diff --git a/contrast/__pycache__/genfeats.cpython-39.pyc b/contrast/__pycache__/genfeats.cpython-39.pyc new file mode 100644 index 0000000..ca68b22 Binary files /dev/null and b/contrast/__pycache__/genfeats.cpython-39.pyc differ diff --git a/contrast/feat_select.py b/contrast/feat_select.py index 0d58ed7..5d64712 100644 --- a/contrast/feat_select.py +++ b/contrast/feat_select.py @@ -16,7 +16,7 @@ from tracking.utils.read_data import extract_data, read_deletedBarcode_file, rea # from tracking.dotrack.dotracks import Track from one2n_contrast import compute_recall_precision, show_recall_prec -from one2n_contrast import performance_evaluate +from one2n_contrast import performance_evaluate, one2n_return, one2n_deleted def compute_similar(feat1, feat2): diff --git a/contrast/genfeats.py b/contrast/genfeats.py index 651c9da..2e889ee 100644 --- a/contrast/genfeats.py +++ b/contrast/genfeats.py @@ -27,7 +27,7 @@ model.load_state_dict(torch.load(model_path, map_location=conf.device)) model.eval() print('load model {} '.format(conf.testbackbone)) -def get_std_barcodeDict(bcdpath, savepath): +def get_std_barcodeDict(bcdpath, savepath, bcdSet): ''' inputs: bcdpath: 已清洗的barcode样本图像，如果barcode下有'base'文件夹，只选用该文件夹下图像 @@ -42,10 +42,14 @@ def get_std_barcodeDict(bcdpath, savepath): '''读取数据集中 barcode 列表''' stdBarcodeList = [] for filename in os.listdir(bcdpath): - filepath = os.path.join(bcdpath, filename) + # filepath = os.path.join(bcdpath, filename) # if not os.path.isdir(filepath) or not filename.isdigit() or len(filename)<8: # continue - stdBarcodeList.append(filename) + if bcdSet is None: + stdBarcodeList.append(filename) + elif filename in bcdSet: + stdBarcodeList.append(filename) + bcdPaths = [(barcode, os.path.join(bcdpath, barcode)) for barcode in stdBarcodeList] @@ -184,18 +188,15 @@ def stdfeat_infer(imgPath, featPath, bcdSet=None): -def genfeatures(imgpath, bcdpath, featpath): +def genfeatures(imgpath, bcdpath, featpath, bcdSet=None): + ''' 生成标准特征集 ''' + '''1. 提取 imgpath 中样本地址，生成字典{barcode: [imgpath1, imgpath1, ...]} + 并存储于: bcdpath, 格式为 barcode.pickle''' + get_std_barcodeDict(imgpath, bcdpath, bcdSet) - get_std_barcodeDict(imgpath, bcdpath) - stdfeat_infer(bcdpath, featpath, bcdSet=None) + '''2. 特征提取，并保存至文件夹 featpath 中，也根据 bcdSet 交集执行''' + stdfeat_infer(bcdpath, featpath, bcdSet) - print(f"Features have generated, saved in: {featpath}") - - - - - - def main(): imgpath = r"\\192.168.1.28\share\展厅barcode数据\整理\zhantingBase" bcdpath = r"D:\exhibition\dataset\bcdpath" diff --git a/contrast/one2n_contrast.py b/contrast/one2n_contrast.py index 0c3ae93..57feea7 100644 --- a/contrast/one2n_contrast.py +++ b/contrast/one2n_contrast.py @@ -21,7 +21,7 @@ import sys sys.path.append(r"D:\DetectTracking") from tracking.utils.plotting import Annotator, colors from tracking.utils.read_data import extract_data, read_deletedBarcode_file, read_tracking_output, read_returnGoods_file -from tracking.utils.plotting import draw_tracking_boxes +from tracking.utils.plotting import draw_tracking_boxes, get_subimgs from contrast.utils.tools import showHist, show_recall_prec, compute_recall_precision @@ -148,13 +148,18 @@ def get_contrast_paths(pair, basepath): if len(input_folds): indice = np.argsort(np.array(times)) input_fold = input_folds[indice[-1]] + inputpath = os.path.join(basepath, input_fold) + '''取出操作错误匹配的放入操作对应的文件夹''' if len(errmatch_folds): indice = np.argsort(np.array(errmatch_times)) errmatch_fold = errmatch_folds[indice[-1]] + errorpath = os.path.join(basepath, errmatch_fold) + + '''放入事件文件夹地址、取出事件文件夹地址''' getoutpath = os.path.join(basepath, getout_fold) @@ -163,33 +168,33 @@ def get_contrast_paths(pair, basepath): return getoutpath, inputpath, errorpath -def save_tracking_imgpairs(pair, basepath, savepath): +def save_tracking_imgpairs(pairs, savepath): ''' - basepath: 原始测试数据文件夹的路径 + pairs: 匹配事件对 savepath: 保存的目标文件夹 ''' + def get_event_path(evtpath): + basepath, eventname = os.path.split(evtpath) + evt_path = '' + for filename in os.listdir(basepath): + if filename.find(eventname)==0: + evt_path = os.path.join(basepath, filename) + break + return evt_path - getoutpath, inputpath, errorpath = get_contrast_paths(pair, basepath) - - if len(inputpath)==0: - return + getoutpath = get_event_path(pairs[0]) + inputpath = get_event_path(pairs[1]) + if len(pairs) == 3: + errorpath = get_event_path(pairs[2]) + else: + errorpath = '' - '''==== 读取放入、取出事件对应的 Yolo输入的前后摄图像，0：后摄，1：前摄 ====''' - - - '''==== 读取放入、取出事件对应的 tracking 输出：boxes, feats ====''' - - if len(inputpath): - imgs_input_0, imgs_input_1 = read_tracking_imgs(inputpath) - - input_data_0 = os.path.join(inputpath, '0_tracking_output.data') - input_data_1 = os.path.join(inputpath, '1_tracking_output.data') - boxes_input_0, feats_input_0 = read_tracking_output(input_data_0) - boxes_input_1, feats_input_1 = read_tracking_output(input_data_1) - ImgsInput_0 = draw_tracking_boxes(imgs_input_0, boxes_input_0) - ImgsInput_1 = draw_tracking_boxes(imgs_input_1, boxes_input_1) - + ''' 1. 读取放入、取出事件对应的 Yolo输入的前后摄图像，0：后摄，1：前摄 + 2. 读取放入、取出事件对应的 tracking 输出：boxes, feats + 3. boxes绘制并保存图像序列 + 4. 