????????YOLOv5官方開源代碼給出了完成的推理實現，但過于封裝，只能通過修改配置參數對指定文件夾下圖像和視頻進行推理，而且三百多行的推理代碼也顯得過于冗長。如果想要在項目上進行部署應用，顯然需要更高的靈活性。

????????這里就用單張圖像目標檢測來重構YOLOv5的推理代碼。

??????依賴項：OpenCV、numpy、pytorch、models文件夾下experimental.py、utils文件夾下general.py、訓練結果yolov5s.pt文件。

???????? 對于圖像目標檢測來說，首先需要讀取圖像，然后轉換為tensor，接著送入模型進行推理，最后獲取推理結果。對推理結果進行解析，就可以拿到檢測框坐標，分類結果和置信度。

官方推理代碼：

# YOLOv5 🚀 by Ultralytics, GPL-3.0 license """ Run inference on images, videos, directories, streams, etc.Usage:$ python path/to/detect.py --source path/to/img.jpg --weights yolov5s.pt --img 640 """import argparse import os import platform import sys from pathlib import Pathimport cv2 import numpy as np import torch import torch.backends.cudnn as cudnnFILE = 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())) # relativefrom models.experimental import attempt_load from utils.datasets import LoadImages, LoadStreams from utils.general import (LOGGER, apply_classifier, check_img_size, check_imshow, check_requirements, check_suffix,colorstr, increment_path, non_max_suppression, print_args, save_one_box, scale_coords,strip_optimizer, xyxy2xywh) from utils.plots import Annotator, colors from utils.torch_utils import load_classifier, select_device, time_sync@torch.no_grad() def run(weights=ROOT / 'yolov5s.pt', # model.pt path(s)source=ROOT / 'data/images', # file/dir/URL/glob, 0 for webcamimgsz=640, # inference size (pixels)conf_thres=0.25, # confidence thresholdiou_thres=0.45, # NMS IOU thresholdmax_det=1000, # maximum detections per imagedevice='', # cuda device, i.e. 0 or 0,1,2,3 or cpuview_img=False, # show resultssave_txt=False, # save results to *.txtsave_conf=False, # save confidences in --save-txt labelssave_crop=False, # save cropped prediction boxesnosave=False, # do not save images/videosclasses=None, # filter by class: --class 0, or --class 0 2 3agnostic_nms=False, # class-agnostic NMSaugment=False, # augmented inferencevisualize=False, # visualize featuresupdate=False, # update all modelsproject=ROOT / 'runs/detect', # save results to project/namename='exp', # save results to project/nameexist_ok=False, # existing project/name ok, do not incrementline_thickness=3, # bounding box thickness (pixels)hide_labels=False, # hide labelshide_conf=False, # hide confidenceshalf=False, # use FP16 half-precision inferencednn=False, # use OpenCV DNN for ONNX inference):source = str(source)save_img = not nosave and not source.endswith('.txt') # save inference imageswebcam = source.isnumeric() or source.endswith('.txt') or source.lower().startswith(('rtsp://', 'rtmp://', 'http://', 'https://'))# Directoriessave_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# Initializedevice = select_device(device)half &= device.type != 'cpu' # half precision only supported on CUDA# Load modelw = str(weights[0] if isinstance(weights, list) else weights)classify, suffix, suffixes = False, Path(w).suffix.lower(), ['.pt', '.onnx', '.tflite', '.pb', '']check_suffix(w, suffixes) # check weights have acceptable suffixpt, onnx, tflite, pb, saved_model = (suffix == x for x in suffixes) # backend booleansstride, names = 64, [f'class{i}' for i in range(1000)] # assign defaultsif pt:model = torch.jit.load(w) if 'torchscript' in w else attempt_load(weights, map_location=device)stride = int(model.stride.max()) # model stridenames = model.module.names if hasattr(model, 'module') else model.names # get class namesif half:model.half() # to FP16if classify: # second-stage classifiermodelc = load_classifier(name='resnet50', n=2) # initializemodelc.load_state_dict(torch.load('resnet50.pt', map_location=device)['model']).to(device).eval()elif onnx:if dnn:check_requirements(('opencv-python>=4.5.4',))net = cv2.dnn.readNetFromONNX(w)else:check_requirements(('onnx', 'onnxruntime-gpu' if torch.has_cuda else 'onnxruntime'))import onnxruntimesession = onnxruntime.InferenceSession(w, None)else: # TensorFlow modelsimport tensorflow as tfif pb: # https://www.tensorflow.org/guide/migrate#a_graphpb_or_graphpbtxtdef wrap_frozen_graph(gd, inputs, outputs):x = tf.compat.v1.wrap_function(lambda: tf.compat.v1.import_graph_def(gd, name=""), []) # wrapped importreturn x.prune(tf.nest.map_structure(x.graph.as_graph_element, inputs),tf.nest.map_structure(x.graph.as_graph_element, outputs))graph_def = tf.Graph().as_graph_def()graph_def.ParseFromString(open(w, 'rb').read())frozen_func = wrap_frozen_graph(gd=graph_def, inputs="x:0", outputs="Identity:0")elif saved_model:model = tf.keras.models.load_model(w)elif tflite:if "edgetpu" in w: # https://www.tensorflow.org/lite/guide/python#install_tensorflow_lite_for_pythonimport tflite_runtime.interpreter as tflridelegate = {'Linux': 'libedgetpu.so.1', # install libedgetpu https://coral.ai/software/#edgetpu-runtime'Darwin': 'libedgetpu.1.dylib','Windows': 'edgetpu.dll'}[platform.system()]interpreter = tflri.Interpreter(model_path=w, experimental_delegates=[tflri.load_delegate(delegate)])else:interpreter = tf.lite.Interpreter(model_path=w) # load TFLite modelinterpreter.allocate_tensors() # allocateinput_details = interpreter.get_input_details() # inputsoutput_details = interpreter.get_output_details() # outputsint8 = input_details[0]['dtype'] == np.uint8 # is TFLite quantized uint8 modelimgsz = check_img_size(imgsz, s=stride) # check image size# Dataloaderif webcam:view_img = check_imshow()cudnn.benchmark = True # set True to speed up constant image size inferencedataset = LoadStreams(source, img_size=imgsz, stride=stride, auto=pt)bs = len(dataset) # batch_sizeelse:dataset = LoadImages(source, img_size=imgsz, stride=stride, auto=pt)bs = 1 # batch_sizevid_path, vid_writer = [None] * bs, [None] * bs# Run inferenceif pt and device.type != 'cpu':model(torch.zeros(1, 3, *imgsz).to(device).type_as(next(model.parameters()))) # run oncedt, seen = [0.0, 0.0, 0.0], 0for path, img, im0s, vid_cap, s in dataset:t1 = time_sync()if onnx:img = img.astype('float32')else:img = torch.from_numpy(img).to(device)img = img.half() if half else img.float() # uint8 to fp16/32img /= 255 # 0 - 255 to 0.0 - 1.0if len(img.shape) == 3:img = img[None] # expand for batch dimt2 = time_sync()dt[0] += t2 - t1# Inferenceif pt:visualize = increment_path(save_dir / Path(path).stem, mkdir=True) if visualize else Falsepred = model(img, augment=augment, visualize=visualize)[0]elif onnx:if dnn:net.setInput(img)pred = torch.tensor(net.forward())else:pred = torch.tensor(session.run([session.get_outputs()[0].name], {session.get_inputs()[0].name: img}))else: # tensorflow model (tflite, pb, saved_model)imn = img.permute(0, 2, 3, 1).cpu().numpy() # image in numpyif pb:pred = frozen_func(x=tf.constant(imn)).numpy()elif saved_model:pred = model(imn, training=False).numpy()elif tflite:if int8:scale, zero_point = input_details[0]['quantization']imn = (imn / scale + zero_point).astype(np.uint8) # de-scaleinterpreter.set_tensor(input_details[0]['index'], imn)interpreter.invoke()pred = interpreter.get_tensor(output_details[0]['index'])if int8:scale, zero_point = output_details[0]['quantization']pred = (pred.astype(np.float32) - zero_point) * scale # re-scalepred[..., 0] *= imgsz[1] # xpred[..., 1] *= imgsz[0] # ypred[..., 2] *= imgsz[1] # wpred[..., 3] *= imgsz[0] # hpred = torch.tensor(pred)t3 = time_sync()dt[1] += t3 - t2# NMSpred = non_max_suppression(pred, conf_thres, iou_thres, classes, agnostic_nms, max_det=max_det)dt[2] += time_sync() - t3# Second-stage classifier (optional)if classify:pred = apply_classifier(pred, modelc, img, im0s)# Process predictionsfor i, det in enumerate(pred): # per imageseen += 1if webcam: # batch_size >= 1p, im0, frame = path[i], im0s[i].copy(), dataset.counts += f'{i}: 'else:p, im0, frame = path, im0s.copy(), getattr(dataset, 'frame', 0)p = Path(p) # to Pathsave_path = str(save_dir / p.name) # img.jpgtxt_path = str(save_dir / 'labels' / p.stem) + ('' if dataset.mode == 'image' else f'_{frame}') # img.txts += '%gx%g ' % img.shape[2:] # print stringgn = torch.tensor(im0.shape)[[1, 0, 1, 0]] # normalization gain whwhimc = im0.copy() if save_crop else im0 # for save_cropannotator = Annotator(im0, line_width=line_thickness, example=str(names))if len(det):# Rescale boxes from img_size to im0 sizedet[:, :4] = scale_coords(img.shape[2:], det[:, :4], im0.shape).round()# Print resultsfor c in det[:, -1].unique():n = (det[:, -1] == c).sum() # detections per classs += f"{n} {names[int(c)]}{'s' * (n > 1)}, " # add to string# Write resultsfor *xyxy, conf, cls in reversed(det):print(xyxy)print(conf)print(cls)if save_txt: # Write to filexywh = (xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist() # normalized xywhline = (cls, *xywh, conf) if save_conf else (cls, *xywh) # label formatwith open(txt_path + '.txt', 'a') as f:f.write(('%g ' * len(line)).rstrip() % line + '\n')if save_img or save_crop or view_img: # Add bbox to imageprint(xyxy)c = int(cls) # integer classlabel = 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)# Print time (inference-only)LOGGER.info(f'{s}Done. ({t3 - t2:.3f}s)')# Stream resultsim0 = annotator.result()if view_img: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 videovid_path[i] = save_pathif isinstance(vid_writer[i], cv2.VideoWriter):vid_writer[i].release() # release previous video writerif vid_cap: # videofps = 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: # streamfps, w, h = 30, im0.shape[1], im0.shape[0]save_path += '.mp4'vid_writer[i] = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*'mp4v'), fps, (w, h))vid_writer[i].write(im0)# Print resultst = tuple(x / seen * 1E3 for x in dt) # speeds per imageLOGGER.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) # update model (to fix SourceChangeWarning)def parse_opt():parser = argparse.ArgumentParser()parser.add_argument('--weights', nargs='+', type=str, default='yolov5s.pt', help='model path(s)')parser.add_argument('--source', type=str, default='data/', help='file/dir/URL/glob, 0 for webcam')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='D:/Sources/Python/pytorch/OpenCV_pytorch/cam_detect/out', 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')opt = parser.parse_args()opt.imgsz *= 2 if len(opt.imgsz) == 1 else 1 # expandprint_args(FILE.stem, opt)return optdef main(opt):check_requirements(exclude=('tensorboard', 'thop'))run(**vars(opt))if __name__ == "__main__":opt = parse_opt()main(opt)

