{'acc': [0.082039911341244262, 0.11086474501108648, 0.12176724137931035, 0.16189427312775331, 0.18847006651884701, 0.19396551724137931, 0.21585903096829218, 0.25720620842572062, 0.28713968961175423, 0.29490022179557057, 0.31818181818181818, 0.34478935705055946, 0.35144124175122465, 0.41241685150732221, 0.4212860311742897, 0.44567627494456763, 0.48447893583060897, 0.49002217294900224, 0.50862068965517238, 0.54767184022260607, 0.57317073177339761, 0.55986696243814782, 0.59201773822704074, 0.60532150789269323, 0.64523281609668437, 0.63325991179580732, 0.65742793804790389, 0.68070953450023208, 0.67073170744923427, 0.70066518847006654, 0.71286031042128606, 0.75942350345810339, 0.73392461203947301, 0.75498891352549891, 0.77494456775965548, 0.74390243889222918, 0.78048780474588775, 0.80487804891264891, 0.79379157414721813, 0.81707317059954621, 0.82372505556453357, 0.82483370275032231, 0.84051724137931039, 0.84368070966652919, 0.83592017751575309, 0.86252771605409173, 0.85033259423503327, 0.87114537444933926, 0.88913525485675249, 0.88802660753880269, 0.89135254988913526, 0.89911308203991136, 0.90576496674057649, 0.89800443472196156, 0.91241685144124174, 0.91463414634146345, 0.89467849223946783, 0.91352549875919142, 0.89356984478935697, 0.92572062084257212, 0.92461197339246115, 0.93569844789356982, 0.94124168514412421, 0.93569844776140876, 0.92349137931034486, 0.93791574266163047, 0.94345897991218486, 0.94678492239467849, 0.94567627494456763, 0.94678492226251743, 0.96475770925110127, 0.95898004421373695, 0.9567627494456763, 0.9567627494456763, 0.96452328159645229, 0.96563192891440208, 0.94789356984478934, 0.96230598669623058, 0.96563192891440208, 0.96230598669623058], 'loss': [4.8589180504403462, 3.4203788557496675, 2.8835118310204866, 2.6010641269221706, 2.4316977254567282, 2.3129776222952483, 2.2217668040208354, 2.1504259347387005, 2.0668677474865627, 1.9932332916428932, 1.9169470843613279, 1.9148425765153838, 1.8047837352012583, 1.7368667717783519, 1.6526634272873533, 1.6127761980382407, 1.5482007730297926, 1.5263558002374653, 1.4652635187938297, 1.3814672428594197, 1.3420182894708841, 1.3430276191948258, 1.2525881198451683, 1.2027667828251147, 1.1598500621292385, 1.1529914206345175, 1.0540501059026781, 1.0455950376992744, 1.0196153390698317, 0.95284692596173337, 0.94675583849989386, 0.88159280962531683, 0.82917687766039183, 0.83506970183548013, 0.77768954324087913, 0.79681974794806498, 0.73832937539813259, 0.67815640562125157, 0.69148718808548415, 0.65336706725562488, 0.61344992374369411, 0.60935167846024163, 0.57461268737398341, 0.56367421176639732, 0.55852250473990939, 0.5207265922737756, 0.51153987269443846, 0.49326585856828398, 0.43728730842438085, 0.42780109195910115, 0.41610263400358, 0.3941102498882097, 0.39578512733897192, 0.40400583159897119, 0.35189808604458217, 0.36417675718764242, 0.36915831000207533, 0.33362168152950822, 0.34438615204754003, 0.29705559070781701, 0.28881390022729292, 0.28417850175083609, 0.26296883937128368, 0.27060881600675984, 0.28997485596558142, 0.25369702401816713, 0.23084514830963573, 0.24530790369552943, 0.22929098224164113, 0.21566672864351463, 0.19668946132917237, 0.20452538674527948, 0.21237614618701048, 0.20793769384699226, 0.18135617736173576, 0.17742964086802201, 0.20119789318737064, 0.17821562935302898, 0.16810262351897762, 0.19411716179017746], 'mean_squared_logarithmic_error': [0.067155109995154214, 0.056938803827022502, 0.052279308438301086, 0.049330060924136693, 0.046778141122369173, 0.045914003175908123, 0.044428862303101543, 0.042930684744188367, 0.041632553426230824, 0.040952282897847192, 0.039801385055426221, 0.039307781059435359, 0.037599997425621208, 0.036534821453551761, 0.035163268612123648, 0.034085437258965692, 0.03303880610001457, 0.032407766137842062, 0.03127461447027223, 0.029379273861844895, 0.028884316016062929, 0.028991732469650436, 0.027004117379481274, 0.026181382955177926, 0.025276419444385495, 0.025091812900772177, 0.02303950196986981, 0.022878665658758908, 0.022200165122350939, 0.020718952657411211, 0.020870027357419156, 0.01921273333468617, 0.01841343736106699, 0.018206229553188295, 0.017145847088085309, 0.017792269273634233, 0.016293431322468226, 