, opt.iou_thres, classes=opt.classes, agnostic=opt.agnostic_nms)
        t3 = time_synchronized()

        # Apply Classifier
        if classify:
            pred = apply_classifier(pred, modelc, img, im0s)

        event, values = window.read(timeout=0.1)
        results = {'person' : 0, 'bike' : 0, 'car' : 0, 'motor' : 0, 'bus' : 0, 'train' : 0, 'truck' : 0, 'light' : 0, 'hydrant' : 0, 'sign' : 0, 'dog' : 0, 'deer' : 0, 'skateboard' : 0, 'stroller' : 0, 'scooter' : 0, 'other vehicle' : 0}
        cats = ['person', 'bike', 'car', 'motor', 'bus', 'train', 'truck', 'light', 'hydrant', 'sign', 'dog', 'deer', 'skateboard', 'stroller', 'scooter', 'other vehicle']
        # Process detections
        frame_time = 0
        for i, det in enumerate(pred):  # detections per image
            if webcam:  # batch_size >= 1
                p, s, im0, frame = path[i], '%g: ' % i, im0s[i].copy(), dataset.count
            else:
                p, s, im0, frame = path, '', im0s, getattr(dataset, 'frame', 0)

            p = Path(p)  # to Path
            save_path = str(save_dir / p.name)  # img.jpg
            txt_path = str(save_dir / 'labels' / p.stem) + ('' if dataset.mode == 'image' else f'_{frame}')  # img.txt
            gn = torch.tensor(im0.shape)[[1, 0, 1, 0]]  # normalization gain whwh
            if len(det):
                # Rescale boxes from img_size to im0 size
                det[:, :4] = scale_coords(img.shape[2:], det[:, :4], im0.shape).round()

                # Print results
                for c in det[:, -1].unique():
                    n = (det[:, -1] == c).sum()  # detections per class
                    results[names[int(c)]] = f'{n}'
                    s += f"{n} {names[int(c)]}{'s' * (n > 1)}, "  # add to string

                # Write results
                for *xyxy, conf, cls in reversed(det):
                    if save_txt:  # Write to file
                        xywh = (xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist()  # normalized xywh
                        line = (cls, *xywh, conf) if opt.save_conf else (cls, *xywh)  # label format
                        with open(txt_path + '.txt', 'a') as f:
                            f.write(('%g ' * len(line)).rstrip() % line + '\n')

                    if save_img or view_img:  # Add bbox to image
                        label = f'{names[int(cls)]} {conf:.2f}'
                        plot_one_box(xyxy, im0, label=label, color=colors[int(cls)], line_thickness=1)

            # Print time (inference + NMS)
            print(f'{s}Done. ({(1E3 * (t2 - t1)):.1f}ms) Inference, ({(1E3 * (t3 - t2)):.1f}ms) NMS')
            frame_time += (1E3 * (t3 - t1))
            
            # Stream results
            if view_img:
                fps = f'{1/(t3 - t1):.1f}'
                # threading.Thread(target=update_text, args=(windows, fps, start)).start()
                update_text(windows, fps, start)
                for i in range (0, 16):
                    windows[i].update(f'{cats[i]} : {results[cats[i]]}')
                # cv2.imshow('image', im0)
                threading.Thread(target=gather_video_frame, args=(video_frames, im0)).start()
                # gather_video_frame(video_frames, im0)
                # cv2.waitKey(1)  # 1 millisecond
                if event == 'Exit' or event == sg.WIN_CLOSED:
                    exit()
                opt.conf_thres = values['-THRESH SLIDER-']

                if len(video_frames) > 2:
                    frame = video_frames.popleft()
                    # t3 = threading.Thread(target=update_video, args=(windows, frame), daemon=True)
                    # t3.start()
                    update_video(windows, frame)
                # opt.conf_thres = cv2.getTrackbarPos('Threshold','image')/100


            # Save results (image with detections)
            if save_img:
                if dataset.mode == 'image':
                    cv2.imwrite(save_path, im0)
                    print(f" The image with the result is saved in: {save_path}")
                else:  # 'video' or 'stream'
                    if vid_path != save_path:  # new video
                        vid_path = save_path
                        if isinstance(vid_writer, cv2.VideoWriter):
                            vid_writer.release()  # release previous video writer
                        if vid_cap:  # video
                            fps = vid_cap.get(cv2.CAP_PROP_FPS)
                            w = int(vid_cap.get(cv2.CAP_PROP_FRAME_WIDTH))
                            h = int(vid_cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
                        else:  # stream
                            fps, w, h = 30, im0.shape[1], im0.shape[0]
                            save_path += '.mp4'
                        