截取并保存轨迹子图 + ''' if len(getoutpath): imgs_getout_0, imgs_getout_1 = read_tracking_imgs(getoutpath) @@ -199,9 +204,28 @@ def save_tracking_imgpairs(pair, basepath, savepath): boxes_output_1, feats_output_1 = read_tracking_output(getout_data_1) ImgsGetout_0 = draw_tracking_boxes(imgs_getout_0, boxes_output_0) ImgsGetout_1 = draw_tracking_boxes(imgs_getout_1, boxes_output_1) - - if len(errorpath): + SubimgsGetout_0 = get_subimgs(imgs_getout_0, boxes_output_0) + SubimgsGetout_1 = get_subimgs(imgs_getout_1, boxes_output_1) + + savedir = os.path.basename(getoutpath) + + if len(inputpath): + imgs_input_0, imgs_input_1 = read_tracking_imgs(inputpath) + + input_data_0 = os.path.join(inputpath, '0_tracking_output.data') + input_data_1 = os.path.join(inputpath, '1_tracking_output.data') + boxes_input_0, feats_input_0 = read_tracking_output(input_data_0) + boxes_input_1, feats_input_1 = read_tracking_output(input_data_1) + ImgsInput_0 = draw_tracking_boxes(imgs_input_0, boxes_input_0) + ImgsInput_1 = draw_tracking_boxes(imgs_input_1, boxes_input_1) + + SubimgsInput_0 = get_subimgs(imgs_input_0, boxes_input_0) + SubimgsInput_1 = get_subimgs(imgs_input_1, boxes_input_1) + + savedir = savedir + '+' + os.path.basename(inputpath) + + if len(errorpath): imgs_error_0, imgs_error_1 = read_tracking_imgs(errorpath) error_data_0 = os.path.join(errorpath, '0_tracking_output.data') @@ -211,37 +235,61 @@ def save_tracking_imgpairs(pair, basepath, savepath): ImgsError_0 = draw_tracking_boxes(imgs_error_0, boxes_error_0) ImgsError_1 = draw_tracking_boxes(imgs_error_1, boxes_error_1) + SubimgsError_0 = get_subimgs(imgs_error_0, boxes_error_0) + SubimgsError_1 = get_subimgs(imgs_error_0, boxes_error_0) - savedir = pair[0] + pair[1] - if len(errorpath): - savedir = savedir + '_' + errorpath.split('_')[-1] - foldname = os.path.join(savepath, 'imgpairs', savedir) - if not os.path.exists(foldname): - os.makedirs(foldname) - - for i, img in enumerate(ImgsInput_0): - imgpath = os.path.join(foldname, f'input_0_{i}.png') - cv2.imwrite(imgpath, img) - for i, img in enumerate(ImgsInput_1): - imgpath = os.path.join(foldname, f'input_1_{i}.png') - cv2.imwrite(imgpath, img) - for i, img in enumerate(ImgsGetout_0): - imgpath = os.path.join(foldname, f'getout_0_{i}.png') - cv2.imwrite(imgpath, img) - for i, img in enumerate(ImgsGetout_1): - imgpath = os.path.join(foldname, f'getout_1_{i}.png') - cv2.imwrite(imgpath, img) + savedir = savedir + '+' + os.path.basename(errorpath) - for i, img in enumerate(ImgsError_0): - imgpath = os.path.join(foldname, f'errMatch_0_{i}.png') + ''' savepath\pairs\savedir\eventpairs\保存画框后的图像序列 ''' + entpairs = os.path.join(savepath, 'pairs', savedir, 'eventpairs') + if not os.path.exists(entpairs): + os.makedirs(entpairs) + for fid, img in ImgsInput_0: + imgpath = os.path.join(entpairs, f'input_0_{fid}.png') cv2.imwrite(imgpath, img) - for i, img in enumerate(ImgsError_1): - imgpath = os.path.join(foldname, f'errMatch_1_{i}.png') + for fid, img in ImgsInput_1: + imgpath = os.path.join(entpairs, f'input_1_{fid}.png') cv2.imwrite(imgpath, img) + for fid, img in ImgsGetout_0: + imgpath = os.path.join(entpairs, f'getout_0_{fid}.png') + cv2.imwrite(imgpath, img) + for fid, img in ImgsGetout_1: + imgpath = os.path.join(entpairs, f'getout_1_{fid}.png') + cv2.imwrite(imgpath, img) + if 'ImgsError_0' in vars() and 'ImgsError_1' in vars(): + for fid, img in ImgsError_0: + imgpath = os.path.join(entpairs, f'errMatch_0_{fid}.png') + cv2.imwrite(imgpath, img) + for fid, img in ImgsError_1: + imgpath = os.path.join(entpairs, f'errMatch_1_{fid}.png') + cv2.imwrite(imgpath, img) + + ''' savepath\pairs\savedir\subimgpairs\保存轨迹子图 ''' + subimgpairs = os.path.join(savepath, 'pairs', savedir, 'subimgpairs') + if not os.path.exists(subimgpairs): + os.makedirs(subimgpairs) + for fid, bid, img in SubimgsGetout_0: + imgpath = os.path.join(subimgpairs, f'getout_0_{fid}_{bid}.png') + cv2.imwrite(imgpath, img) + for fid, bid, img in SubimgsGetout_1: + imgpath = os.path.join(subimgpairs, f'getout_1_{fid}_{bid}.png') + cv2.imwrite(imgpath, img) + for fid, bid, img in SubimgsInput_0: + imgpath = os.path.join(subimgpairs, f'input_0_{fid}_{bid}.png') + cv2.imwrite(imgpath, img) + for fid, bid, img in SubimgsInput_1: + imgpath = os.path.join(subimgpairs, f'input_1_{fid}_{bid}.png') + cv2.imwrite(imgpath, img) + if 'SubimgsError_0' in vars() and 'SubimgsError_1' in vars(): + for fid, bid, img in SubimgsError_0: + imgpath = os.path.join(subimgpairs, f'errMatch_0_{fid}_{bid}.png') + cv2.imwrite(imgpath, img) + for fid, bid, img in SubimgsError_1: + imgpath = os.path.join(subimgpairs, f'errMatch_1_{fid}_{bid}.png') + cv2.imwrite(imgpath, img) - -def one2n_old(all_list): +def one2n_deleted(all_list): corrpairs, errpairs, correct_similarity, err_similarity = [], [], [], [] for s_list in all_list: seqdir = s_list['SeqDir'].strip() @@ -277,8 +325,9 @@ def one2n_old(all_list): -def one2n_new(all_list): - corrpairs, correct_similarity, errpairs, err_similarity = [], [], [], [] +def one2n_return(all_list, basepath): + corrpairs, corr_similarity, errpairs, err_similarity = [], [], [], [] + for s_list in all_list: seqdir = s_list['SeqDir'].strip() delete = s_list['Deleted'].strip() @@ -305,7 +354,7 @@ def one2n_new(all_list): matched_barcode = barcodes[index] if matched_barcode == delete: corrpairs.append((seqdir, events[index])) - correct_similarity.append(max(similarity)) + corr_similarity.append(max(similarity)) else: idx = [i for i, name in enumerate(events) if name.split('_')[-1] == delete] idxmax, simimax = -1, -1 @@ -314,49 +363,80 @@ def one2n_new(all_list): if similarity[k] > simimax: idxmax = k simimax = similarity[k] - - errpairs.append((seqdir, events[idxmax], events[index])) + if idxmax>-1: + input_event = events[idxmax] + else: + input_event = '' + + errpairs.append((seqdir, input_event, events[index])) err_similarity.append(max(similarity)) - - return errpairs, corrpairs, err_similarity, correct_similarity + return corrpairs, errpairs, corr_similarity, err_similarity -# def contrast_analysis(del_barcode_file, basepath, savepath, saveimgs=False): -def get_relative_paths(del_barcode_file, basepath, savepath, saveimgs=False): - ''' - del_barcode_file: - deletedBarcode.txt 格式的 1:n 数据结果文件 - returnGoods.txt格式数据文件不需要调用该函数，one2n_old() 函数返回的 errpairs - 中元素为三元元组（取出，放入, 错误匹配） - ''' +def test_rpath_deleted(): + '''deletedBarcode.txt 格式的 1:n 数据结果文件, returnGoods.txt格式数据文件不需要调用该函数''' + + del_bfile = r'\\192.168.1.28\share\测试_202406\709\deletedBarcode.txt' + basepath = r'\\192.168.1.28\share\测试_202406\709' + savepath = r'D:\DetectTracking\contrast\result' + saveimgs = True + + + relative_paths = [] '''1. 读取 deletedBarcode 文件 ''' - all_list = read_deletedBarcode_file(del_barcode_file) + all_list = read_deletedBarcode_file(del_bfile) '''2. 