diff --git a/.gitignore b/.gitignore
old mode 100755
new mode 100644
diff --git a/data/scripts/download_weights.sh b/data/scripts/download_weights.sh
old mode 100755
new mode 100644
diff --git a/data/scripts/get_coco.sh b/data/scripts/get_coco.sh
old mode 100755
new mode 100644
diff --git a/data/scripts/get_coco128.sh b/data/scripts/get_coco128.sh
old mode 100755
new mode 100644
diff --git a/data/scripts/get_imagenet.sh b/data/scripts/get_imagenet.sh
old mode 100755
new mode 100644
diff --git a/detect2.py b/detect2.py
new file mode 100644
index 000000000000..e54ce21e6800
--- /dev/null
+++ b/detect2.py
@@ -0,0 +1,334 @@
+# YOLOv5 🚀 by Ultralytics, AGPL-3.0 license
+"""
+Run YOLOv5 detection inference on images, videos, directories, globs, YouTube, webcam, streams, etc.
+
+Usage - sources:
+    $ python detect.py --weights yolov5s.pt --source 0                               # webcam
+                                                     img.jpg                         # image
+                                                     vid.mp4                         # video
+                                                     screen                          # screenshot
+                                                     path/                           # directory
+                                                     list.txt                        # list of images
+                                                     list.streams                    # list of streams
+                                                     'path/*.jpg'                    # glob
+                                                     'https://youtu.be/Zgi9g1ksQHc'  # YouTube
+                                                     'rtsp://example.com/media.mp4'  # RTSP, RTMP, HTTP stream
+
+Usage - formats:
+    $ python detect.py --weights yolov5s.pt                 # PyTorch
+                                 yolov5s.torchscript        # TorchScript
+                                 yolov5s.onnx               # ONNX Runtime or OpenCV DNN with --dnn
+                                 yolov5s_openvino_model     # OpenVINO
+                                 yolov5s.engine             # TensorRT
+                                 yolov5s.mlmodel            # CoreML (macOS-only)
+                                 yolov5s_saved_model        # TensorFlow SavedModel
+                                 yolov5s.pb                 # TensorFlow GraphDef
+                                 yolov5s.tflite             # TensorFlow Lite
+                                 yolov5s_edgetpu.tflite     # TensorFlow Edge TPU
+                                 yolov5s_paddle_model       # PaddlePaddle
+"""
+
+import argparse
+import os
+import platform
+import sys
+from pathlib import Path
+
+import torch
+
+FILE = Path(__file__).resolve()
+ROOT = FILE.parents[0]  # YOLOv5 root directory
+if str(ROOT) not in sys.path:
+    sys.path.append(str(ROOT))  # add ROOT to PATH
+ROOT = Path(os.path.relpath(ROOT, Path.cwd()))  # relative
+
+from models.common import DetectMultiBackend
+from utils.dataloaders import IMG_FORMATS, VID_FORMATS, LoadImages, LoadScreenshots, LoadStreams
+from utils.general import (
+    LOGGER,
+    Profile,
+    check_file,
+    check_img_size,
+    check_imshow,
+    check_requirements,
+    colorstr,
+    cv2,
+    increment_path,
+    non_max_suppression,
+    print_args,
+    scale_boxes,
+    strip_optimizer,
+    xyxy2xywh,
+)
+from utils.plots import Annotator, colors, save_one_box
+from utils.torch_utils import select_device, smart_inference_mode
+
+
+@smart_inference_mode()
+def run(
+    weights=ROOT / "yolov5s.pt",  # model path or triton URL
+    source=ROOT / "data/images",  # file/dir/URL/glob/screen/0(webcam)
+    data=ROOT / "data/coco128.yaml",  # dataset.yaml path
+    imgsz=(640, 640),  # inference size (height, width)
+    conf_thres=0.25,  # confidence threshold
+    iou_thres=0.45,  # NMS IOU threshold
+    max_det=1000,  # maximum detections per image
+    device="",  # cuda device, i.e. 0 or 0,1,2,3 or cpu
+    view_img=False,  # show results
+    save_txt=False,  # save results to *.txt
+    save_conf=False,  # save confidences in --save-txt labels
+    save_crop=False,  # save cropped prediction boxes
+    nosave=False,  # do not save images/videos
+    classes=None,  # filter by class: --class 0, or --class 0 2 3
+    agnostic_nms=False,  # class-agnostic NMS
+    augment=False,  # augmented inference
+    visualize=False,  # visualize features
+    update=False,  # update all models
+    project=ROOT / "runs/detect",  # save results to project/name
+    name="exp",  # save results to project/name
+    exist_ok=False,  # existing project/name ok, do not increment
+    line_thickness=3,  # bounding box thickness (pixels)
+    hide_labels=False,  # hide labels
+    hide_conf=False,  # hide confidences
+    half=False,  # use FP16 half-precision inference
+    dnn=False,  # use OpenCV DNN for ONNX inference
+    vid_stride=1,  # video frame-rate stride
+):
+    source = str(source)
+    save_img = True  # not nosave and not source.endswith('.txt')  # save inference images
+    is_file = Path(source).suffix[1:] in (IMG_FORMATS + VID_FORMATS)
+    is_url = source.lower().startswith(("rtsp://", "rtmp://", "http://", "https://"))
+    webcam = source.isnumeric() or source.endswith(".streams") or (is_url and not is_file)
+    screenshot = source.lower().startswith("screen")
+    if is_url and is_file:
+        source = check_file(source)  # download
+
+    # définir les classes dont on veut afficher les rectangles sur les images, afficher les 3 en même temps peut rendre l'image difficilement lisble
+    liste_classes_sauvegardées = ["Porte-Aiguille"]
+    # Autres classes possibles : "GepBox" ou "Pincette"
+
+    # Directories
+    save_dir = 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
+
+    # Load model
+    device = select_device(device)
+    model = DetectMultiBackend(weights, device=device, dnn=dnn, data=data, fp16=half)
+    stride, names, pt = model.stride, model.names, model.pt
+    imgsz = check_img_size(imgsz, s=stride)  # check image size
+
+    # Dataloader
+    bs = 1  # batch_size
+    if webcam:
+        view_img = check_imshow(warn=True)
+        dataset = LoadStreams(source, img_size=imgsz, stride=stride, auto=pt, vid_stride=vid_stride)
+        bs = len(dataset)
+    elif screenshot:
+        dataset = LoadScreenshots(source, img_size=imgsz, stride=stride, auto=pt)
+    else:
+        dataset = LoadImages(source, img_size=imgsz, stride=stride, auto=pt, vid_stride=vid_stride)
+    vid_path, vid_writer = [None] * bs, [None] * bs
+
+    # Run inference
+    model.warmup(imgsz=(1 if pt or model.triton else bs, 3, *imgsz))  # warmup
+    seen, windows, dt = 0, [], (Profile(), Profile(), Profile())
+    compteur = 0
+    for path, im, im0s, vid_cap, s in dataset:
+        with dt[0]:
+            im = torch.from_numpy(im).to(model.device)
+            im = im.half() if model.fp16 else im.float()  # uint8 to fp16/32
+            im /= 255  # 0 - 255 to 0.0 - 1.0
+            if len(im.shape) == 3:
+                im = im[None]  # expand for batch dim
+
+        # Inference
+        with dt[1]:
+            visualize = increment_path(save_dir / Path(path).stem, mkdir=True) if visualize else False
+            pred = model(im, augment=augment, visualize=visualize)
+
+        # NMS
+        with dt[2]:
+            pred = non_max_suppression(pred, conf_thres, iou_thres, classes, agnostic_nms, max_det=max_det)
+
+        # Second-stage classifier (optional)
+        # pred = utils.general.apply_classifier(pred, classifier_model, im, im0s)
+
+        # Process predictions
+        count = 0
+        for i, det in enumerate(pred):  # per image
+            compteur += 1
+            count += 1
