Selected Program Examples

Python+Yolov8 gesture feature recognition and detection

If you need to install the operating environment or remote debugging, please see your personal QQ business card at the bottom of the article for remote assistance from professional technicians!

Preface

This blog writes code for <<Python+Yolov8 gesture feature recognition and detection>>. The code is clean, regular and easy to read. Recommended for learning and application.

Article directory

1. Required tools and software

2. Usage steps

1. Import the library

2. Identify image features

3. Parameter settings

4. Running results

3. Online assistance

1. Required tools and software

1. Pycharm, Python

2. Yolov8, OpenCV

2. Usage steps

1. Import the library

The code is as follows (example):


import torch

from ultralytics.yolo.engine.predictor import BasePredictor
from ultralytics.yolo.engine.results import Results
from ultralytics.yolo.utils import DEFAULT_CFG, ROOT, ops
from ultralytics.yolo.utils.plotting import Annotator, colors, save_one_box

2. Identify image features

The code is as follows (example):


class DetectionPredictor(BasePredictor):

    def get_annotator(self, img):
        return Annotator(img, line_width=self.args.line_thickness, example=str(self.model.names))

    def preprocess(self, img):
        img = torch.from_numpy(img).to(self.model.device)
        img = img.half() if self.model.fp16 else img.float()  # uint8 to fp16/32
        img /= 255  # 0 - 255 to 0.0 - 1.0
        return img

    def postprocess(self, preds, img, orig_img):
        preds = ops.non_max_suppression(preds,
                                        self.args.conf,
                                        self.args.iou,
                                        agnostic=self.args.agnostic_nms,
                                        max_det=self.args.max_det,
                                        classes=self.args.classes)

        results = []
        for i, pred in enumerate(preds):
            orig_img = orig_img[i] if isinstance(orig_img, list) else orig_img
            shape = orig_img.shape
            pred[:, :4] = ops.scale_boxes(img.shape[2:], pred[:, :4], shape).round()
            results.append(Results(boxes=pred, orig_img=orig_img, names=self.model.names))
        return results

    def write_results(self, idx, results, batch):
        p, im, im0 = batch
        log_string = ''
        if len(im.shape) == 3:
            im = im[None]  # expand for batch dim
        self.seen += 1
        imc = im0.copy() if self.args.save_crop else im0
        if self.source_type.webcam or self.source_type.from_img:  # batch_size >= 1
            log_string += f'{idx}: '
            frame = self.dataset.count
        else:
            frame = getattr(self.dataset, 'frame', 0)
        self.data_path = p
        self.txt_path = str(self.save_dir / 'labels' / p.stem) + ('' if self.dataset.mode == 'image' else f'_{frame}')
        log_string += '%gx%g ' % im.shape[2:]  # print string
        self.annotator = self.get_annotator(im0)

        det = results[idx].boxes  # TODO: make boxes inherit from tensors
        if len(det) == 0:
            return log_string
        for c in det.cls.unique():
            n = (det.cls == c).sum()  # detections per class
            log_string += f"{n} {self.model.names[int(c)]}{'s' * (n > 1)}, "

        # write
        for d in reversed(det):
            cls, conf = d.cls.squeeze(), d.conf.squeeze()
            if self.args.save_txt:  # Write to file
                line = (cls, *(d.xywhn.view(-1).tolist()), conf) \
                    if self.args.save_conf else (cls, *(d.xywhn.view(-1).tolist()))  # label format
                with open(f'{self.txt_path}.txt', 'a') as f:
                    f.write(('%g ' * len(line)).rstrip() % line + '\n')
            if self.args.save or self.args.save_crop or self.args.show:  # Add bbox to image
                c = int(cls)  # integer class
                name = f'id:{int(d.id.item())} {self.model.names[c]}' if d.id is not None else self.model.names[c]
                label = None if self.args.hide_labels else (name if self.args.hide_conf else f'{name} {conf:.2f}')
                self.annotator.box_label(d.xyxy.squeeze(), label, color=colors(c, True))
            if self.args.save_crop:
                save_one_box(d.xyxy,
                             imc,
                             file=self.save_dir / 'crops' / self.model.model.names[c] / f'{self.data_path.stem}.jpg',
                             BGR=True)

        return log_string

3. Parameter definition

The code is as follows (example):


if __name__ == '__main__':
    parser = argparse.ArgumentParser()
    parser.add_argument('--weights', nargs='+', type=str, default='yolov5_best_road_crack_recog.pt', help='model.pt path(s)')
    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('--view-img', action='store_true', help='display results')
    parser.add_argument('--save-txt', action='store_true', help='save results to *.txt')
    parser.add_argument('--classes', nargs='+', type=int, default='0', 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')
    opt = parser.parse_args()

4. The running results are as follows

3. Online assistance:

If you need to install the operating environment or remote debugging, please see your personal QQ business card at the bottom of the article for remote assistance from professional technicians!
1) Remote installation and running environment, code debugging
2) Qt, C++, Python entry guide
3) Interface beautification
4) Software production