算法性能评估，并输出 (取出，删除, 错误匹配) 对 ''' - errpairs, corrpairs, _, _ = one2n_old(all_list) + corrpairs, errpairs, _, _ = one2n_deleted(all_list) '''3. 构造事件组合(取出，放入并删除, 错误匹配) 对应路径 ''' for errpair in errpairs: GetoutPath, InputPath, ErrorPath = get_contrast_paths(errpair, basepath) - relative_paths.append((GetoutPath, InputPath, ErrorPath)) + pairs = (GetoutPath, InputPath, ErrorPath) + relative_paths.append(pairs) + + print(InputPath) '''3. 获取 (取出，放入并删除, 错误匹配) 对应路径，保存相应轨迹图像''' - if saveimgs: - save_tracking_imgpairs(errpair, basepath, savepath) + if saveimgs: + save_tracking_imgpairs(pairs, savepath) - return relative_paths - - -def one2n_test(): - fpath = r'\\192.168.1.28\share\测试_202406\deletedBarcode\other' - fpath = r'\\192.168.1.28\share\测试_202406\1030\images' +def test_rpath_return(): + return_bfile = r'\\192.168.1.28\share\测试_202406\1101\images\returnGoods.txt' + basepath = r'\\192.168.1.28\share\测试_202406\1101\images' + savepath = r'D:\DetectTracking\contrast\result' + all_list = read_returnGoods_file(return_bfile) + corrpairs, errpairs, _, _ = one2n_return(all_list, basepath) + for corrpair in corrpairs: + GetoutPath = os.path.join(basepath, corrpair[0]) + InputPath = os.path.join(basepath, corrpair[1]) + + pairs = (GetoutPath, InputPath) + save_tracking_imgpairs(pairs, savepath) + + for errpair in errpairs: + GetoutPath = os.path.join(basepath, errpair[0]) + InputPath = os.path.join(basepath, errpair[1]) + ErrorPath = os.path.join(basepath, errpair[2]) + + pairs = (GetoutPath, InputPath, ErrorPath) + save_tracking_imgpairs(pairs, savepath) + + +def test_one2n(): + ''' + 1:n 性能测试 + 兼容 2 种 txt 文件格式：returnGoods.txt, deletedBarcode.txt + fpath: 文件路径、或文件夹，其中包含多个 txt 文件 + savepath: pr曲线保存路径 + ''' + # fpath = r'\\192.168.1.28\share\测试_202406\deletedBarcode\other' # deletedBarcode.txt + fpath = r'\\192.168.1.28\share\测试_202406\returnGoods\all' # returnGoods.txt savepath = r'\\192.168.1.28\share\测试_202406\deletedBarcode\illustration' - if not os.path.exists(savepath): - os.mkdir(savepath) if os.path.isdir(fpath): filepaths = [os.path.join(fpath, f) for f in os.listdir(fpath) @@ -366,37 +446,27 @@ def one2n_test(): filepaths = [fpath] else: return - - - FileFormat = {} + if not os.path.exists(savepath): + os.mkdir(savepath) + BarLists, blists = {}, [] for pth in filepaths: file = str(Path(pth).stem) if file.find('deletedBarcode')>=0: - FileFormat[file] = 'deletedBarcode' blist = read_deletedBarcode_file(pth) - elif file.find('returnGoods')>=0: - FileFormat[file] = 'returnGoods' + if file.find('returnGoods')>=0: blist = read_returnGoods_file(pth) - else: - return - - + BarLists.update({file: blist}) blists.extend(blist) - BarLists.update({file: blist}) - BarLists.update({"Total": blists}) - + if len(blists): BarLists.update({"Total": blists}) for file, blist in BarLists.items(): - if FileFormat[file] == 'deletedBarcode': - _, _, err_similarity, correct_similarity = one2n_old(blist) - elif FileFormat[file] == 'returnGoods': - _, _, err_similarity, correct_similarity = one2n_new(blist) - else: - _, _, err_similarity, correct_similarity = one2n_old(blist) - + if all(b['filetype']=="deletedBarcode" for b in blist): + _, _, correct_similarity, err_similarity = one2n_deleted(blist) + if all(b['filetype']=="returnGoods" for b in blists): + _, _, correct_similarity, err_similarity = one2n_return(blist) recall, prec, ths = compute_recall_precision(err_similarity, correct_similarity) @@ -413,51 +483,16 @@ def one2n_test(): - -def test_getreltpath(): - ''' - 适用于：deletedBarcode.txt，不适用于：returnGoods.txt - ''' - - del_barcode_file = r'\\192.168.1.28\share\测试_202406\709\deletedBarcode.txt' - basepath = r'\\192.168.1.28\share\测试_202406\709' - - # del_barcode_file = r'\\192.168.1.28\share\测试_202406\1030\images\returnGoods.txt' - # basepath = r'\\192.168.1.28\share\测试_202406\1030\images' - - savepath = r'D:\contrast\dataset\result' - saveimgs = True - try: - relative_path = get_relative_paths(del_barcode_file, basepath, savepath, saveimgs) - except Exception as e: - print(f'Error Type: {e}') - - if __name__ == '__main__': - - one2n_test() - - # test_getreltpath() - + # test_one2n() + test_rpath_return() # returnGoods.txt + test_rpath_deleted() # deleteBarcode.txt + + + # try: + # test_rpath_return() + # test_rpath_deleted() + # except Exception as e: + # print(e) - - - - - - - - - - - - - - - - - - - - diff --git a/contrast/one2one_contrast.py b/contrast/one2one_contrast.py index 27f4b20..289d4fd 100644 --- a/contrast/one2one_contrast.py +++ b/contrast/one2one_contrast.py @@ -11,7 +11,7 @@ Created on Fri Aug 30 17:53:03 2024 标准特征提取，并保存至文件夹 stdFeaturePath 中， 也可在运行过程中根据与购物事件集合 barcodes 交集执行 2. 1:1 比对性能测试， - func: contrast_performance_evaluate(resultPath) + func: one2one_eval(resultPath) (1) 求购物事件和标准特征级 Barcode 交集，构造 evtDict、stdDict (2) 构造扫 A 放 A、扫 A 放 B 组合，mergePairs = AA_list + AB_list (3) 循环计算 mergePairs 中元素 "(A, A) 或 (A, B)" 相似度; @@ -32,86 +32,83 @@ import os import sys import random import pickle -import torch +# import torch import time -import json +# import json from pathlib import Path from scipy.spatial.distance import cdist import matplotlib.pyplot as plt import shutil from datetime import datetime -from openpyxl import load_workbook, Workbook +# from openpyxl import load_workbook, Workbook -# Vit版resnet, 和现场特征不一致，需将resnet_vit中文件提出 # from config import config as conf -# from model import resnet18 -# from inference import load_contrast_model -# from inference import featurize -# embedding_size = conf.embedding_size -# img_size = conf.img_size -# device = conf.device -# model = load_contrast_model() +# from model import resnet18 as resnet18 +# from feat_inference import inference_image sys.path.append(r"D:\DetectTracking") -from tracking.utils.read_data import extract_data, read_tracking_output, read_deletedBarcode_file - -from config import config as conf -from model import resnet18 as resnet18 -from feat_inference import inference_image +from tracking.utils.read_data import extract_data, read_tracking_output, read_one2one_simi, read_deletedBarcode_file +from genfeats import genfeatures, stdfeat_infer IMG_FORMAT = ['.bmp', '.jpg', '.jpeg', '.png'] -''' -共6个地址： - (1) stdSamplePath: 用于生成比对标准特征集的原始图像地址 - (2) stdBarcodePath: 比对标准特征集原始图像地址的pickle文件存储，{barcode: [imgpath1, imgpath1, ...]