+            seen += 1
+            if webcam:  # batch_size >= 1
+                p, im0, frame = path[i], im0s[i].copy(), dataset.count
+                s += f"{i}: "
+            else:
+                p, im0, frame = path, im0s.copy(), getattr(dataset, "frame", 0)
+            l = p.split("/")[-1].split("jpg")[0].split("_")
+            # print(l)
+            save_name = l[0] + "_" + l[1] + "_" + l[2]
+            id_texte = l[-1]
+            chemin = save_name + "_coordinates.txt"
+            if not os.path.isfile(chemin):
+                f = open(chemin, "w")
+                f.write("ID, x1, y1, x2, y2, Confidence, Classe\n")
+                f.close()
+            p = Path(p)  # to Path
+
+            save_path = str(save_dir / p.name)  # im.jpg
+            txt_path = str(save_dir / "labels" / p.stem) + ("" if dataset.mode == "image" else f"_{frame}")  # im.txt
+            s += "%gx%g " % im.shape[2:]  # print string
+            gn = torch.tensor(im0.shape)[[1, 0, 1, 0]]  # normalization gain whwh
+            imc = im0.copy() if save_crop else im0  # for save_crop
+            annotator = Annotator(im0, line_width=line_thickness, example=str(names))
+            if len(det):
+                # Rescale boxes from img_size to im0 size
+                det[:, :4] = scale_boxes(im.shape[2:], det[:, :4], im0.shape).round()
+
+                # Print results
+                for c in det[:, 5].unique():
+                    n = (det[:, 5] == c).sum()  # detections per class
+                    s += f"{n} {names[int(c)]}{'s' * (n > 1)}, "  # add to string
+
+                # Write results
+                l_max = [0] * len(names)
+                count_max = 0
+                for *xyxy, conf, cls in reversed(det):
+                    count_max += 1
+                    if l_max[int(cls)] < float(conf.cpu().numpy()):
+                        l_max[int(cls)] = count_max
+
+                count_max = 0
+                for *xyxy, conf, cls in reversed(det):
+                    count_max += 1
+                    if (
+                        save_txt and l_max[int(cls)] == count_max
+                    ):  # Write to file if box with maximum conf for one class
+                        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
+                        x1 = int(xyxy[0].item())
+                        y1 = int(xyxy[1].item())
+                        x2 = int(xyxy[2].item())
+                        y2 = int(xyxy[3].item())
+
+                        confidence_score = conf
+                        conf = float(conf.cpu().numpy())
+                        class_index = cls
+                        object_name = names[int(cls)]
+                        f = open(chemin, "a+")
+                        f.write(
+                            id_texte
+                            + ","
+                            + str(x1)
+                            + ","
+                            + str(y1)
+                            + ","
+                            + str(x2)
+                            + ","
+                            + str(y2)
+                            + ","
+                            + str(conf)
+                            + ","
+                            + str(object_name)
+                            + "\n"
+                        )
+                        f.close()
+
+                    if (
+                        (save_img or save_crop or view_img)
+                        and l_max[int(cls)] == count_max
+                        and names[int(cls)] in liste_classes_sauvegardées
+                    ):  # Add bbox to image if box with maximum conf for PorteAiguille class
+                        c = int(cls)  # integer class
+                        label = None if hide_labels else (names[c] if hide_conf else f"{names[c]} {conf:.2f}")
+                        annotator.box_label(xyxy, label, color=colors(c, True))
+
+                    count_max += 1
+
+                    if save_crop:
+                        save_one_box(xyxy, imc, file=save_dir / "crops" / names[c] / f"{p.stem}.jpg", BGR=True)
+            # Stream results
+            im0 = annotator.result()
+            if view_img:
+                if platform.system() == "Linux" and p not in windows:
+                    windows.append(p)
+                    cv2.namedWindow(str(p), cv2.WINDOW_NORMAL | cv2.WINDOW_KEEPRATIO)  # allow window resize (Linux)
+                    cv2.resizeWindow(str(p), im0.shape[1], im0.shape[0])
+                cv2.imshow(str(p), im0)
+                cv2.waitKey(1)  # 1 millisecond
+
+            # Save results (image with detections)
+            if save_img:
+                if dataset.mode == "image":
+                    cv2.imwrite(save_path, im0)
+                else:  # 'video' or 'stream'
+                    if vid_path[i] != save_path:  # new video
+                        vid_path[i] = save_path
+                        if isinstance(vid_writer[i], cv2.VideoWriter):
+                            vid_writer[i].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 = str(Path(save_path).with_suffix(".mp4"))  # force *.mp4 suffix on results videos
+                        vid_writer[i] = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*"mp4v"), fps, (w, h))
+                    vid_writer[i].write(im0)
+
+        # Print time (inference-only)
+        LOGGER.info(f"{s}{'' if len(det) else '(no detections), '}{dt[1].dt * 1E3:.1f}ms")
+
+    # Print results
+    t = tuple(x.t / seen * 1e3 for x in dt)  # speeds per image
+    LOGGER.info(f"Speed: %.1fms pre-process, %.1fms inference, %.1fms NMS per image at shape {(1, 3, *imgsz)}" % t)
+    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 ""
+        LOGGER.info(f"Results saved to {colorstr('bold', save_dir)}{s}")
+    if update:
+        strip_optimizer(weights[0])  # update model (to fix SourceChangeWarning)
+
+
+def parse_opt():
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--weights", nargs="+", type=str, default=ROOT / "yolov5s.pt", help="model path or triton URL")
+    parser.add_argument("--source", type=str, default=ROOT / "data/images", help="file/dir/URL/glob/screen/0(webcam)")
+    parser.add_argument("--data", type=str, default=ROOT / "data/coco128.yaml", help="(optional) dataset.yaml path")
+    parser.add_argument("--imgsz", "--img", "--img-size", nargs="+", type=int, default=[640], help="inference size h,w")
+    parser.add_argument("--conf-thres", type=float, default=0.25, help="confidence threshold")
+    parser.add_argument("--iou-thres", type=float, default=0.45, help="NMS IoU threshold")
+    parser.add_argument("--max-det", type=int, default=1000, help="maximum detections per image")
+    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="show 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("--save-crop", action="store_true", help="save cropped prediction boxes")
+    parser.add_argument("--nosave", action="store_true", help="do not save images/videos")
+    parser.add_argument("--classes", nargs="+", type=int, help="filter by class: --classes 0, or --classes 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("--visualize", action="store_true", help="visualize features")
+    parser.add_argument("--update", action="store_true", help="update all models")
+    parser.add_argument("--project", default=ROOT / "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("--line-thickness", default=3, type=int, help="bounding box thickness (pixels)")
+    parser.add_argument("--hide-labels", default=False, action="store_true", help="hide labels")
+    parser.add_argument("--hide-conf", default=False, action="store_true", help="hide confidences")
+    parser.add_argument("--half", action="store_true", help="use FP16 half-precision inference")
