yolov8的predict使用方法，更改predict.py的输出结果，输出label的真实坐标，保存图片和txt文档，图片中没有异物生成空的txt文档 |
您所在的位置：网站首页 › 标签生成图像的方法是什么 › yolov8的predict使用方法，更改predict.py的输出结果，输出label的真实坐标，保存图片和txt文档，图片中没有异物生成空的txt文档 |
|
Yolov8的predict的使用方法： 新建predict.py如下： from ultralytics import YOLO model = YOLO("你训练好的模型.pt") model.predict(source="datasets/images/val",save=True,save_conf=True,save_txt=True,name='output') #source后为要预测的图片数据集的的路径 #save=True为保存预测结果 #save_conf=True为保存坐标信息 #save_txt=True为保存txt结果，但是yolov8本身当图片中预测不到异物时，不产生txt文件默认predict的输出坐标为xywh格式，即中心点坐标和预测的框的宽高，将其改为真实坐标方法如下：在ultralytics\engine\results.py中，将def save_txt()置换为如下代码： def save_txt(self, txt_file, save_conf=False): """ Save predictions into txt file. Args: txt_file (str): txt file path. save_conf (bool): save confidence score or not. """ boxes = self.boxes masks = self.masks probs = self.probs kpts = self.keypoints texts = [] if probs is not None: # Classify [texts.append(f'{probs.data[j]:.2f} {self.names[j]}') for j in probs.top5] elif boxes: # Detect/segment/pose for j, d in enumerate(boxes): c, conf, id = int(d.cls), float(d.conf), None if d.id is None else int(d.id.item()) #line = (c, *d.xywhn.view(-1)) line = ( c,conf, *d.xyxy.view(-1)) #重点在这里，还可以通过这里改变txt中信息#的顺序 if masks: seg = masks[j].xyn[0].copy().reshape(-1) # reversed mask.xyn, (n,2) to (n*2) line = (c, *seg) if kpts is not None: kpt = torch.cat((kpts[j].xyn, kpts[j].conf[..., None]), 2) if kpts[j].has_visible else kpts[j].xyn line += (*kpt.reshape(-1).tolist(), ) line += (conf, ) * save_conf + (() if id is None else (id, )) line = line[:-1] texts.append('%s %.6f %d %d %d %d' % (line[0], float(line[1]), int(line[2]), int(line[3]), int(line[4]), int(line[5]))) if texts: Path(txt_file).parent.mkdir(parents=True, exist_ok=True) # make directory with open(txt_file, 'a') as f: f.writelines(text + '\n' for text in texts)要实现图片中没有异物生成空的txt文档，采用如下方法： 在ultralytics\engine\predictor.py中，找到def stream_inference()，将其置换为如下代码： def stream_inference(self, source=None, model=None, *args, **kwargs): """Streams real-time inference on camera feed and saves results to file.""" if self.args.verbose: LOGGER.info('') # Setup model if not self.model: self.setup_model(model) # Setup source every time predict is called self.setup_source(source if source is not None else self.args.source) # Check if save_dir/ label file exists if self.args.save or self.args.save_txt: (self.save_dir / 'labels' if self.args.save_txt else self.save_dir).mkdir(parents=True, exist_ok=True) # Warmup model if not self.done_warmup: self.model.warmup(imgsz=(1 if self.model.pt or self.model.triton else self.dataset.bs, 3, *self.imgsz)) self.done_warmup = True self.seen, self.windows, self.batch, profilers = 0, [], None, (ops.Profile(), ops.Profile(), ops.Profile()) self.run_callbacks('on_predict_start') for batch in self.dataset: self.run_callbacks('on_predict_batch_start') self.batch = batch path, im0s, vid_cap, s = batch # Preprocess with profilers[0]: im = self.preprocess(im0s) # Inference with profilers[1]: preds = self.inference(im, *args, **kwargs) # Postprocess with profilers[2]: self.results = self.postprocess(preds, im, im0s) self.run_callbacks('on_predict_postprocess_end') # Visualize, save, write results n = len(im0s) for i in range(n): self.seen += 1 self.results[i].speed = { 'preprocess': profilers[0].dt * 1E3 / n, 'inference': profilers[1].dt * 1E3 / n, 'postprocess': profilers[2].dt * 1E3 / n} p, im0 = path[i], None if self.source_type.tensor else im0s[i].copy() p = Path(p) if self.args.verbose or self.args.save or self.args.save_txt or self.args.show: s += self.write_results(i, self.results, (p, im, im0)) if self.args.save or self.args.save_txt: self.results[i].save_dir = self.save_dir.__str__() if self.args.show and self.plotted_img is not None: self.show(p) if self.args.save and self.plotted_img is not None: self.save_preds(vid_cap, i, str(self.save_dir / p.name)) self.run_callbacks('on_predict_batch_end') yield from self.results # Print time (inference-only) if self.args.verbose: LOGGER.info(f'{s}{profilers[1].dt * 1E3:.1f}ms') # Release assets if isinstance(self.vid_writer[-1], cv2.VideoWriter): self.vid_writer[-1].release() # release final video writer # Print results if self.args.verbose and self.seen: t = tuple(x.t / self.seen * 1E3 for x in profilers) # speeds per image LOGGER.info(f'Speed: %.1fms preprocess, %.1fms inference, %.1fms postprocess per image at shape ' f'{(1, 3, *im.shape[2:])}' % t) if self.args.save or self.args.save_txt or self.args.save_crop: nl = len(list(self.save_dir.glob('labels/*.txt'))) # number of labels s = f"\n{nl} label{'s' * (nl > 1)} saved to {self.save_dir / 'labels'}" if self.args.save_txt else '' m = f"\n{nl} image{'s' * (nl > 1)} saved to {self.save_dir / 'images'}" if self.args.save_txt else '' LOGGER.info(f"Results saved to {colorstr('bold', self.save_dir)}") # 原始文件夹路径和目标文件夹路径 source_folder = self.save_dir target_folder = os.path.join(source_folder, 'images') target_label_folder = os.path.join(source_folder, 'labels') # 创建目标文件夹 os.makedirs(target_folder, exist_ok=True) # 获取原始文件夹中的所有文件 files = os.listdir(source_folder) # 遍历所有文件 for file in files: # 构建文件的绝对路径 file_path = os.path.join(source_folder, file) # 检查文件是否是图片文件 if os.path.isfile(file_path) and file.lower().endswith(('.jpg', '.jpeg', '.png')): # 构建目标文件的路径 target_file_path = os.path.join(target_folder, file) # 将图片文件复制到目标文件夹 shutil.copy(file_path, target_file_path) # 删除原始文件夹中的图片文件 os.remove(file_path) image_folder = target_folder txt_folder = target_label_folder image_files = [file for file in os.listdir(image_folder) if file.lower().endswith(('.jpg', '.jpeg', '.png'))] # 遍历图片文件夹中的图片文件 for image_file in image_files: # 构建图片和txt文件的路径 image_file_path = os.path.join(image_folder, image_file) txt_file_path = os.path.join(txt_folder, os.path.splitext(image_file)[0] + '.txt') # 检查txt文件是否已存在 if os.path.isfile(txt_file_path): #print(f"txt文件'{txt_file_path}'已存在，不执行操作。") pass else: # 创建空白的txt文件 with open(txt_file_path, 'w') as txt_file: pass self.run_callbacks('on_predict_end') |
今日新闻 |
推荐新闻 |
| CopyRight 2018-2019 办公设备维修网 版权所有 豫ICP备15022753号-3 |