} - (3) stdFeaturePath: 比对标准特征集特征存储地址 - (4) eventFeatPath: 用于1:1比对的购物事件特征存储地址、对应子图存储地址 - (5) subimgPath: 1:1比对购物事件轨迹、标准barcode所对应的 subimgs 存储地址 - (6) resultPath: 1:1比对结果存储地址 -''' - -stdSamplePath = r"\\192.168.1.28\share\已标注数据备份\对比数据\barcode\barcode_500_1979_已清洗" -stdBarcodePath = r"\\192.168.1.28\share\测试_202406\contrast\std_barcodes_2192" -stdFeaturePath = r"\\192.168.1.28\share\测试_202406\contrast\std_features_ft32" -eventFeatPath = r"\\192.168.1.28\share\测试_202406\contrast\events" -subimgPath = r'\\192.168.1.28\share\测试_202406\contrast\subimgs' -resultPath = r"D:\DetectTracking\contrast\result\pickle" -if not os.path.exists(resultPath): - os.makedirs(resultPath) - -##============ load resnet mdoel -model = resnet18().to(conf.device) -# model = nn.DataParallel(model).to(conf.device) -model.load_state_dict(torch.load(conf.test_model, map_location=conf.device)) -model.eval() -print('load model {} '.format(conf.testbackbone)) -def creat_shopping_event(eventPath, subimgPath=False): +def int8_to_ft16(arr_uint8, amin, amax): + arr_ft16 = (arr_uint8 / 255 * (amax-amin) + amin).astype(np.float16) + + return arr_ft16 + +def ft16_to_uint8(arr_ft16): + # pickpath = r"\\192.168.1.28\share\测试_202406\contrast\std_features_ft32vsft16\6902265587712_ft16.pickle" + + # with open(pickpath, 'rb') as f: + # edict = pickle.load(f) + + # arr_ft16 = edict['feats'] + + amin = np.min(arr_ft16) + amax = np.max(arr_ft16) + arr_ft255 = (arr_ft16 - amin) * 255 / (amax-amin) + arr_uint8 = arr_ft255.astype(np.uint8) + + arr_ft16_ = int8_to_ft16(arr_uint8, amin, amax) + + arrDistNorm = np.linalg.norm(arr_ft16_ - arr_ft16) / arr_ft16_.size + + return arr_uint8, arr_ft16_ + +def creat_shopping_event(eventPath): '''构造放入商品事件字典，这些事件需满足条件： 1) 前后摄至少有一条轨迹输出 2) 保存有帧图像，以便裁剪出 boxe 子图 ''' - # filename = "20240723-155413_6904406215720" - - '''filename下为一次购物事件''' - eventName = os.path.basename(eventPath) - '''================ 0. 检查 filename 及 eventPath 正确性和有效性 ================''' - nmlist = eventName.split('_') - # if eventName.find('2024')<0 or len(nmlist)!=2 or len(nmlist[0])!=15 or len(nmlist[1])<11: - # return - if eventName.find('2024')<0 or len(nmlist)!=2 or len(nmlist[1])<11: + '''evtName 为一次购物事件''' + evtName = os.path.basename(eventPath) + evtList = evtName.split('_') + + '''================ 0. 检查 evtName 及 eventPath 正确性和有效性 ================''' + if evtName.find('2024')<0 and len(evtList[0])!=15: return if not os.path.isdir(eventPath): return + + if len(evtList)==1 or (len(evtList)==2 and len(evtList[1])==0): + barcode = '' + else: + barcode = evtList[-1] + + if len(evtList)==3 and evtList[-1]== evtList[-2]: + evtType = 'input' + else: + evtType = 'other' '''================ 1. 构造事件描述字典，暂定 9 items ===============''' event = {} - event['barcode'] = eventName.split('_')[1] - event['type'] = 'input' + event['barcode'] = barcode + event['type'] = evtType event['filepath'] = eventPath event['back_imgpaths'] = [] event['front_imgpaths'] = [] @@ -120,7 +117,8 @@ def creat_shopping_event(eventPath, subimgPath=False): event['back_feats'] = np.empty((0, 256), dtype=np.float64) event['front_feats'] = np.empty((0, 256), dtype=np.float64) event['feats_compose'] = np.empty((0, 256), dtype=np.float64) - # event['feats_select'] = np.empty((0, 256), dtype=np.float64) + event['one2one_simi'] = None + event['feats_select'] = np.empty((0, 256), dtype=np.float64) '''================= 2. 读取 data 文件 =============================''' @@ -144,8 +142,12 @@ def creat_shopping_event(eventPath, subimgPath=False): elif CamerType == '1': event['front_boxes'] = tracking_output_boxes event['front_feats'] = tracking_output_feats - - + + if dataname.find("process.data")==0: + simiDict = read_one2one_simi(datapath) + event['one2one_simi'] = simiDict + + if len(event['back_boxes'])==0 or len(event['front_boxes'])==0: return None @@ -165,16 +167,8 @@ def creat_shopping_event(eventPath, subimgPath=False): if len(ft_feats): event['feats_select'] = ft_feats - # pickpath = os.path.join(savePath, f"{filename}.pickle") - # with open(pickpath, 'wb') as f: - # pickle.dump(event, f) - # print(f"Event: {filename}") - - # if subimgPath==False: - # eventList.append(event) - # continue - '''================ 2. 读取图像文件地址，并按照帧ID排序 =============''' + '''================ 3. 读取图像文件地址，并按照帧ID排序 =============''' frontImgs, frontFid = [], [] backImgs, backFid = [], [] for imgname in os.listdir(eventPath): @@ -194,11 +188,11 @@ def creat_shopping_event(eventPath, subimgPath=False): frontIdx = np.argsort(np.array(frontFid)) backIdx = np.argsort(np.array(backFid)) - '''2.1 生成依据帧 ID 排序的前后摄图像地址列表''' + '''3.1 生成依据帧 ID 排序的前后摄图像地址列表''' frontImgs = [frontImgs[i] for i in frontIdx] backImgs = [backImgs[i] for i in backIdx] - '''2.2 将前、后摄图像路径添加至事件字典''' + '''3.2 将前、后摄图像路径添加至事件字典''' bfid = event['back_boxes'][:, 7].astype(np.int64) @@ -209,101 +203,16 @@ def creat_shopping_event(eventPath, subimgPath=False): event['front_imgpaths'] = [frontImgs[i-1] for i in ffid] - '''================ 3. 判断当前事件有效性，并添加至事件列表 ==========''' + '''================ 4. 判断当前事件有效性，并添加至事件列表 ==========''' condt1 = len(event['back_imgpaths'])==0 or len(event['front_imgpaths'])==0 condt2 = len(event['front_feats'])==0 and len(event['back_feats'])==0 if condt1 or condt2: - print(f"Event: {eventName}, Error, condt1: {condt1}, condt2: {condt2}") + print(f"Event: {evtName}, Error, condt1: {condt1}, condt2: {condt2}") return None - - - - - '''构造放入商品事件列表，暂不处理''' - # delepath = os.path.join(basePath, 'deletedBarcode.txt') - # bcdList = read_deletedBarcode_file(delepath) - # for slist in bcdList: - # getoutFold = slist['SeqDir'].strip() - # getoutPath = os.path.join(basePath, getoutFold) - - # '''取出事件文件夹不存在，跳出循环''' - # if not os.path.exists(getoutPath) and not os.path.isdir(getoutPath): - # continue - - # ''' 生成取出事件字典 ''' - # event = {} - # event['barcode'] = slist['Deleted'].strip() - # event['type'] = 'getout' - # event['basePath'] = getoutPath return event -# def get_std_barcodeDict(bcdpath, savepath): -# ''' -# inputs: -# bcdpath: 已清洗的barcode样本图像，如果barcode下有'base'文件夹，只选用该文件夹下图像 -# (default = r'\\192.168.1.28\share\已标注数据备份\对比数据\barcode\barcode_1771') -# 功能： -# 生成并保存只有一个key值的字典 {barcode: [imgpath1, imgpath1, ...]