外贸网站空间,中国建设银行员工培训网站,网易考拉的网站建设,做国外网站的公证要多少钱提示#xff1a;文章写完后#xff0c;目录可以自动生成#xff0c;如何生成可参考右边的帮助文档 文章目录 前言一、误报二、漏报三、源码总结 前言
本文主要用于记录数据标注和模型预测之间的漏报和误报思想及其源码 提示#xff1a;以下是本篇文章正文内容#xff0c;… 提示文章写完后目录可以自动生成如何生成可参考右边的帮助文档 文章目录 前言一、误报二、漏报三、源码总结 前言
本文主要用于记录数据标注和模型预测之间的漏报和误报思想及其源码 提示以下是本篇文章正文内容下面案例可供参考
一、误报
我自己定义的误报是模型的预测结果框比人为标注的目标框多也就是当标注人员标注图片的时候标注不仔细未能标注全的情况逻辑是将在原始标注的xml文件当中添加误报-类别名称的框。
二、漏报
我自己定义的漏报是人为标注的框模型没有全部预测出来也就是当标注人员标注图片的时候标注错误或者标注的框质量不合格的情况跟模型性能也有关系逻辑是将在原始标注的xml文件当中添加漏报-类别名称的框。
三、源码
import argparse
import os
import time
import shutil
import cv2
import numpy as np
import torch
from pathlib import Path
from pascal_voc_writer import Writer
import torchvision
from xml.etree import ElementTree
from xml.etree.ElementTree import Elementimport warnings
warnings.simplefilter(actionignore, categoryFutureWarning)FILE Path(__file__).resolve()
ROOT FILE.parents[0]def xywh2xyxy(x):# Convert nx4 boxes from [x, y, w, h] to [x1, y1, x2, y2] where xy1top-left, xy2bottom-righty x.clone() if isinstance(x, torch.Tensor) else np.copy(x)y[:, 0] x[:, 0] - x[:, 2] / 2 # top left xy[:, 1] x[:, 1] - x[:, 3] / 2 # top left yy[:, 2] x[:, 0] x[:, 2] / 2 # bottom right xy[:, 3] x[:, 1] x[:, 3] / 2 # bottom right yreturn ydef box_iou(box1, box2):def box_area(box):# box 4xnreturn (box[2] - box[0]) * (box[3] - box[1])area1 box_area(box1.T)area2 box_area(box2.T)# inter(N,M) (rb(N,M,2) - lt(N,M,2)).clamp(0).prod(2)inter (torch.min(box1[:, None, 2:], box2[:, 2:]) - torch.max(box1[:, None, :2], box2[:, :2])).clamp(0).prod(2)return inter / (area1[:, None] area2 - inter) # iou inter / (area1 area2 - inter)def cv_imread(file_path):cv_img cv2.imdecode(np.fromfile(file_path, dtypenp.uint8), cv2.IMREAD_UNCHANGED) #读取的为bgr图像return cv2.cvtColor(cv_img, cv2.COLOR_BGR2RGB)def letterbox(im, new_shape(640, 640), color(114, 114, 114), autoTrue, scaleFillFalse, scaleupTrue, stride32):# Resize and pad image while meeting stride-multiple constraintsshape im.shape[:2] # current shape [height, width]if isinstance(new_shape, int):new_shape (new_shape, new_shape)# Scale ratio (new / old)r min(new_shape[0] / shape[0], new_shape[1] / shape[1])if not scaleup: # only scale down, do not scale up (for better val mAP)r min(r, 1.0)# Compute paddingratio r, r # width, height ratiosnew_unpad int(round(shape[1] * r)), int(round(shape[0] * r))dw, dh new_shape[1] - new_unpad[0], new_shape[0] - new_unpad[1] # wh paddingif auto: # minimum rectangledw, dh np.mod(dw, stride), np.mod(dh, stride) # wh paddingelif scaleFill: # stretchdw, dh 0.0, 0.0new_unpad (new_shape[1], new_shape[0])ratio new_shape[1] / shape[1], new_shape[0] / shape[0] # width, height ratiosdw / 2 # divide padding into 2 sidesdh / 2if shape[::-1] ! new_unpad: # resizeim cv2.resize(im, new_unpad, interpolationcv2.INTER_LINEAR)top, bottom int(round(dh - 0.1)), int(round(dh 0.1))left, right int(round(dw - 0.1)), int(round(dw 0.1))im cv2.copyMakeBorder(im, top, bottom, left, right, cv2.BORDER_CONSTANT, valuecolor) # add borderreturn im, ratio, (dw, dh)def preprocess_file(path, img_size, stride, auto):img_rgb_ cv_imread(path) # RGBassert img_rgb_ is not None, fImage Not Found {path}# Padded resizeimg_rgb letterbox(img_rgb_, img_size, stridestride, autoauto)[0]# Convertimg_rgb img_rgb.transpose((2, 0, 1)) # HWC to CHWimg_rgb np.ascontiguousarray(img_rgb)# 将一个内存不连续存储的数组转换为内存连续存储的数组使得运行速度更快return img_rgb, img_rgb_def preprocess_mat(mat, img_size, stride, auto):img_bgr mat # BGR# Padded resizeimg_rgb letterbox(img_bgr, img_size, stridestride, autoauto)[0]# Convertimg_rgb