+    parser.add_argument("--dnn", action="store_true", help="use OpenCV DNN for ONNX inference")
+    parser.add_argument("--vid-stride", type=int, default=1, help="video frame-rate stride")
+    opt = parser.parse_args()
+    opt.imgsz *= 2 if len(opt.imgsz) == 1 else 1  # expand
+    print_args(vars(opt))
+    return opt
+
+
+def main(opt):
+    check_requirements(exclude=("tensorboard", "thop"))
+    run(**vars(opt))
+
+
+if __name__ == "__main__":
+    opt = parse_opt()
+    main(opt)
diff --git a/detect3.py b/detect3.py
new file mode 100644
index 000000000000..e05c624a0b17
--- /dev/null
+++ b/detect3.py
@@ -0,0 +1,320 @@
+# YOLOv5 🚀 by Ultralytics, AGPL-3.0 license
+"""
+Run YOLOv5 detection inference on images, videos, directories, globs, YouTube, webcam, streams, etc.
+
+Usage - sources:
+    $ python detect.py --weights yolov5s.pt --source 0                               # webcam
+                                                     img.jpg                         # image
+                                                     vid.mp4                         # video
+                                                     screen                          # screenshot
+                                                     path/                           # directory
+                                                     list.txt                        # list of images
+                                                     list.streams                    # list of streams
+                                                     'path/*.jpg'                    # glob
+                                                     'https://youtu.be/Zgi9g1ksQHc'  # YouTube
+                                                     'rtsp://example.com/media.mp4'  # RTSP, RTMP, HTTP stream
+
+Usage - formats:
+    $ python detect.py --weights yolov5s.pt                 # PyTorch
+                                 yolov5s.torchscript        # TorchScript
+                                 yolov5s.onnx               # ONNX Runtime or OpenCV DNN with --dnn
+                                 yolov5s_openvino_model     # OpenVINO
+                                 yolov5s.engine             # TensorRT
+                                 yolov5s.mlmodel            # CoreML (macOS-only)
+                                 yolov5s_saved_model        # TensorFlow SavedModel
+                                 yolov5s.pb                 # TensorFlow GraphDef
+                                 yolov5s.tflite             # TensorFlow Lite
+                                 yolov5s_edgetpu.tflite     # TensorFlow Edge TPU
+                                 yolov5s_paddle_model       # PaddlePaddle
+"""
+
+import argparse
+import os
+import platform
+import sys
+from pathlib import Path
+
+import torch
+
+FILE = Path(__file__).resolve()
+ROOT = FILE.parents[0]  # YOLOv5 root directory
+if str(ROOT) not in sys.path:
+    sys.path.append(str(ROOT))  # add ROOT to PATH
+ROOT = Path(os.path.relpath(ROOT, Path.cwd()))  # relative
+
+from models.common import DetectMultiBackend
+from utils.dataloaders import IMG_FORMATS, VID_FORMATS, LoadImages, LoadScreenshots, LoadStreams
+from utils.general import (
+    LOGGER,
+    Profile,
+    check_file,
+    check_img_size,
+    check_imshow,
+    check_requirements,
+    colorstr,
+    cv2,
+    increment_path,
+    non_max_suppression,
+    print_args,
+    scale_boxes,
+    strip_optimizer,
+    xyxy2xywh,
+)
+from utils.plots import Annotator, colors, save_one_box
+from utils.torch_utils import select_device, smart_inference_mode
+
+
+@smart_inference_mode()
+def run(
+    weights=ROOT / "yolov5s.pt",  # model path or triton URL
+    source=ROOT / "data/images",  # file/dir/URL/glob/screen/0(webcam)
+    data=ROOT / "data/coco128.yaml",  # dataset.yaml path
+    imgsz=(640, 640),  # inference size (height, width)
+    conf_thres=0.25,  # confidence threshold
+    iou_thres=0.45,  # NMS IOU threshold
+    max_det=1000,  # maximum detections per image
+    device="",  # cuda device, i.e. 0 or 0,1,2,3 or cpu
+    view_img=False,  # show results
+    save_txt=False,  # save results to *.txt
+    save_conf=False,  # save confidences in --save-txt labels
+    save_crop=False,  # save cropped prediction boxes
+    nosave=False,  # do not save images/videos
+    classes=None,  # filter by class: --class 0, or --class 0 2 3
+    agnostic_nms=False,  # class-agnostic NMS
+    augment=False,  # augmented inference
+    visualize=False,  # visualize features
+    update=False,  # update all models
+    project=ROOT / "runs/detect",  # save results to project/name
+    name="exp",  # save results to project/name
+    exist_ok=False,  # existing project/name ok, do not increment
+    line_thickness=3,  # bounding box thickness (pixels)
+    hide_labels=False,  # hide labels
+    hide_conf=False,  # hide confidences
+    half=False,  # use FP16 half-precision inference
+    dnn=False,  # use OpenCV DNN for ONNX inference
+    vid_stride=1,  # video frame-rate stride
+):
+    source = str(source)
+    save_img = not nosave and not source.endswith(".txt")  # save inference images
+    is_file = Path(source).suffix[1:] in (IMG_FORMATS + VID_FORMATS)
+    is_url = source.lower().startswith(("rtsp://", "rtmp://", "http://", "https://"))
+    webcam = source.isnumeric() or source.endswith(".streams") or (is_url and not is_file)
+    screenshot = source.lower().startswith("screen")
+    if is_url and is_file:
+        source = check_file(source)  # download
+
+    # Directories
+    save_dir = 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
+
+    # Load model
+    device = select_device(device)
+    model = DetectMultiBackend(weights, device=device, dnn=dnn, data=data, fp16=half)
+    stride, names, pt = model.stride, model.names, model.pt
+    imgsz = check_img_size(imgsz, s=stride)  # check image size
+
+    # Dataloader
+    bs = 1  # batch_size
+    if webcam:
+        view_img = check_imshow(warn=True)
+        dataset = LoadStreams(source, img_size=imgsz, stride=stride, auto=pt, vid_stride=vid_stride)
+        bs = len(dataset)
+    elif screenshot:
+        dataset = LoadScreenshots(source, img_size=imgsz, stride=stride, auto=pt)
+    else:
+        dataset = LoadImages(source, img_size=imgsz, stride=stride, auto=pt, vid_stride=vid_stride)
+    vid_path, vid_writer = [None] * bs, [None] * bs
+
+    # Run inference
+    model.warmup(imgsz=(1 if pt or model.triton else bs, 3, *imgsz))  # warmup
+    seen, windows, dt = 0, [], (Profile(), Profile(), Profile())
+    compteur = 0
+    path = "box_coordinates.txt"
+    f = open(path, "w")
+    f.write("ID, x1, y1, x2, y2, Confidence, Classe\n")
+    for path, im, im0s, vid_cap, s in dataset:
+        with dt[0]:
+            im = torch.from_numpy(im).to(model.device)
+            im = im.half() if model.fp16 else im.float()  # uint8 to fp16/32
+            im /= 255  # 0 - 255 to 0.0 - 1.0
+            if len(im.shape) == 3:
+                im = im[None]  # expand for batch dim
+
+        # Inference
+        with dt[1]:
+            visualize = increment_path(save_dir / Path(path).stem, mkdir=True) if visualize else False
+            pred = model(im, augment=augment, visualize=visualize)
+
+        # NMS
+        with dt[2]:
+            pred = non_max_suppression(pred, conf_thres, iou_thres, classes, agnostic_nms, max_det=max_det)
+
+        # Second-stage classifier (optional)
+        # pred = utils.general.apply_classifier(pred, classifier_model, im, im0s)
+
+        # Process predictions
+        count = 0
+        for i, det in enumerate(pred):  # per image
+            compteur += 1
+            count += 1
+            seen += 1
+            if webcam:  # batch_size >= 1
+                p, im0, frame = path[i], im0s[i].copy(), dataset.count