}， -# savepath: 字典存储地址，文件名格式：barcode.pickle -# ''' - -# # savepath = r'\\192.168.1.28\share\测试_202406\contrast\std_barcodes' - -# '''读取数据集中 barcode 列表''' -# stdBarcodeList = [] -# for filename in os.listdir(bcdpath): -# filepath = os.path.join(bcdpath, filename) -# # if not os.path.isdir(filepath) or not filename.isdigit() or len(filename)<8: -# # continue -# stdBarcodeList.append(filename) - -# bcdPaths = [(barcode, os.path.join(bcdpath, barcode)) for barcode in stdBarcodeList] - -# '''遍历数据集，针对每一个barcode，生成并保存字典{barcode: [imgpath1, imgpath1, ...]}''' -# k = 0 -# errbarcodes = [] -# for barcode, bpath in bcdPaths: -# pickpath = os.path.join(savepath, f"{barcode}.pickle") -# if os.path.isfile(pickpath): -# continue - -# stdBarcodeDict = {} -# stdBarcodeDict[barcode] = [] -# for root, dirs, files in os.walk(bpath): -# imgpaths = [] -# if "base" in dirs: -# broot = os.path.join(root, "base") -# for imgname in os.listdir(broot): -# imgpath = os.path.join(broot, imgname) -# file, ext = os.path.splitext(imgpath) - -# if ext not in IMG_FORMAT: -# continue -# imgpaths.append(imgpath) - -# stdBarcodeDict[barcode].extend(imgpaths) -# break - -# else: -# for imgname in files: -# imgpath = os.path.join(root, imgname) -# _, ext = os.path.splitext(imgpath) -# if ext not in IMG_FORMAT: continue -# imgpaths.append(imgpath) -# stdBarcodeDict[barcode].extend(imgpaths) - -# pickpath = os.path.join(savepath, f"{barcode}.pickle") -# with open(pickpath, 'wb') as f: -# pickle.dump(stdBarcodeDict, f) -# print(f"Barcode: {barcode}") - -# # k += 1 -# # if k == 10: -# # break -# print(f"Len of errbarcodes: {len(errbarcodes)}") -# return def save_event_subimg(event, savepath): ''' @@ -340,131 +249,20 @@ def save_event_subimg(event, savepath): print(f"Image saved: {os.path.basename(event['filepath'])}") - -def batch_inference(imgpaths, batch): - size = len(imgpaths) - groups = [] - for i in range(0, size, batch): - end = min(batch + i, size) - groups.append(imgpaths[i: end]) - features = [] - for group in groups: - feature = featurize(group, conf.test_transform, model, conf.device) - features.append(feature) - features = np.concatenate(features, axis=0) - return features - -# def stdfeat_infer(imgPath, featPath, bcdSet=None): -# ''' -# inputs: -# imgPath: 该文件夹下的 pickle 文件格式 {barcode: [imgpath1, imgpath1, ...]} -# featPath: imgPath图像对应特征的存储地址 -# 功能: -# 对 imgPath中图像进行特征提取，生成只有一个key值的字典， -# {barcode: features}，features.shape=(nsample, 256)，并保存至 featPath 中 - -# ''' - -# # imgPath = r"\\192.168.1.28\share\测试_202406\contrast\std_barcodes" -# # featPath = r"\\192.168.1.28\share\测试_202406\contrast\std_features" -# stdBarcodeDict = {} -# stdBarcodeDict_ft16 = {} - - -# '''4处同名: (1)barcode原始图像文件夹; (2)imgPath中的 .pickle 文件名、该pickle文件中字典的key值''' - -# k = 0 -# for filename in os.listdir(imgPath): -# bcd, ext = os.path.splitext(filename) -# pkpath = os.path.join(featPath, f"{bcd}.pickle") - -# if os.path.isfile(pkpath): continue -# if bcdSet is not None and bcd not in bcdSet: -# continue - -# filepath = os.path.join(imgPath, filename) - -# stdbDict = {} -# stdbDict_ft16 = {} -# stdbDict_uint8 = {} - -# t1 = time.time() - -# try: -# with open(filepath, 'rb') as f: -# bpDict = pickle.load(f) -# for barcode, imgpaths in bpDict.items(): -# # feature = batch_inference(imgpaths, 8) #from vit distilled model of LiChen -# feature = inference_image(imgpaths, conf.test_transform, model, conf.device) -# feature /= np.linalg.norm(feature, axis=1)[:, None] - -# # float16 -# feature_ft16 = feature.astype(np.float16) -# feature_ft16 /= np.linalg.norm(feature_ft16, axis=1)[:, None] - -# # uint8, 两种策略，1) 精度损失小, 2) 计算复杂度小 -# # feature_uint8, _ = ft16_to_uint8(feature_ft16) -# feature_uint8 = (feature_ft16*128).astype(np.int8) - -# except Exception as e: -# print(f"Error accured at: {filename}, with Exception is: {e}") - -# '''================ 保存单个barcode特征 ================''' -# ##================== float32 -# stdbDict["barcode"] = barcode -# stdbDict["imgpaths"] = imgpaths -# stdbDict["feats_ft32"] = feature -# stdbDict["feats_ft16"] = feature_ft16 -# stdbDict["feats_uint8"] = feature_uint8 - -# with open(pkpath, 'wb') as f: -# pickle.dump(stdbDict, f) - -# stdBarcodeDict[barcode] = feature -# stdBarcodeDict_ft16[barcode] = feature_ft16 - -# t2 = time.time() -# print(f"Barcode: {barcode}, need time: {t2-t1:.1f} secs") -# # k += 1 -# # if k == 10: -# # break - -# ##================== float32 -# # pickpath = os.path.join(featPath, f"barcode_features_{k}.pickle") -# # with open(pickpath, 'wb') as f: -# # pickle.dump(stdBarcodeDict, f) - -# ##================== float16 -# # pickpath_ft16 = os.path.join(featPath, f"barcode_features_ft16_{k}.pickle") -# # with open(pickpath_ft16, 'wb') as f: -# # pickle.dump(stdBarcodeDict_ft16, f) - -# return - - -def contrast_performance_evaluate(resultPath): +def one2one_eval(resultPath): # stdBarcode = [p.stem for p in Path(stdFeaturePath).iterdir() if p.is_file() and p.suffix=='.pickle'] stdBarcode = [p.stem for p in Path(stdBarcodePath).iterdir() if p.is_file() and p.suffix=='.pickle'] - '''购物事件列表，该列表中的 Barcode 存在于标准的 stdBarcode 内''' - # evtList = [(p.stem, p.stem.split('_')[1]) for p in Path(eventFeatPath).iterdir() - # if p.is_file() - # and p.suffix=='.pickle' - # and len(p.stem.split('_'))==2 - # and p.stem.split('_')[1].isdigit() - # and p.stem.split('_')[1] in stdBarcode - # ] - - evtList = [(p.stem, p.stem.split('_')[1]) for p in Path(eventFeatPath).iterdir() + '''购物事件列表，该列表中的 Barcode 存在于标准的 stdBarcode 内''' + evtList = [(p.stem, p.stem.split('_')[-1]) for p in Path(eventFeatPath).iterdir() if p.is_file() - and str(p).find('240910')>0 and p.suffix=='.pickle' - and len(p.stem.split('_'))==2 - and p.stem.split('_')[1].isdigit() - and p.stem.split('_')[1] in stdBarcode + and (len(p.stem.split('_'))==2 or len(p.stem.split('_'))==3) + and p.stem.split('_')[-1].isdigit() + and p.stem.split('_')[-1] in stdBarcode ] barcodes = set([bcd for _, bcd in evtList]) @@ -612,7 +410,7 @@ def contrast_performance_evaluate(resultPath): f.write(line + '\n') - print("func: contrast_performance_evaluate(), have finished!") + print("func: one2one_eval(), have finished!") @@ -684,44 +482,16 @@ def compute_precise_recall(pickpath): plt.savefig(f'./result/{file}_pr.png') # svg, png, pdf - - -def generate_event_and_stdfeatures(): - '''=========================== 1. 