img_rgb.transpose((2, 0, 1))[::-1] # HWC to CHW, BGR to RGBimg_rgb np.ascontiguousarray(img_rgb)return img_rgb, img_bgrdef clip_coords(boxes, shape):# Clip bounding xyxy bounding boxes to image shape (height, width)if isinstance(boxes, torch.Tensor): # faster individuallyboxes[:, 0].clamp_(0, shape[1]) # x1boxes[:, 1].clamp_(0, shape[0]) # y1boxes[:, 2].clamp_(0, shape[1]) # x2boxes[:, 3].clamp_(0, shape[0]) # y2else: # np.array (faster grouped)boxes[:, [0, 2]] boxes[:, [0, 2]].clip(0, shape[1]) # x1, x2boxes[:, [1, 3]] boxes[:, [1, 3]].clip(0, shape[0]) # y1, y2def scale_coords(img1_shape, coords, img0_shape, ratio_padNone):# Rescale coords (xyxy) from img1_shape to img0_shapeif ratio_pad is None: # calculate from img0_shapegain min(img1_shape[0] / img0_shape[0], img1_shape[1] / img0_shape[1]) # gain old / newpad (img1_shape[1] - img0_shape[1] * gain) / 2, (img1_shape[0] - img0_shape[0] * gain) / 2 # wh paddingelse:gain ratio_pad[0][0]pad ratio_pad[1]coords[:, [0, 2]] - pad[0] # x paddingcoords[:, [1, 3]] - pad[1] # y paddingcoords[:, :4] / gainclip_coords(coords, img0_shape)return coordsdef remove_name_elements(element):name_element element.find(name)if name_element is not None and name_element.text and name_element.text.startswith(\ufeff):name_element.text name_element.text.lstrip(\ufeff)for child in element:remove_name_elements(child)def read_xml(xml_file: str, names):if os.path.getsize(xml_file) 0:return []with open(xml_file, encodingutf-8-sig) as in_file:# if not in_file.readline():# return []tree ElementTree.parse(in_file)root tree.getroot()remove_name_elements(root)results []obj: Elementfor obj in tree.findall(object):xml_box obj.find(bndbox)x_min float(xml_box.find(xmin).text)y_min float(xml_box.find(ymin).text)x_max float(xml_box.find(xmax).text)y_max float(xml_box.find(ymax).text)b [x_min, y_min, x_max, y_max]cls_id names.index(obj.find(name).text)results.append([cls_id, b])return resultsdef non_max_suppression(prediction, conf_thres0.25, iou_thres0.45, classesNone, agnosticFalse, multi_labelFalse,labels(), max_det300):Runs Non-Maximum Suppression (NMS) on inference resultsReturns:list of detections, on (n,6) tensor per image [xyxy, conf, cls]nc prediction.shape[2] - 5 # number of classesxc prediction[..., 4] conf_thres # candidates# Checksassert 0 conf_thres 1, fInvalid Confidence threshold {conf_thres}, valid values are between 0.0 and 1.0assert 0 iou_thres 1, fInvalid IoU {iou_thres}, valid values are between 0.0 and 1.0# Settingsmin_wh, max_wh 2, 7680 # (pixels) minimum and maximum box width and heightmax_nms 30000 # maximum number of boxes into torchvision.ops.nms()time_limit 10.0 # seconds to quit afterredundant True # require redundant detectionsmulti_label nc 1 # multiple labels per box (adds 0.5ms/img)merge False # use merge-NMSt time.time()output [torch.zeros((0, 6), deviceprediction.device)] * prediction.shape[0]for xi, x in enumerate(prediction): # image index, image inference# Apply constraintsx[((x[..., 2:4] min_wh) | (x[..., 2:4] max_wh)).any(1), 4] 0 # width-heightx x[xc[xi]] # confidence# Cat apriori labels if autolabellingif labels and len(labels[xi]):lb labels[xi]v torch.zeros((len(lb), nc 5), devicex.device)v[:, :4] lb[:, 1:5] # boxv[:, 4] 1.0 # confv[range(len(lb)), lb[:, 0].long() 5] 1.0 # clsx torch.cat((x, v), 0)# If none remain process next imageif not x.shape[0]:continue# Compute confx[:, 5:] * x[:, 4:5] # conf obj_conf * cls_conf# Box (center x, center y, width, height) to (x1, y1, x2, y2)box