+                s += f"{i}: "
+            else:
+                p, im0, frame = path, im0s.copy(), getattr(dataset, "frame", 0)
+            print(p.split("/")[-1].split("jpg")[0].split("_")[-2])
+            p = Path(p)  # to Path
+
+            save_path = str(save_dir / p.name)  # im.jpg
+            txt_path = str(save_dir / "labels" / p.stem) + ("" if dataset.mode == "image" else f"_{frame}")  # im.txt
+            s += "%gx%g " % im.shape[2:]  # print string
+            gn = torch.tensor(im0.shape)[[1, 0, 1, 0]]  # normalization gain whwh
+            imc = im0.copy() if save_crop else im0  # for save_crop
+            annotator = Annotator(im0, line_width=line_thickness, example=str(names))
+            if len(det):
+                # Rescale boxes from img_size to im0 size
+                det[:, :4] = scale_boxes(im.shape[2:], det[:, :4], im0.shape).round()
+
+                # Print results
+                for c in det[:, 5].unique():
+                    n = (det[:, 5] == c).sum()  # detections per class
+                    s += f"{n} {names[int(c)]}{'s' * (n > 1)}, "  # add to string
+
+                # Write results
+                l_max = [0] * len(names)
+                count_max = 0
+                for *xyxy, conf, cls in reversed(det):
+                    count_max += 1
+                    if l_max[int(cls)] < float(conf.cpu().numpy()):
+                        l_max[int(cls)] = count_max
+
+                count_max = 0
+                for *xyxy, conf, cls in reversed(det):
+                    count_max += 1
+                    if (
+                        save_txt and l_max[int(cls)] == count_max
+                    ):  # Write to file if box with maximum conf for one class
+                        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
+                        x1 = int(xyxy[0].item())
+                        y1 = int(xyxy[1].item())
+                        x2 = int(xyxy[2].item())
+                        y2 = int(xyxy[3].item())
+
+                        confidence_score = conf
+                        conf = float(conf.cpu().numpy())
+                        class_index = cls
+                        object_name = names[int(cls)]
+
+                        f.write(
+                            str(compteur)
+                            + ","
+                            + str(x1)
+                            + ","
+                            + str(y1)
+                            + ","
+                            + str(x2)
+                            + ","
+                            + str(y2)
+                            + ","
+                            + str(conf)
+                            + ","
+                            + str(object_name)
+                            + "\n"
+                        )
+
+                    if (save_img or save_crop or view_img) and l_max[
+                        int(cls)
+                    ] == count_max:  # Add bbox to image if box with maximum conf for one class
+                        c = int(cls)  # integer class
+                        label = None if hide_labels else (names[c] if hide_conf else f"{names[c]} {conf:.2f}")
+                        annotator.box_label(xyxy, label, color=colors(c, True))
+                    if save_crop:
+                        save_one_box(xyxy, imc, file=save_dir / "crops" / names[c] / f"{p.stem}.jpg", BGR=True)
+            # Stream results
+            im0 = annotator.result()
+            if view_img:
+                if platform.system() == "Linux" and p not in windows:
+                    windows.append(p)
+                    cv2.namedWindow(str(p), cv2.WINDOW_NORMAL | cv2.WINDOW_KEEPRATIO)  # allow window resize (Linux)
+                    cv2.resizeWindow(str(p), im0.shape[1], im0.shape[0])
+                cv2.imshow(str(p), im0)
+                cv2.waitKey(1)  # 1 millisecond
+
+            # Save results (image with detections)
+            if save_img:
+                if dataset.mode == "image":
+                    cv2.imwrite(save_path, im0)
+                else:  # 'video' or 'stream'
+                    if vid_path[i] != save_path:  # new video
+                        vid_path[i] = save_path
+                        if isinstance(vid_writer[i], cv2.VideoWriter):
+                            vid_writer[i].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 = str(Path(save_path).with_suffix(".mp4"))  # force *.mp4 suffix on results videos
+                        vid_writer[i] = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*"mp4v"), fps, (w, h))
+                    vid_writer[i].write(im0)
+
+        # Print time (inference-only)
+        LOGGER.info(f"{s}{'' if len(det) else '(no detections), '}{dt[1].dt * 1E3:.1f}ms")
+
+    # Print results
+    f.close()
+    t = tuple(x.t / seen * 1e3 for x in dt)  # speeds per image
+    LOGGER.info(f"Speed: %.1fms pre-process, %.1fms inference, %.1fms NMS per image at shape {(1, 3, *imgsz)}" % t)
+    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 ""
+        LOGGER.info(f"Results saved to {colorstr('bold', save_dir)}{s}")
+    if update:
+        strip_optimizer(weights[0])  # update model (to fix SourceChangeWarning)
+
+
+def parse_opt():
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--weights", nargs="+", type=str, default=ROOT / "yolov5s.pt", help="model path or triton URL")
+    parser.add_argument("--source", type=str, default=ROOT / "data/images", help="file/dir/URL/glob/screen/0(webcam)")
+    parser.add_argument("--data", type=str, default=ROOT / "data/coco128.yaml", help="(optional) dataset.yaml path")
+    parser.add_argument("--imgsz", "--img", "--img-size", nargs="+", type=int, default=[640], help="inference size h,w")
+    parser.add_argument("--conf-thres", type=float, default=0.25, help="confidence threshold")
+    parser.add_argument("--iou-thres", type=float, default=0.45, help="NMS IoU threshold")
+    parser.add_argument("--max-det", type=int, default=1000, help="maximum detections per image")
+    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="show 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("--save-crop", action="store_true", help="save cropped prediction boxes")
+    parser.add_argument("--nosave", action="store_true", help="do not save images/videos")
+    parser.add_argument("--classes", nargs="+", type=int, help="filter by class: --classes 0, or --classes 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("--visualize", action="store_true", help="visualize features")
+    parser.add_argument("--update", action="store_true", help="update all models")
+    parser.add_argument("--project", default=ROOT / "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("--line-thickness", default=3, type=int, help="bounding box thickness (pixels)")
+    parser.add_argument("--hide-labels", default=False, action="store_true", help="hide labels")
+    parser.add_argument("--hide-conf", default=False, action="store_true", help="hide confidences")
+    parser.add_argument("--half", action="store_true", help="use FP16 half-precision inference")
+    parser.add_argument("--dnn", action="store_true", help="use OpenCV DNN for ONNX inference")
+    parser.add_argument("--vid-stride", type=int, default=1, help="video frame-rate stride")
+    opt = parser.parse_args()
+    opt.imgsz *= 2 if len(opt.imgsz) == 1 else 1  # expand
+    print_args(vars(opt))
+    return opt
+
+
+def main(opt):
+    check_requirements(exclude=("tensorboard", "thop"))
+    run(**vars(opt))
+
+
+if __name__ == "__main__":
+    opt = parse_opt()
+    main(opt)
diff --git a/export.py b/export.py
index dfb1c06fb5e2..f3216a564290 100644
--- a/export.py
+++ b/export.py
@@ -449,6 +449,7 @@ def transform_fn(data_item):
             Quantization transform function.
 