                        vid_writer = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*'mp4v'), fps, (w, h))
                    vid_writer.write(im0)
            

    print(f'{1000/(frame_time/len(pred)):.3f}fps')
    if save_txt or save_img:
        s = f"\n{len(list(save_dir.glob('labels/*.txt')))} labels saved to {save_dir / 'labels'}" if save_txt else ''
        print(f"Results saved to {save_dir}{s}")

    print(f'Done. ({time.time() - t0:.3f}s)')
    



if __name__ == '__main__':
    parser = argparse.ArgumentParser()
    parser.add_argument('--weights', nargs='+', type=str, default='yolov7.pt', help='model.pt path(s)')
    parser.add_argument('--source', type=str, default='inference/images', help='source')  # file/folder, 0 for webcam
    parser.add_argument('--img-size', type=int, default=640, help='inference size (pixels)')
    parser.add_argument('--conf-thres', type=float, default=0.25, help='object confidence threshold')
    parser.add_argument('--iou-thres', type=float, default=0.45, help='IOU threshold for NMS')
    parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
    parser.add_argument('--view-img', action='store_true', help='display results')
    parser.add_argument('--save-txt', action='store_true', help='save results to *.txt')
    parser.add_argument('--save-conf', action='store_true', help='save confidences in --save-txt labels')
    parser.add_argument('--nosave', action='store_true', help='do not save images/videos')
    parser.add_argument('--classes', nargs='+', type=int, help='filter by class: --class 0, or --class 0 2 3')
    parser.add_argument('--agnostic-nms', action='store_true', help='class-agnostic NMS')
    parser.add_argument('--augment', action='store_true', help='augmented inference')
    parser.add_argument('--update', action='store_true', help='update all models')
    parser.add_argument('--project', default='runs/detect', help='save results to project/name')
    parser.add_argument('--name', default='exp', help='save results to project/name')
    parser.add_argument('--exist-ok', action='store_true', help='existing project/name ok, do not increment')
    parser.add_argument('--no-trace', action='store_true', help='don`t trace model')
    opt = parser.parse_args()
    print(opt)
    #check_requirements(exclude=('pycocotools', 'thop'))

    sg.theme('Default1')
    layout = [
        [sg.Text('Control Panel', size=(100, 1), justification='center')],
        [sg.Image(filename='', key='-IMAGE-')],
        [sg.Text(text='', size=(100, 1), justification='center', key='-FPS-')],
        [sg.Text(text='Person : 0', size=(100, 1), key='-CAT PERSON-')],
        [sg.Text(text='bike : 0', size=(100, 1), key='-CAT BIKE-')],
        [sg.Text(text='car : 0', size=(100, 1), key='-CAT CAR-')],
        [sg.Text(text='motor : 0', size=(100, 1), key='-CAT MOTOR-')],
        [sg.Text(text='bus : 0', size=(100, 1), key='-CAT BUS-')],
        [sg.Text(text='train : 0', size=(100, 1), key='-CAT TRAIN-')],
        [sg.Text(text='truck : 0', size=(100, 1), key='-CAT TRUCK-')],
        [sg.Text(text='light : 0', size=(100, 1), key='-CAT LIGHT-')],
        [sg.Text(text='hydrant : 0', size=(100, 1), key='-CAT HYDRANT-')],
        [sg.Text(text='sign : 0', size=(100, 1), key='-CAT SIGN-')],
        [sg.Text(text='dog : 0', size=(100, 1), key='-CAT DOG-')],
        [sg.Text(text='deer : 0', size=(100, 1), key='-CAT DEER-')],
        [sg.Text(text='skateboard : 0', size=(100, 1), key='-CAT SKATEBOARD-')],
        [sg.Text(text='stroller : 0', size=(100, 1), key='-CAT STROLLER-')],
        [sg.Text(text='scooter : 0', size=(100, 1), key='-CAT SCOOTER-')],
        [sg.Text(text='other vehicle : 0', size=(100, 1), key='-CAT OTHER-')],
        [sg.Text('Threshold', size=(10, 1), key='-THRESH-'),
        sg.Slider((0.1, 0.9), 0.5, 0.01, orientation='h', size=(40, 15), key='-THRESH SLIDER-')],
        [sg.Button('Exit', size=(100, 1))],
        [sg.Text(text='', size=(100, 1), key='-UPTIME-')]
    ]
    window = sg.Window('FLIR APK IR camera + YOLOv7', layout, location=(0, 0), size=(1920, 1080), keep_on_top=True, alpha_channel=1, no_titlebar=True, grab_anywhere=True)
    screen_width, screen_height = window.get_screen_dimensions()
    
    with torch.no_grad():
        if opt.update:  # update all models (to fix SourceChangeWarning)
            for opt.weights in ['yolov7.pt']:
                detect()
                strip_optimizer(opt.weights)
        else:
            windows = [window['-CAT PERSON-'], window['-CAT BIKE-'], window['-CAT CAR-'], window['-CAT MOTOR-'], window['-CAT BUS-']
                       , window['-CAT TRAIN-'], window['-CAT TRUCK-'], window['-CAT LIGHT-'], window['-CAT HYDRANT-'], window['-CAT SIGN-'], window['-CAT DOG-']
                       , window['-CAT DEER-'], window['-CAT SKATEBOARD-'], window['-CAT STROLLER-'], window['-CAT SCOOTER-'], window['-CAT OTHER-'],
                       window['-IMAGE-'], window['-FPS-'], window['-UPTIME-']]
            detect(windows, window)

# cats = ['person', 'bike', 'car', 'motor', 'bus', 'train', 'truck', 'light', 'hydrant', 'sign', 'dog', 'deer', 'skateboard', 'stroller', 'scooter', 'other vehicle']