xywh2xyxy(x[:, :4])# Detections matrix nx6 (xyxy, conf, cls)if multi_label:i, j (x[:, 5:] conf_thres).nonzero(as_tupleFalse).Tx torch.cat((box[i], x[i, j 5, None], j[:, None].float()), 1)else: # conf是置信度 j是类别conf, j x[:, 5:].max(1, keepdimTrue)x torch.cat((box, conf, j.float()), 1)[conf.view(-1) conf_thres]# Filter by classif classes is not None:x x[(x[:, 5:6] torch.tensor(classes, devicex.device)).any(1)]# Apply finite constraint# if not torch.isfinite(x).all():# x x[torch.isfinite(x).all(1)]# Check shapen x.shape[0] # number of boxesif not n: # no boxescontinueelif n max_nms: # excess boxesx x[x[:, 4].argsort(descendingTrue)[:max_nms]] # sort by confidence# Batched NMSc x[:, 5:6] * (0 if agnostic else max_wh) # classesboxes, scores x[:, :4] c, x[:, 4] # boxes (offset by class), scoresi torchvision.ops.nms(boxes, scores, iou_thres) # NMSif i.shape[0] max_det: # limit detectionsi i[:max_det]if merge and (1 n 3E3): # Merge NMS (boxes merged using weighted mean)# update boxes as boxes(i,4) weights(i,n) * boxes(n,4)iou box_iou(boxes[i], boxes) iou_thres # iou matrixweights iou * scores[None] # box weightsx[i, :4] torch.mm(weights, x[:, :4]).float() / weights.sum(1, keepdimTrue) # merged boxesif redundant:i i[iou.sum(1) 1] # require redundancyoutput[xi] x[i]if (time.time() - t) time_limit:break # time limit exceededend time.time()# print(time.time() - t,seconds)return outputclass Detect():def __init__(self, weights, imgsz, conf_thres, iou_thres):self.device cpuself.weights weightsself.model Noneself.imgsz imgszself.conf_thres conf_thresself.iou_thres iou_thresif torch.cuda.is_available() and torch.cuda.device_count() 1:self.device torch.device(cuda:0)self.init_model()self.stride max(int(self.model.stride.max()), 32)def init_model(self):ckpt torch.load(self.weights, map_locationself.device) # loadckpt (ckpt.get(ema, None) or ckpt[model]).float() # FP32 modelfuse Trueself.model ckpt.fuse().eval() if fuse else ckpt.eval() # fused or un-fused model in eval mode fuse()将Conv和bn层进行合并提高模型的推理速度self.model.float()def infer_image(self, image_path):im, im0 preprocess_file(image_path, img_sizeself.imgsz, strideself.stride, autoTrue)im torch.from_numpy(im).to(self.device).float() / 255if len(im.shape) 3:im im[None] # expand for batch dim# Inferencepred self.model(im, augmentFalse, visualizeFalse)[0]# NMSpred non_max_suppression(pred, self.conf_thres, self.iou_thres, None, False, max_det1000)det pred[0]results []if len(det):# Rescale boxes from img_size to im0 sizedet[:, :4] scale_coords(im.shape[2:], det[:, :4], im0.shape).round()# resultsfor *xyxy, conf, cls in reversed(det):xyxy (torch.tensor(xyxy).view(1, 4)).view(-1).tolist() # normalized xywhresults.append([cls.item(), xyxy, conf.item()])return resultsdef infer_mat(self, mat):im, im0 preprocess_mat(mat, img_sizeself.imgsz, strideself.stride, autoTrue)im torch.from_numpy(im).to(self.device).float() / 255if len(im.shape) 3:im im[None] # expand for batch dim# Inferencepred self.model(im, augmentFalse, visualizeFalse)[0]# NMSpred non_max_suppression(pred, self.conf_thres, self.iou_thres, None, False, max_det1000)det pred[0]results []if len(det):# Rescale boxes from img_size to im0 sizedet[:, :4] scale_coords(im.shape[2:], det[:, :4], im0.shape).round()# resultsfor *xyxy, conf, cls in reversed(det):xyxy (torch.tensor(xyxy).view(1, 4)).view(-1).tolist() # normalized xywhresults.append([cls.item(), xyxy, conf.item()])return resultsdef box_iou_np(box1, box2):x11, y11, x12, y12 box1x21, y21, x22, y22 box2width1 