生成标准特征集 ========================''' - '''1.1 提取 stdSamplePath 中样本地址，生成字典{barcode: [imgpath1, imgpath1, ...]} - 并存储为 pickle 文件，barcode.pickle''' - # get_std_barcodeDict(stdSamplePath, stdBarcodePath) - # print("standard imgpath have extracted and saved") - - - '''1.2 特征提取，并保存至文件夹 stdFeaturePath 中，也可在运行过程中根据 barcodes 交集执行''' - # stdfeat_infer(stdBarcodePath, stdFeaturePath, bcdSet=None) - # print("standard features have generated!") - - - '''=========================== 2. 提取并存储事件特征 ========================''' - eventDatePath = [r'\\192.168.1.28\share\测试_202406\0910\images', - # r'\\192.168.1.28\share\测试_202406\0723\0723_1', - # r'\\192.168.1.28\share\测试_202406\0723\0723_2', - # r'\\192.168.1.28\share\测试_202406\0723\0723_3', - # r'\\192.168.1.28\share\测试_202406\0722\0722_01', - # r'\\192.168.1.28\share\测试_202406\0722\0722_02' - # r'\\192.168.1.28\share\测试_202406\0719\719_3', - # r'\\192.168.1.28\share\测试_202406\0716\0716_1', - # r'\\192.168.1.28\share\测试_202406\0716\0716_2', - # r'\\192.168.1.28\share\测试_202406\0716\0716_3', - # r'\\192.168.1.28\share\测试_202406\0712\0712_1', # 无帧图像 - # r'\\192.168.1.28\share\测试_202406\0712\0712_2', # 无帧图像 - ] +def gen_eventdict(eventDatePath, saveimg=True): eventList = [] # k = 0 for datePath in eventDatePath: for eventName in os.listdir(datePath): + pickpath = os.path.join(eventFeatPath, f"{eventName}.pickle") if os.path.isfile(pickpath): continue - eventPath = os.path.join(datePath, eventName) eventDict = creat_shopping_event(eventPath) @@ -736,52 +506,61 @@ def generate_event_and_stdfeatures(): # break ## 保存轨迹中 boxes 子图 + if not saveimg: + return for event in eventList: basename = os.path.basename(event['filepath']) savepath = os.path.join(subimgPath, basename) if not os.path.exists(savepath): os.makedirs(savepath) save_event_subimg(event, savepath) + + + + + +def test_one2one(): + eventDatePath = [r'\\192.168.1.28\share\测试_202406\1101\images', + # r'\\192.168.1.28\share\测试_202406\0910\images', + # r'\\192.168.1.28\share\测试_202406\0723\0723_1', + # r'\\192.168.1.28\share\测试_202406\0723\0723_2', + # r'\\192.168.1.28\share\测试_202406\0723\0723_3', + # r'\\192.168.1.28\share\测试_202406\0722\0722_01', + # r'\\192.168.1.28\share\测试_202406\0722\0722_02' + # r'\\192.168.1.28\share\测试_202406\0719\719_3', + # r'\\192.168.1.28\share\测试_202406\0716\0716_1', + # r'\\192.168.1.28\share\测试_202406\0716\0716_2', + # r'\\192.168.1.28\share\测试_202406\0716\0716_3', + # r'\\192.168.1.28\share\测试_202406\0712\0712_1', # 无帧图像 + # r'\\192.168.1.28\share\测试_202406\0712\0712_2', # 无帧图像 + ] + bcdList = [] + for evtpath in eventDatePath: + for evtname in os.listdir(evtpath): + evt = evtname.split('_') + if len(evt)>=2 and evt[-1].isdigit() and len(evt[-1])>=10: + bcdList.append(evt[-1]) + + bcdSet = set(bcdList) - print("eventList have generated and features have saved!") - -def int8_to_ft16(arr_uint8, amin, amax): - arr_ft16 = (arr_uint8 / 255 * (amax-amin) + amin).astype(np.float16) - - return arr_ft16 - -def ft16_to_uint8(arr_ft16): - # pickpath = r"\\192.168.1.28\share\测试_202406\contrast\std_features_ft32vsft16\6902265587712_ft16.pickle" - - # with open(pickpath, 'rb') as f: - # edict = pickle.load(f) - # arr_ft16 = edict['feats'] - - amin = np.min(arr_ft16) - amax = np.max(arr_ft16) - arr_ft255 = (arr_ft16 - amin) * 255 / (amax-amin) - arr_uint8 = arr_ft255.astype(np.uint8) - arr_ft16_ = int8_to_ft16(arr_uint8, amin, amax) + + '''==== 1. 生成标准特征集, 只需运行一次 ===============''' + genfeatures(stdSamplePath, stdBarcodePath, stdFeaturePath, bcdSet) + print("stdFeats have generated and saved!") - arrDistNorm = np.linalg.norm(arr_ft16_ - arr_ft16) / arr_ft16_.size - - - return arr_uint8, arr_ft16_ + '''==== 2. 生成事件字典, 只需运行一次 ===============''' + + gen_eventdict(eventDatePath) + print("eventList have generated and saved!") - - - - -def main(): - # generate_event_and_stdfeatures() - - contrast_performance_evaluate(resultPath) + '''==== 3. 1:1性能评估 ===============''' + one2one_eval(resultPath) for filename in os.listdir(resultPath): if filename.find('.pickle') < 0: continue if filename.find('0911') < 0: continue @@ -789,63 +568,29 @@ def main(): compute_precise_recall(pickpath) -# def main_std(): -# std_sample_path = r"\\192.168.1.28\share\已标注数据备份\对比数据\barcode\barcode_500_2192_已清洗" -# std_barcode_path = r"\\192.168.1.28\share\测试_202406\contrast\std_barcodes_2192" -# std_feature_path = r"\\192.168.1.28\share\测试_202406\contrast\std_features_2192_ft32vsft16" - - -# get_std_barcodeDict(std_sample_path, std_barcode_path) -# stdfeat_infer(std_barcode_path, std_feature_path, bcdSet=None) - -# # fileList = [] -# # for filename in os.listdir(std_barcode_path): -# # filepath = os.path.join(std_barcode_path, filename) -# # with open(filepath, 'rb') as f: -# # bpDict = pickle.load(f) - -# # for v in bpDict.values(): -# # fileList.append(len(v)) -# # print("done") if __name__ == '__main__': - main() - # main_std() + ''' + 共6个地址： + (1) stdSamplePath: 用于生成比对标准特征集的原始图像地址 + (2) stdBarcodePath: 比对标准特征集原始图像地址的pickle文件存储，{barcode: [imgpath1, imgpath1, ...]