簡化后的代碼：

import cv2 import numpy as np import torch from models.experimental import attempt_load from utils.general import non_max_suppression, scale_coords if __name__ == "__main__":weights = 'yolov5s.pt'w = str(weights[0] if isinstance(weights, list) else weights)model = torch.jit.load(w) if 'torchscript' in w else attempt_load(weights, map_location='cpu') #加載模型height, width = 640, 640img0 = cv2.imread('data/img.jpg')img = cv2.resize(img0, (height, width)) #尺寸變換img = img / 255.img = img[:, :, ::-1].transpose((2, 0, 1)) #HWC轉CHWimg = np.expand_dims(img, axis=0) #擴展維度至[1,3,640,640]img = torch.from_numpy(img.copy()) #numpy轉tensorimg = img.to(torch.float32) #float64轉換float32pred = model(img, augment='store_true', visualize='store_true')[0]pred.clone().detach()pred = non_max_suppression(pred, 0.25, 0.45, None, False, max_det=1000) #非極大值抑制for i, det in enumerate(pred):if len(det):det[:, :4] = scale_coords(img.shape[2:], det[:, :4], img0.shape).round()for *xyxy, conf, cls in reversed(det):print('{},{},{}'.format(xyxy, conf.numpy(), cls.numpy())) #輸出結果：xyxy檢測框左上角和右下角坐標，conf置信度，cls分類結果img0 = cv2.rectangle(img0, (int(xyxy[0].numpy()), int(xyxy[1].numpy())), (int(xyxy[2].numpy()), int(xyxy[3].numpy())), (0, 255, 0), 2)cv2.imwrite('out.jpg', img0) #簡單畫個框

運行結果：

[tensor(226.), tensor(46.), tensor(344.), tensor(376.)],0.8777655363082886,0.0
[tensor(54.), tensor(94.), tensor(557.), tensor(538.)],0.8839194178581238,17.0

測試圖像：

結果：

? ? ? ? ?簡化后，可以通過插入圖像或視頻處理代碼實現更多功能擴展，也可封裝為獨立函數，將圖像或視頻預處理為tensor以后再輸入，然后返回檢測框、分類、置信度結果。

總結

以上是生活随笔為你收集整理的砍掉九成代码，重构并简化YOLOv5图像目标检测推理实现的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。