             Extracts and preprocess input data from dataloader item for quantization.
+
             Parameters:
                data_item: Tuple with data item produced by DataLoader during iteration
             Returns:
diff --git a/utils/augmentations.py b/utils/augmentations.py
index 4a6e441d7c45..bdbe07712716 100644
--- a/utils/augmentations.py
+++ b/utils/augmentations.py
@@ -156,7 +156,6 @@ def random_perspective(
 ):
     # torchvision.transforms.RandomAffine(degrees=(-10, 10), translate=(0.1, 0.1), scale=(0.9, 1.1), shear=(-10, 10))
     # targets = [cls, xyxy]
-
     """Applies random perspective transformation to an image, modifying the image and corresponding labels."""
     height = im.shape[0] + border[0] * 2  # shape(h,w,c)
     width = im.shape[1] + border[1] * 2
diff --git a/utils/callbacks.py b/utils/callbacks.py
index 0a0bcbdb2b96..21c587bd74c6 100644
--- a/utils/callbacks.py
+++ b/utils/callbacks.py
@@ -64,7 +64,6 @@ def run(self, hook, *args, thread=False, **kwargs):
             thread: (boolean) Run callbacks in daemon thread
             kwargs: Keyword Arguments to receive from YOLOv5
         """
-
         assert hook in self._callbacks, f"hook '{hook}' not found in callbacks {self._callbacks}"
         for logger in self._callbacks[hook]:
             if thread:
diff --git a/utils/dataloaders.py b/utils/dataloaders.py
index 21308f0cedbd..bdeffec465e7 100644
--- a/utils/dataloaders.py
+++ b/utils/dataloaders.py
@@ -1104,7 +1104,8 @@ def extract_boxes(path=DATASETS_DIR / "coco128"):
 def autosplit(path=DATASETS_DIR / "coco128/images", weights=(0.9, 0.1, 0.0), annotated_only=False):
     """Autosplit a dataset into train/val/test splits and save path/autosplit_*.txt files
     Usage: from utils.dataloaders import *; autosplit()
-    Arguments
+
+    Arguments:
         path:            Path to images directory
         weights:         Train, val, test weights (list, tuple)
         annotated_only:  Only use images with an annotated txt file
@@ -1183,7 +1184,7 @@ class HUBDatasetStats:
     """
     Class for generating HUB dataset JSON and `-hub` dataset directory.
 