np.maximum(0, x12 - x11)height1 np.maximum(0, y12 - y11)width2 np.maximum(0, x22 - x21)height2 np.maximum(0, y22 - y21)area1 width1 * height1area2 width2 * height2# 计算交集需要计算交集部分的左、上、右、下坐标xi1 np.maximum(x11, x21)yi1 np.maximum(y11, y21)xi2 np.minimum(x12, x22)yi2 np.minimum(y12, y22)# 计算交集部分面积w np.maximum(0, xi2 - xi1)h np.maximum(0, yi2 - yi1)intersection w * h# 计算并集union area1 area2 - intersection# 计算iouiou intersection / unionreturn ioudef main(opt):if not os.path.exists(opt.output_path):os.makedirs(opt.output_path, exist_okTrue)#oxist_ok表示如果目录存在不要抛出异常正常结束detect Detect(opt.weights, opt.imgsz, opt.conf_thres, opt.iou_thres)imgs []for root,dirs,files in os.walk(opt.input_path):for file in files:if os.path.splitext(file)[1] in opt.extensions:imgs.append(root/file)total len(imgs)for i,img in enumerate(imgs):print(f{i 1 : 05d}/{total : 05d} {img})mat cv_imread(img)xml os.path.splitext(img)[0].xmlh,w,_ mat.shaperesults detect.infer_image(img)# 标注anns []if os.path.exists(xml):anns read_xml(xml, opt.names)else:anns []# 核查误报fps []if opt.fp:for result in results:result_cls, result_box, _ resultif result_cls in opt.verifynames:finded Falsefor ann in anns:ann_cls, ann_box annif ann_cls result_cls and box_iou_np(ann_box, result_box) 0:finded Truebreakif not finded:fps.append([result_cls, result_box])# 核查漏报fns []if opt.fn:for ann in anns:ann_cls, ann_box annif ann_cls in opt.verifynames:finded Falsefor result in results:result_cls, result_box, _ resultif ann_cls result_cls and box_iou_np(ann_box, result_box) 0:finded Truebreakif not finded:fns.append([ann_cls, ann_box])if len(fps) 0 and len(fns) 0:continue# 写文件writer Writer(img, w, h)# 写原始标注for ann in anns:ann_cls, ann_box annx_min ann_box[0]y_min ann_box[1]x_max ann_box[2]y_max ann_box[3]writer.addObject(opt.names[int(ann_cls)], x_min, y_min, x_max, y_max)# 写误报if opt.fp:for ann in fps:ann_cls, ann_box annx_min ann_box[0]y_min ann_box[1]x_max ann_box[2]y_max ann_box[3]writer.addObject(误报- opt.names[int(ann_cls)], x_min, y_min, x_max, y_max)# 写漏报if opt.fn:for ann in fns:ann_cls, ann_box annx_min ann_box[0]y_min ann_box[1]x_max ann_box[2]y_max ann_box[3]writer.addObject(漏报- opt.names[int(ann_cls)], x_min, y_min, x_max, y_max)# 写文件writer.save(os.path.join(opt.output_path, os.path.basename(xml)))shutil.copy2(img, os.path.join(opt.output_path, os.path.basename(img)))def parse_opt(known):parser argparse.ArgumentParser()parser.add_argument(--weights,typestr, defaultROOT / weights/best.pt, help模型权重pt文件)parser.add_argument(--imgsz, typetuple, default(1280,1280), help输入模型大小)parser.add_argument(--conf_thres, typefloat, default0.25, help模型conf阈值)parser.add_argument(--iou_thres, typefloat, default0.5, help标注与模型输出框的IOU阈值用于判断误报和漏报)parser.add_argument(--names, typelist, default[键盘, 显示器, 鼠标, 桌子, 椅子, 人],help核查的所有类别标注名称)parser.add_argument(--verifynames, typelist, default[0,1], help需要核查的类别)parser.add_argument(--input_path, typestr, defaultr, help输入image和xml路径)parser.add_argument(--output_path, typestr, defaultr核查, help输出image和xml路径)parser.add_argument(--extensions, typelist, default[.jpg, .JPG, .jpeg, .png, .bmp, .tiff, .tif, .svg, .pfg])parser.add_argument(--fp, typebool, defaultTrue, help是否核查误报)parser.add_argument(--fn, typebool, defaultTrue, help是否核查漏报)return parser.parse_known_args()[0] if known else parser.parse_args() #True 标志可以处理任何位置参数不会因为位置参数崩溃Fakse任何未知参数导致程序显示错误消息并退出if __name__ __main__:opt parse_opt(True)main(opt) 总结
安装对应的库修改命令行参数weights、names、verifynames、input_path和output_path即可使用。注将源码放置到yolov5对应的文件夹下方即可。
