detect

import argparse
import time
from pathlib import Path

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

def detect(save_img=False):
    agnostic_nms, augment, classes, exist_ok, no_trace, nosave, save_conf, save_txt = False, False, None, False, False, False, False, False
    conf_thres, iou_thres, imgsz = 0.45, 0.45, 640
    device, update, view_img = '', False, False
    trace = no_trace
    save_img = not nosave and not source.endswith('.txt')  # save inference images
    # Directories
    save_dir = Path(increment_path(Path(project) / name, exist_ok=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(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
    # Set Dataloader
    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]
    # print("object predict classname and color:",names,colors)
    # while True:
    t0 = time.time()
    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)
        # Inference
        t1 = time_synchronized()

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

        # Apply NMS
        pred = non_max_suppression(pred, conf_thres, iou_thres, classes=classes, agnostic=agnostic_nms)
        t3 = time_synchronized()
        # Process detections
        with open(r"D:\LABELAOI\Test\Yovo7_predictions.txt", "a")as ffff:
            class_label = ""
            for i, det in enumerate(pred):  # detections per image
                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
                print("save path is:", save_path, "txtpath is:", txt_path, "p is:", p)
                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
                        s += f"{n} {names[int(c)]}{'s' * (n > 1)}, "  # add to string

                    # Write results
                    with open(r"D:\LABELAOI\Test\label_position.txt", "a")as wLab:
                        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 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(
                                # f'--------------plot_one_box({xyxy}, {im0}, label={label}, color={colors[int(cls)]}, line_thickness=1)')
                                x1 = int(xyxy[0].item())
                                y1 = int(xyxy[1].item())
                                x2 = int(xyxy[2].item())
                                y2 = int(xyxy[3].item())

                                wLab.write(
                                    p.name + "," + label + "," + str(x1) + "," + str(x2) + "," + str(y1) + "," + str(
                                        y2) + "\n")
                                class_label = label
                            # Print time (inference + NMS)
                            results = str(label.split(" ")).replace("[", "").replace("]", "").replace("'", "").replace(
                                " ", "")
                            ffff.write(f"{results}" + "\n")
                print(f'{s}Done. ({(1E3 * (t2 - t1)):.1f}ms) Inference, ({(1E3 * (t3 - t2)):.1f}ms) NMS')

            # Save results (image with detections)
            if save_img:
                if dataset.mode == 'image':
                    if class_label:
                        cv2.imwrite(save_path, im0)
                #                  print(f" The image with the result is saved in: {save_path}")

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

if __name__ == '__main__':
    name = 'D:\\LABELAOI\\Test\\Yolov7_Test\\predictionsv7'
    project = 'D:\\LABELAOI\\Test\\Yolov7_predictions'
    source = 'D:\\LABELAOI\\Test'
    weights = ['e:\\best.pt']
    with torch.no_grad():
        detect()