} + (3) stdFeaturePath: 比对标准特征集特征存储地址 + (4) eventFeatPath: 用于1:1比对的购物事件特征存储地址、对应子图存储地址 + (5) subimgPath: 1:1比对购物事件轨迹、标准barcode所对应的 subimgs 存储地址 + (6) resultPath: 1:1比对结果存储地址 + ''' + + stdSamplePath = r"\\192.168.1.28\share\已标注数据备份\对比数据\barcode\barcode_500_1979_已清洗" + stdBarcodePath = r"\\192.168.1.28\share\测试_202406\contrast\std_barcodes_2192" + stdFeaturePath = r"\\192.168.1.28\share\测试_202406\contrast\std_features_ft32" + eventFeatPath = r"\\192.168.1.28\share\测试_202406\contrast\events" + subimgPath = r'\\192.168.1.28\share\测试_202406\contrast\subimgs' + resultPath = r"D:\DetectTracking\contrast\result\pickle" + if not os.path.exists(resultPath): + os.makedirs(resultPath) + + test_one2one() - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - \ No newline at end of file diff --git a/time_devide.py b/time_devide.py index e843a7e..28d4d65 100644 --- a/time_devide.py +++ b/time_devide.py @@ -17,7 +17,6 @@ import copy import matplotlib.pyplot as plt from imgs_inference import run_yolo - from event_time_specify import devide_motion_state#, state_measure from tracking.utils.read_data import read_seneor diff --git a/tracking/utils/__pycache__/plotting.cpython-39.pyc b/tracking/utils/__pycache__/plotting.cpython-39.pyc index ab513f6..a0008c1 100644 Binary files a/tracking/utils/__pycache__/plotting.cpython-39.pyc and b/tracking/utils/__pycache__/plotting.cpython-39.pyc differ diff --git a/tracking/utils/__pycache__/read_data.cpython-39.pyc b/tracking/utils/__pycache__/read_data.cpython-39.pyc index a35e79e..3fc17b0 100644 Binary files a/tracking/utils/__pycache__/read_data.cpython-39.pyc and b/tracking/utils/__pycache__/read_data.cpython-39.pyc differ diff --git a/tracking/utils/plotting.py b/tracking/utils/plotting.py index 50a6dc1..9eb4c78 100644 --- a/tracking/utils/plotting.py +++ b/tracking/utils/plotting.py @@ -285,6 +285,38 @@ def boxing_img(det, img, line_width=3): return imgx +def array2list(bboxes): + track_fids = np.unique(bboxes[:, 7].astype(int)) + track_fids.sort() + + lboxes = [] + for f_id in track_fids: + # print(f"The ID is: {t_id}") + idx = np.where(bboxes[:, 7] == f_id)[0] + box = bboxes[idx, :] + lboxes.append(box) + + assert len(set(box[:, 4])) == len(box), "Please check!!!" + + return lboxes + + +def get_subimgs(imgs, tracks, scale=2): + bboxes = [] + if len(tracks): + bboxes = array2list(tracks) + + subimgs = [] + for i, boxes in enumerate(bboxes): + fid = int(boxes[0, 7]) + + for *xyxy, tid, conf, cls, fid, bid in boxes: + pt2 = [p/scale for p in xyxy] + x1, y1, x2, y2 = (int(pt2[0]), int(pt2[1])), (int(pt2[2]), int(pt2[3])) + subimgs.append((int(fid), int(bid), imgs[fid-1][y1:y2, x1:x2])) + + return subimgs + def draw_tracking_boxes(imgs, tracks, scale=2): '''需要确保 imgs 覆盖tracks中的帧ID数 tracks: [x1, y1, x2, y2, track_id, score, cls, frame_index, box_index] @@ -295,27 +327,15 @@ def draw_tracking_boxes(imgs, tracks, scale=2): ''' - def array2list(bboxes): - track_fids = np.unique(bboxes[:, 7].astype(int)) - track_fids.sort() - - lboxes = [] - for f_id in track_fids: - # print(f"The ID is: {t_id}") - idx = np.where(bboxes[:, 7] == f_id)[0] - box = bboxes[idx, :] - lboxes.append(box) - - assert len(set(box[:, 4])) == len(box), "Please check!!!" - - return lboxes - - bboxes = array2list(tracks) + + bboxes = [] + if len(tracks): + bboxes = array2list(tracks) # if len(bboxes)!=len(imgs): # return False, imgs - subimgs = [] + annimgs = [] for i, boxes in enumerate(bboxes): fid = int(boxes[0, 7]) annotator = Annotator(imgs[fid-1].copy()) @@ -331,11 +351,11 @@ def draw_tracking_boxes(imgs, tracks, scale=2): pt2 = [p/scale for p in xyxy] annotator.box_label(pt2, label, color=color) - + img = annotator.result() - subimgs.append((fid, img)) + annimgs.append((int(fid), img)) - return subimgs + return annimgs diff --git a/tracking/utils/read_data.py b/tracking/utils/read_data.py index 663890d..a733fe6 100644 --- a/tracking/utils/read_data.py +++ b/tracking/utils/read_data.py @@ -37,6 +37,9 @@ def find_samebox_in_array(arr, target): def extract_data(datapath): + ''' + 0/1_track.data 数据读取 + ''' bboxes, ffeats = [], [] trackerboxes = np.empty((0, 9), dtype=np.float64) @@ -147,8 +150,15 @@ def extract_data(datapath): return bboxes, ffeats, trackerboxes, tracker_feat_dict, trackingboxes, tracking_feat_dict def read_tracking_output(filepath): + ''' + 0/1_tracking_output.data 数据读取 + ''' + boxes = [] feats = [] + if not os.path.isfile(filepath): + return np.array(boxes), np.array(feats) + with open(filepath, 'r', encoding='utf-8') as file: for line in file: line = line.strip() # 去除行尾的换行符和可能的空白字符 @@ -176,7 +186,6 @@ def read_deletedBarcode_file(filePath): split_flag, all_list = False, [] dict, barcode_list, similarity_list = {}, [], [] - clean_lines = [line.strip().replace("'", '').replace('"', '') for line in lines] for i, line in enumerate(clean_lines): @@ -199,6 +208,7 @@ def read_deletedBarcode_file(filePath): if label == 'SeqDir': dict['SeqDir'] = value + dict['filetype'] = "deletedBarcode" if label == 'Deleted': dict['Deleted'] = value if label == 'List': @@ -259,15 +269,19 @@ def read_returnGoods_file(filePath): if label == 'SeqDir': dict['SeqDir'] = value dict['Deleted'] = value.split('_')[-1] + dict['filetype'] = "returnGoods" if label == 'List': split_flag = True continue if split_flag: + bcd = label.split('_')[-1] + # event_list.append(label + '_' + bcd) event_list.append(label) - barcode_list.append(label.split('_')[-1]) + barcode_list.append(bcd) similarity_list.append(value.split(',')[0]) type_list.append(value.split('=')[-1]) + if len(barcode_list): dict['barcode'] = barcode_list if len(similarity_list): dict['similarity'] = similarity_list if len(event_list): dict['event'] = event_list @@ -279,33 +293,51 @@ def read_returnGoods_file(filePath): + +# ============================================================================= +# def read_seneor(filepath): +# WeightDict = OrderedDict() +# with open(filepath, 'r', encoding='utf-8') as f: +# lines = f.readlines() +# for i, line in enumerate(lines): +# line = line.strip() +# +# keyword = line.split(':')[0] +# value = line.split(':')[1] +# +# vdata = [float(s) for