yolov3--25--Detectron目标检测可视化-P-R曲线绘制-Recall-TP-FP-FN等评价指标

Detectron目标检测平台

评估训练结果（生成mAP）

CUDA_VISIBLE_DEVICES=4 python tools/test_net.py --cfg experiments/2gpu_e2e_faster_rcnn_R-50-FPN-voc2007.yaml   TEST.WEIGHTS out-faster-rcnn-1/train/voc_2007_train/generalized_rcnn/model_final.pkl NUM_GPUS 1 | tee visualization/2gpu_e2e_faster_rcnn_R-50-FPN-voc2007-test_net.log

可视化检测结果（测试多张图片）

CUDA_VISIBLE_DEVICES=4 python tools/visualize_results.py --dataset voc_2007_val --detections out-faster-rcnn-1/test/voc_2007_val/generalized_rcnn/detections.pkl --output-dir out-faster-rcnn-1/detectron-visualizations

P-R曲线绘制

效果如下图：

得到Recall-TP-FP-FN等评价指标

改动一：函数部分更改为：

    # first load gtif not os.path.isdir(cachedir):os.mkdir(cachedir)imageset = os.path.splitext(os.path.basename(imagesetfile))[0]cachefile = os.path.join(cachedir, imageset + '_annots.pkl')  #val_annotations.pkl# read list of imageswith open(imagesetfile, 'r') as f:  #lines = f.readlines()imagenames = [x.strip() for x in lines]#if not os.path.isfile(cachefile):# load annotsrecs = {}for i, imagename in enumerate(imagenames):recs[imagename] = parse_rec(annopath.format(imagename))if i % 100 == 0:logger.info('Reading annotation for {:d}/{:d}'.format(i + 1, len(imagenames)))# savelogger.info('Saving cached annotations to {:s}'.format(cachefile))save_object(recs, cachefile)   #changeelse:recs = load_object(cachefile)   #change# extract gt objects for this classclass_recs = {}npos = 0for imagename in imagenames:R = [obj for obj in recs[imagename] if obj['name'] == classname] #bbox = np.array([x['bbox'] for x in R])difficult = np.array([x['difficult'] for x in R]).astype(np.bool)det = [False] * len(R)npos = npos + sum(~difficult)class_recs[imagename] = {'bbox': bbox,'difficult': difficult,'det': det}# read detsdetfile = detpath.format(classname)  #with open(detfile, 'r') as f:lines = f.readlines()  #splitlines = [x.strip().split(' ') for x in lines]  #image_ids = [x[0] for x in splitlines]       #confidence = np.array([float(x[1]) for x in splitlines])  #BB = np.array([[float(z) for z in x[2:]] for x in splitlines]) ## sort by confidencesorted_ind = np.argsort(-confidence) #BB = BB[sorted_ind, :]      #image_ids = [image_ids[x] for x in sorted_ind]  ## go down dets and mark TPs and FPsnd = len(image_ids)  #tp = np.zeros(nd)fp = np.zeros(nd)for d in range(nd):  #R = class_recs[image_ids[d]]  #image_ids[d]bb = BB[d, :].astype(float)  #ovmax = -np.infBBGT = R['bbox'].astype(float)#if BBGT.size > 0:# compute overlaps# intersectionixmin = np.maximum(BBGT[:, 0], bb[0])iymin = np.maximum(BBGT[:, 1], bb[1])ixmax = np.minimum(BBGT[:, 2], bb[2])iymax = np.minimum(BBGT[:, 3], bb[3])iw = np.maximum(ixmax - ixmin + 1., 0.)ih = np.maximum(iymax - iymin + 1., 0.)inters = iw * ih# unionuni = ((bb[2] - bb[0] + 1.) * (bb[3] - bb[1] + 1.) +(BBGT[:, 2] - BBGT[:, 0] + 1.) *(BBGT[:, 3] - BBGT[:, 1] + 1.) - inters)overlaps = inters / uniovmax = np.max(overlaps)jmax = np.argmax(overlaps)if ovmax > ovthresh:if not R['difficult'][jmax]:if not R['det'][jmax]:tp[d] = 1.R['det'][jmax] = 1  #else:fp[d] = 1.  else:fp[d] = 1.  #num = len(np.where(confidence>0.7)[0])   #confidence# compute precision recallfp = np.cumsum(fp)fpnum = int(fp[num-1]) #tp = np.cumsum(tp)tpnum = int(tp[num-1]) #rec = tp / float(npos)objectnum = int(npos)# avoid divide by zero in case the first detection matches a difficult# ground truthprec = tp / np.maximum(tp + fp, np.finfo(np.float64).eps)alarm = 1-prec[num-1]ap = voc_ap(rec, prec, use_07_metric)return rec, prec, ap, objectnum, tpnum, fpnum, alarm