-    Arguments
+    Arguments:
         path:           Path to data.yaml or data.zip (with data.yaml inside data.zip)
         autodownload:   Attempt to download dataset if not found locally
 
@@ -1314,7 +1315,7 @@ class ClassificationDataset(torchvision.datasets.ImageFolder):
     """
     YOLOv5 Classification Dataset.
 
-    Arguments
+    Arguments:
         root:  Dataset path
         transform:  torchvision transforms, used by default
         album_transform: Albumentations transforms, used if installed
diff --git a/utils/general.py b/utils/general.py
index e311504b3031..57db68a7ac76 100644
--- a/utils/general.py
+++ b/utils/general.py
@@ -518,7 +518,6 @@ def check_font(font=FONT, progress=False):
 
 def check_dataset(data, autodownload=True):
     """Validates and/or auto-downloads a dataset, returning its configuration as a dictionary."""
-
     # Download (optional)
     extract_dir = ""
     if isinstance(data, (str, Path)) and (is_zipfile(data) or is_tarfile(data)):
@@ -1023,7 +1022,6 @@ def non_max_suppression(
     Returns:
          list of detections, on (n,6) tensor per image [xyxy, conf, cls]
     """
-
     # Checks
     assert 0 <= conf_thres <= 1, f"Invalid Confidence threshold {conf_thres}, valid values are between 0.0 and 1.0"
     assert 0 <= iou_thres <= 1, f"Invalid IoU {iou_thres}, valid values are between 0.0 and 1.0"
diff --git a/utils/loggers/__init__.py b/utils/loggers/__init__.py
index 2bd8583d2ade..7051e8da0a29 100644
--- a/utils/loggers/__init__.py
+++ b/utils/loggers/__init__.py
@@ -350,7 +350,8 @@ class GenericLogger:
     """
     YOLOv5 General purpose logger for non-task specific logging
     Usage: from utils.loggers import GenericLogger; logger = GenericLogger(...)
-    Arguments
+
+    Arguments:
         opt:             Run arguments
         console_logger:  Console logger
         include:         loggers to include
diff --git a/utils/loggers/clearml/clearml_utils.py b/utils/loggers/clearml/clearml_utils.py
index 2b5351ef8533..de4129e08a16 100644
--- a/utils/loggers/clearml/clearml_utils.py
+++ b/utils/loggers/clearml/clearml_utils.py
@@ -80,7 +80,7 @@ def __init__(self, opt, hyp):
         - Initialize ClearML Task, this object will capture the experiment
         - Upload dataset version to ClearML Data if opt.upload_dataset is True
 