s in value.split(',') if len(s)] +# +# WeightDict[keyword] = vdata[-1] +# +# return WeightDict +# ============================================================================= + +def read_one2one_simi(filePath): - - - - - - - - - - - -def read_seneor(filepath): - WeightDict = OrderedDict() - with open(filepath, 'r', encoding='utf-8') as f: + SimiDict = {} + with open(filePath, 'r', encoding='utf-8') as f: lines = f.readlines() + flag = False for i, line in enumerate(lines): line = line.strip() + if line.find('barcode:')<0 and not flag: + continue + if line.find('barcode:')==0 : + flag = True + continue - keyword = line.split(':')[0] - value = line.split(':')[1] - - vdata = [float(s) for s in value.split(',') if len(s)] - - WeightDict[keyword] = vdata[-1] - - return WeightDict + # if line.endswith(','): + # line = line[:-1] + if flag: + barcode = line.split(',')[0].strip() + value = line.split(',')[1].split(':')[1].strip() + SimiDict[barcode] = float(value) + + if flag and not line: + flag = False + + return SimiDict + def read_weight_timeConsuming(filePth): @@ -362,15 +394,14 @@ def plot_sensor_curve(WeightDict, SensorDict, ProcessTimeDict): nw = len(wdata) assert(nw) >= 8, "The num of weight data is less than 8!" - i1, i2 = 0, 7 - while i2 < nw: - data = wdata[i1:(i2+1)] - max(data) - min(data) - - if i2<7: - i1 = 0 - else: - i1 = i2-windth + # i1, i2 = 0, 7 + # while i2 < nw: + # data = wdata[i1:(i2+1)] + # max(data) - min(data) + # if i2<7: + # i1 = 0 + # else: + # i1 = i2-windth min_t = min(wtime + stime) wtime = [t-min_t for t in wtime] @@ -405,15 +436,12 @@ def plot_sensor_curve(WeightDict, SensorDict, ProcessTimeDict): -def main(file_path): +def test_process(file_path): WeightDict, SensorDict, ProcessTimeDict = read_weight_timeConsuming(file_path) plot_sensor_curve(WeightDict, SensorDict, ProcessTimeDict) - - - - -if __name__ == "__main__": + +def main(): files_path = r'\\192.168.1.28\share\测试_202406\0814\0814\20240814-102227-62264578-a720-4eb9-b95e-cb8be009aa98_null' k = 0 for filename in os.listdir(files_path): @@ -424,42 +452,21 @@ if __name__ == "__main__": extract_data(file_path) if os.path.isfile(file_path) and filename.find("process.data")>=0: - main(file_path) + test_process(file_path) k += 1 if k == 1: break - - - - # print("Done") - - - - - - - - - - - - - - - - - - - - - - - - - - + +def main1(): + fpath = r'\\192.168.1.28\share\测试_202406\1101\images\20241101-140456-44dc75b5-c406-4cb2-8317-c4660bb727a3_6922130101355_6922130101355\process.data' + simidct = read_one2one_simi(fpath) + print(simidct) + +if __name__ == "__main__": + # main() + main1() diff --git a/说明文档.txt b/说明文档.txt index 90b9d34..00b3ee9 100644 --- a/说明文档.txt +++ b/说明文档.txt @@ -144,15 +144,124 @@ precision_compare(filepath, savepath) 读取 deletedBarcode.txt 和 deletedBarcodeTest.txt 中的数据，进行相似度比较 - + + genfeats.py + get_std_barcodeDict(bcdpath, savepath) + 功能: 生成并保存只有一个key值的字典 {barcode: [imgpath1, imgpath1, ...]} + + stdfeat_infer(imgPath, featPath, bcdSet=None) + 功能: 对 imgPath 中图像进行特征提取，生成只有一个key值的字典。 + {barcode: features}，features.shape=(nsample, 256)，并保存至 featPath 中 + one2n_contrast.py - 1:n 比对，读取 deletedBarcode.txt，实现现场测试评估。 - main(): - 循环读取不同文件夹中的 deletedBarcode.txt，合并评估。 - main1(): - 指定deletedBarcode.txt进行1:n性能评估 + test_one2n() + 1:n 现场测试性能评估，输出 PR 曲线 + 兼容 2 种 txt 文件格式：returnGoods.txt, deletedBarcode.txt, + 分别对应不同的文件读取函数： + - read_deletedBarcode_file() + - read_returnGoods_file() + + one2n_return(all_list) + 输入：从returnGoods.txt读取的数据 + 输出： + corrpairs：(取出事件, 正确匹配的放入事件) + errpairs：(取出事件, 放入事件, 错误匹配的放入事件) + corr_similarity: (正确匹配时的相似度) + err_similarity: (错误匹配时的相似度) + + + one2n_deleted(all_list) + 输入: 从deletedBarcode.txt读取的数据 + 输出： + corrpairs：(取出事件, 取出的barcode) + errpairs：(取出事件, 取出的barcode, 错误匹配的barcode) + corr_similarity: (正确匹配时的相似度) + err_similarity: (错误匹配时的相似度) + + save_tracking_imgpairs(pairs, savepath) + 输入： + pairs：匹配时间对，len(2)=2 or 3, 对应正确匹配与错误匹配 + savepath：结果保存地址，其中图像文件的命名为：取出事件 + 放入事件 + 错误匹配时间 + 子函数 get_event_path(), 扫码放入的对齐名 + 对于 returnGoods.txt, 放入事件的事件名和对应的文件夹名不一致，需要对齐 + + test_rpath_deleted() + 功能： + 针对 eletedBarcode.txt 格式的 1:n 数据结果文件 + 获得 1:n 情况下正确或匹配事件对（取出事件、放入事件、错误匹配事件） + 匹配事件分析, 实现函数：save_tracking_imgpairs() + 重要参数： + del_barcode_file: + basepath: 对应事件路径 + savepath: 存储路径, 是函数 save_tracking_imgpairs() 的输入 + saveimgs: Ture, False, 是否保存错误匹配的事件对 + + get_contrast_paths() + 针对 eletedBarcode.txt 格式的 1:n 数据结果文件,返回三元时间元组（getoutpath, inputpath, errorpath） + + test_rpath_return() + 针对 returnGoods.txt 格式 1:n 数据文件，不需要调用函数get_contrast_paths() + 获得 1:n 情况下正确或匹配事件对（取出事件、放入事件、错误匹配事件） + 匹配事件分析, 实现函数：save_tracking_imgpairs() + + + one2one_contrast.py + 共6个地址： + (1) stdSamplePath: 用于生成比对标准特征集的原始图像地址 + (2) stdBarcodePath: 比对标准特征集原始图像地址的pickle文件存储，{barcode: [imgpath1, imgpath1, ...]} + (3) stdFeaturePath: 比对标准特征集特征存储地址 + (4) eventFeatPath: 用于1:1比对的购物事件特征存储地址、对应子图存储地址 + (5) subimgPath: 1:1比对购物事件轨迹、标准barcode所对应的 subimgs 存储地址 + (6) resultPath: 1:1比对结果存储地址 + + (1), (2), (3): 保存标准特征集向量，只需运行一次 + (4): 保存测试的事件字典，只需运行一次 + + + test_one2one() + (1) 生成标准特征集, 只需运行一次 + genfeatures() + (2) 生成事件字典, 只需运行一次 + gen_eventdict(eventDatePath, saveimg) + 参数: + eventDatePath: 事件集列表，其中每个元素均为事件的集合; + saveimg: 是否保存事件子图 + + (3) 1:1性能评估 + (4) 计算PR曲线 + + + + creat_shopping_event(eventPath, subimgPath=False) + 构造一次购物事件字典, 共12个关键字。 + save_event_subimg(event, savepath) + 保存一次购物事件的子图 + + + one2one_eval() + + + + compute_precise_recall() + + + + + int8_to_ft16() + + + ft16_to_uint8() + + + + + + + + + one2one_onsite.py 现场试验输出数据的 1:1 性能评估； 适用于202410前数据保存版本的，需调用 OneToOneCompare.txt @@ -161,11 +270,13 @@ std_sample_path：图像样本的存储地址 std_barcode_path：对 std_sample_path 中文件列表进行遍历，形成{barcode: 图像样本地址}形式字典并进行存储 std_feature_path：调用 inference_image(), 对每一个barcode，生成字典并进行存储 - - + + + genfeats.py genfeatures(imgpath, bcdpath, featpath) - 功能：生成标准特征向量 + 功能：生成标准特征向量的字典, 并保存为: barcode.pickle + keys: barcode, imgpaths, feats_ft32, feats_ft16, feats_uint8 参数： (1) imgpath：图像样本的存储地址 (2) bcdpath：对 imgpath 中文件列表进行遍历，形成{barcode: 图像样本地址}形式字典并进行存储