改动二：函数部分更改为：

if not os.path.isdir(output_dir):os.mkdir(output_dir)for _, cls in enumerate(json_dataset.classes):if cls == '__background__':continuefilename = _get_voc_results_file_template(json_dataset, salt).format(cls)rec, prec, ap ,objectnum, tpnum, fpnum, alarm = voc_eval(filename, anno_path, image_set_path, cls, cachedir, ovthresh=0.5,use_07_metric=use_07_metric)aps += [ap]logger.info('AP for {} = {:.4f}'.format(cls, ap))logger.info(' {}TP+FN{:d}, TP{:d}, FN{:d}, recall{:.4f}, FP{:d}, precision{:.4f}, precision2{:.4f}'.format(cls, objectnum, tpnum, objectnum-tpnum, tpnum/float(objectnum), fpnum, 1-alarm, tpnum/(tpnum+fpnum)))

不使用07_metric计算AP指标，替换True与False的位置（重要，会影响精度）

.sh 训练文件:

 CUDA_VISIBLE_DEVICES='6,7' python tools/train_net.py --cfg experiments/e2e_mask_rcnn_R-101-FPN_2x_gn-train1999-2gpu.yaml OUTPUT_DIR e2e_mask_rcnn_R-101-FPN_2x_gn-train1999-2gpu/ | tee visualization/e2e_mask_rcnn_R-101-FPN_2x_gn-train1999-2gpu-start6-18-416-416-1.log

1、训练得到.pkl文件，

2、转换为此种格式：

3、和其它曲线画到一张图中：

出现错误：

python3错误之ImportError: No module named 'cPickle'

Python 文件操作出现错误(result, consumed) = self._buffer_decode(data, self.errors, final)

解决办法：

解决办法：“r”改为“rb”

R = [obj for obj in recs[imagename] if obj['name'] == classname] KeyError: '007765'

有效解决方案:训练前需要将cache中的pki文件以及VOCdevkit2007中annotations_cache的缓存删掉。我的路径是../data/VOCdevkit/annotations_cache/ ,删掉annots.pkl即可正常test,亲测有效

问题：https://blog.csdn.net/nuoyanli/article/details/94434890

注意Python插入程序时的对齐：空4格

pickle.load的时候出现EOFError: Ran out of input

参考：https://blog.csdn.net/Mr_health/article/details/89519469

yolov3--25--Detectron目标检测可视化-P-R曲线绘制-Recall-TP-FP-FN等评价指标相关推荐

计算机视觉：基于YOLO-V3林业病虫害目标检测
计算机视觉:基于YOLO-V3林业病虫害目标检测卷积神经网络提取特征根据输出特征图计算预测框位置和类别建立输出特征图与预测框之间的关联计算预测框是否包含物体的概率计算预测框位置坐标计算物体 ...
树莓派摄像头 C++ OpenCV YoloV3 实现实时目标检测
树莓派摄像头 C++ OpenCV YoloV3 实现实时目标检测本文将实现树莓派摄像头 C++ OpenCV YoloV3 实现实时目标检测,我们会先实现树莓派对视频文件的逐帧检测来验证算法流程, ...
YOLOv3实现鱼类目标检测
YOLOv3实现鱼类目标检测我将以一个项目实例,记录如何用YOLOv3训练自己的数据集. 在开始之前,首先了解一下YOLO系列代表性的DarkNet网络. 如下图所示,是YOLOv3中使用的Dark ...
手把手教你用yolov3模型实现目标检测教程(一) - 环境配置
手把手教你用yolov3模型实现目标检测(一) 写在前面: 由于项目需要,使用yolov3模型做了各种现实场景物体的目标检测.做完了过了好长时间,感觉有些遗忘,还是该留下点东西,方便自己查找,也希望能 ...
基于yolov3的行人目标检测算法在图像和视频中识别检测
资源下载地址:https://download.csdn.net/download/sheziqiong/85772186 资源下载地址:https://download.csdn.net/downl ...
目标检测 TP\FP\FN\TN如何理解？FN和TN无意义
1.TP TN FP FN的概念 TP TN FP FN里面一共出现了4个字母,分别是T F P N. T是True: F是False: P是Positive: N是Negative. T或者F代表的 ...
yolov3权重_目标检测之 YOLOv3 (Pytorch实现)
1.文章目的 Github上已经有YOLOv3 Pytorch版本的实现,但我总觉得不是自己的东西直接拿过来用着不舒服.想着自己动手丰衣足食,因此,本文主要是出于学习的目的,将YOLO3网络自己搭建一 ...
目标检测计算mAP，AP，Recall，Precision的计算方式和代码(YOLO和FastRCNN等)
目标检测中计算mAP是较为复杂的,并不是很多讲解中说的那个计算precision和recall,然后总的ground truth 目标和检测出的真实目标做除法就可以了.而是需要构建precision和 ...
目标检测相关概念：IOU，precision, recall, AP, mAP
1.IOU(交并比) IOU,交并比,顾名思义,就是预测框bounding box与真实框ground truth的交集比上并集.可以用来衡量检测物体位置的偏差.形象点可以看下图(用画图软件所画): ...