-        arguments:
+        Arguments:
         opt (namespace) -- Commandline arguments for this run
         hyp (dict) -- Hyperparameters for this run
 
@@ -133,7 +133,7 @@ def log_scalars(self, metrics, epoch):
         """
         Log scalars/metrics to ClearML.
 
-        arguments:
+        Arguments:
         metrics (dict) Metrics in dict format: {"metrics/mAP": 0.8, ...}
         epoch (int) iteration number for the current set of metrics
         """
@@ -145,7 +145,7 @@ def log_model(self, model_path, model_name, epoch=0):
         """
         Log model weights to ClearML.
 
-        arguments:
+        Arguments:
         model_path (PosixPath or str) Path to the model weights
         model_name (str) Name of the model visible in ClearML
         epoch (int) Iteration / epoch of the model weights
@@ -158,7 +158,7 @@ def log_summary(self, metrics):
         """
         Log final metrics to a summary table.
 
-        arguments:
+        Arguments:
         metrics (dict) Metrics in dict format: {"metrics/mAP": 0.8, ...}
         """
         for k, v in metrics.items():
@@ -168,7 +168,7 @@ def log_plot(self, title, plot_path):
         """
         Log image as plot in the plot section of ClearML.
 
-        arguments:
+        Arguments:
         title (str) Title of the plot
         plot_path (PosixPath or str) Path to the saved image file
         """
@@ -183,7 +183,7 @@ def log_debug_samples(self, files, title="Debug Samples"):
         """
         Log files (images) as debug samples in the ClearML task.
 
-        arguments:
+        Arguments:
         files (List(PosixPath)) a list of file paths in PosixPath format
         title (str) A title that groups together images with the same values
         """
@@ -199,7 +199,7 @@ def log_image_with_boxes(self, image_path, boxes, class_names, image, conf_thres
         """
         Draw the bounding boxes on a single image and report the result as a ClearML debug sample.
 
-        arguments:
+        Arguments:
         image_path (PosixPath) the path the original image file
         boxes (list): list of scaled predictions in the format - [xmin, ymin, xmax, ymax, confidence, class]
         class_names (dict): dict containing mapping of class int to class name
diff --git a/utils/loggers/wandb/wandb_utils.py b/utils/loggers/wandb/wandb_utils.py
index 930f2c7543af..6a32c8cc7b03 100644
--- a/utils/loggers/wandb/wandb_utils.py
+++ b/utils/loggers/wandb/wandb_utils.py
@@ -49,7 +49,7 @@ def __init__(self, opt, run_id=None, job_type="Training"):
         - Upload dataset if opt.upload_dataset is True
         - Setup training processes if job_type is 'Training'
 
-        arguments:
+        Arguments:
         opt (namespace) -- Commandline arguments for this run
         run_id (str) -- Run ID of W&B run to be resumed
         job_type (str) -- To set the job_type for this run
@@ -90,7 +90,7 @@ def setup_training(self, opt):
           - Update data_dict, to contain info of previous run if resumed and the paths of dataset artifact if downloaded
           - Setup log_dict, initialize bbox_interval
 
-        arguments:
+        Arguments:
         opt (namespace) -- commandline arguments for this run
 
         """
@@ -120,7 +120,7 @@ def log_model(self, path, opt, epoch, fitness_score, best_model=False):
         """
         Log the model checkpoint as W&B artifact.
 
-        arguments:
+        Arguments:
         path (Path)   -- Path of directory containing the checkpoints
         opt (namespace) -- Command line arguments for this run
         epoch (int)  -- Current epoch number
@@ -159,7 +159,7 @@ def log(self, log_dict):
         """
         Save the metrics to the logging dictionary.
 
-        arguments:
+        Arguments:
         log_dict (Dict) -- metrics/media to be logged in current step
         """
         if self.wandb_run:
@@ -170,7 +170,7 @@ def end_epoch(self):
         """
         Commit the log_dict, model artifacts and Tables to W&B and flush the log_dict.
 
-        arguments:
+        Arguments:
         best_result (boolean): Boolean representing if the result of this evaluation is best or not
         """
         if self.wandb_run:
@@ -197,7 +197,7 @@ def finish_run(self):
 
 @contextmanager
 def all_logging_disabled(highest_level=logging.CRITICAL):
-    """source - https://gist.github.com/simon-weber/7853144
+    """Source - https://gist.github.com/simon-weber/7853144
     A context manager that will prevent any logging messages triggered during the body from being processed.
     :param highest_level: the maximum logging level in use.
       This would only need to be changed if a custom level greater than CRITICAL is defined.
diff --git a/utils/metrics.py b/utils/metrics.py
index 385fdc471748..9acc38591f96 100644
--- a/utils/metrics.py
+++ b/utils/metrics.py
@@ -41,7 +41,6 @@ def ap_per_class(tp, conf, pred_cls, target_cls, plot=False, save_dir=".", names
     # Returns
         The average precision as computed in py-faster-rcnn.
     """
-
     # Sort by objectness
     i = np.argsort(-conf)
     tp, conf, pred_cls = tp[i], conf[i], pred_cls[i]
@@ -103,7 +102,6 @@ def compute_ap(recall, precision):
     # Returns
         Average precision, precision curve, recall curve
     """
-
     # Append sentinel values to beginning and end
     mrec = np.concatenate(([0.0], recall, [1.0]))
     mpre = np.concatenate(([1.0], precision, [0.0]))
@@ -137,6 +135,7 @@ def process_batch(self, detections, labels):
         Return intersection-over-union (Jaccard index) of boxes.
 
         Both sets of boxes are expected to be in (x1, y1, x2, y2) format.
+
         Arguments:
             detections (Array[N, 6]), x1, y1, x2, y2, conf, class
             labels (Array[M, 5]), class, x1, y1, x2, y2
@@ -233,7 +232,6 @@ def bbox_iou(box1, box2, xywh=True, GIoU=False, DIoU=False, CIoU=False, eps=1e-7
 
     Input shapes are box1(1,4) to box2(n,4).
     """
-
     # Get the coordinates of bounding boxes
     if xywh:  # transform from xywh to xyxy
         (x1, y1, w1, h1), (x2, y2, w2, h2) = box1.chunk(4, -1), box2.chunk(4, -1)
@@ -279,14 +277,15 @@ def box_iou(box1, box2, eps=1e-7):
     Return intersection-over-union (Jaccard index) of boxes.
 
     Both sets of boxes are expected to be in (x1, y1, x2, y2) format.
+
     Arguments:
         box1 (Tensor[N, 4])
         box2 (Tensor[M, 4])
+
     Returns:
         iou (Tensor[N, M]): the NxM matrix containing the pairwise
             IoU values for every element in boxes1 and boxes2
     """
-
     # inter(N,M) = (rb(N,M,2) - lt(N,M,2)).clamp(0).prod(2)
     (a1, a2), (b1, b2) = box1.unsqueeze(1).chunk(2, 2), box2.unsqueeze(0).chunk(2, 2)
     inter = (torch.min(a2, b2) - torch.max(a1, b1)).clamp(0).prod(2)
@@ -304,7 +303,6 @@ def bbox_ioa(box1, box2, eps=1e-7):
     box2:       np.array of shape(nx4)
     returns:    np.array of shape(n)
     """
-
     # Get the coordinates of bounding boxes
     b1_x1, b1_y1, b1_x2, b1_y2 = box1
     b2_x1, b2_y1, b2_x2, b2_y2 = box2.T
diff --git a/utils/segment/augmentations.py b/utils/segment/augmentations.py
index d7dd8aec6691..2e1dca1198b0 100644
--- a/utils/segment/augmentations.py
+++ b/utils/segment/augmentations.py
@@ -29,7 +29,6 @@ def random_perspective(
 ):
     # torchvision.transforms.RandomAffine(degrees=(-10, 10), translate=(.1, .1), scale=(.9, 1.1), shear=(-10, 10))
     # targets = [cls, xyxy]
-
     """Applies random perspective, rotation, scale, shear, and translation augmentations to an image and targets."""
     height = im.shape[0] + border[0] * 2  # shape(h,w,c)
     width = im.shape[1] + border[1] * 2
diff --git a/utils/segment/general.py b/utils/segment/general.py
index 2f65d60238dd..0793470a95e4 100644
--- a/utils/segment/general.py
+++ b/utils/segment/general.py
@@ -14,7 +14,6 @@ def crop_mask(masks, boxes):
         - masks should be a size [n, h, w] tensor of masks
         - boxes should be a size [n, 4] tensor of bbox coords in relative point form
     """
-
     n, h, w = masks.shape
     x1, y1, x2, y2 = torch.chunk(boxes[:, :, None], 4, 1)  # x1 shape(1,1,n)
     r = torch.arange(w, device=masks.device, dtype=x1.dtype)[None, None, :]  # rows shape(1,w,1)
@@ -33,7 +32,6 @@ def process_mask_upsample(protos, masks_in, bboxes, shape):
 
     return: h, w, n
     """
-
     c, mh, mw = protos.shape  # CHW
     masks = (masks_in @ protos.float().view(c, -1)).sigmoid().view(-1, mh, mw)
     masks = F.interpolate(masks[None], shape, mode="bilinear", align_corners=False)[0]  # CHW
@@ -51,7 +49,6 @@ def process_mask(protos, masks_in, bboxes, shape, upsample=False):
 
     return: h, w, n
     """
-
     c, mh, mw = protos.shape  # CHW
     ih, iw = shape
     masks = (masks_in @ protos.float().view(c, -1)).sigmoid().view(-1, mh, mw)  # CHW
diff --git a/utils/triton.py b/utils/triton.py
index 3d529ec88a07..2fee42815517 100644
--- a/utils/triton.py
+++ b/utils/triton.py
@@ -17,10 +17,9 @@ class TritonRemoteModel:
 
     def __init__(self, url: str):
         """
-        Keyword arguments:
+        Keyword Arguments:
         url: Fully qualified address of the Triton server - for e.g. grpc://localhost:8000
         """
-
         parsed_url = urlparse(url)
         if parsed_url.scheme == "grpc":
             from tritonclient.grpc import InferenceServerClient, InferInput