0.014863567620912307, 0.015419038161304997, 0.014260596672110177, 0.013371800491689578, 0.013311770067296246, 0.012703327767165571, 0.012309849753711546, 0.012429454068585141, 0.01141882481718407, 0.011385613005451378, 0.010906013434482041, 0.0095637164671312676, 0.0092805552062993572, 0.0091338233119847376, 0.008497708120606344, 0.0084578627544948763, 0.0088139912381999513, 0.0075054856331114497, 0.0077915503085898589, 0.0082048912958021039, 0.0072145944506656831, 0.0077487496646769559, 0.006334182838966116, 0.0062645845132737431, 0.0060215846907983464, 0.0055124084583944135, 0.0056709239874737222, 0.0063721403110258536, 0.0054449146270685875, 0.0048503348141280883, 0.0051173288870743263, 0.0048309970779257709, 0.0044627294249981308, 0.0038777457905055275, 0.0042469638984179549, 0.0042960015011996762, 0.0042967605198054116, 0.0036587371344279558, 0.0035149582771134219, 0.0042304032773374193, 0.0036889180471860452, 0.0033227385717656817, 0.0038942266921585056], 'val_mean_squared_logarithmic_error': [0.060751424313516683, 0.0533270184983171, 0.049728772906532839, 0.048914366271635909, 0.046850733235974003, 0.044953461166496025, 0.043729587811191968, 0.04252847995270382, 0.041243523375818839, 0.040028925200391502, 0.038554194331697773, 0.037809701045838799, 0.037915107589669345, 0.035035939783915185, 0.03482408122781111, 0.033248652408762673, 0.033559324513055266, 0.031550639757097695, 0.031135872241828236, 0.029354261692836385, 0.028735808862947309, 0.028702125073040933, 0.027542491842003462, 0.02625314921900597, 0.023600105287098303, 0.023476102052797498, 0.022010788259544552, 0.022128420177756285, 0.021988516756046374, 0.019778701776180192, 0.020103275278240375, 0.019942699508233505, 0.017579136668248081, 0.018189489608114284, 0.016595523903546999, 0.016254307235489929, 0.015109785338925681, 0.015082554239160205, 0.014973387741659275, 0.012984959313650089, 0.013269283059166699, 0.012524941545847117, 0.012215877843900953, 0.011729102032444958, 0.011552947795353086, 0.010908642833321427, 0.011255587195097871, 0.01101404058431046, 0.009937883836904875, 0.0098406750917385127, 0.009189145272998283, 0.0085277436554076734, 0.0078902151864104625, 0.0085402892245818127, 0.0073543914605113791, 0.007764689936127076, 0.0070965719830550405, 0.007528345421175503, 0.0068384658198332839, 0.0061426392287643678, 0.0065073611953258594, 0.0055947513949382065, 0.0056977603572137868, 0.0064400739435048699, 0.0056373993189852614, 0.0054127773842536859, 0.0051276340142115458, 0.0045415748818312873, 0.0056865329207840092, 0.0047467035513620061, 0.0045701322577348571, 0.0043490428726360233, 0.0039303467928807762, 0.0046190995505020777, 0.003608110410361623, 0.0041763961455576169, 0.0034990403987054286, 0.0037707993884606001, 0.0028460693928700131, 0.0032649316090342904], 'val_acc': [0.096452328192685496, 0.1374722838467875, 0.15964523288204507, 0.15742793798182333, 0.18403547671840353, 0.21840354767184036, 0.25166297124124681, 0.24944567627494457, 0.28048780487804881, 0.31929046566496933, 0.3503325943011138, 0.37139689585322022, 0.36585365866874642, 0.43015521070909607, 0.43015521064301554, 0.47671840354767187, 0.46341463421242202, 0.50332594235033257, 0.51662971175166295, 0.56208425720620847, 0.57427937915742788, 0.56430155223859124, 0.590909091041252, 0.61640798226164084, 0.68514412403635339, 0.65631929046563198, 0.68957871383679681, 0.67849223933568814, 0.69290465618712938, 0.73392461210555349, 0.71286031042128606, 0.71618625277161863, 0.76940133024477908, 0.75831485574367041, 0.78824833716098586, 0.78492239481065329, 0.81596452341375758, 0.80266075374810497, 0.80931263871309234, 0.83592017738359203, 0.83370288235120926, 0.84257206221641823, 0.84700665175253964, 0.8658536584044243, 0.85033259423503327, 0.86252771631841385, 0.86141906860398088, 0.8580931262536482, 0
没有合适的资源?快使用搜索试试~ 我知道了~
温馨提示
基于双目的人体姿态匹配与识别C++源码+项目说明(毕业设计项目).zip 实现基于双目的十个动作识别 ##运行说明 程序都是用vs2015+opencv2.4.9.opencv已打包在内 在matchAndRecognition里面训练文件夹是我整理好的图片数据 Script文件夹是python文件,里面HumanActionRecognitionTrain.py是整个的训练文件,HumanActionRecognitionPredictAll.py是python全部图片的识别文件。Subm里面有一个全部文件的识别结果。 Out文件夹是c++每一张图片的识别结果。 主要程序在main文件夹里面。里面MODE改为MATCH问匹配,给为RECOGNITION为识别。 改下面这句话就可了。 define MODE RECOGNITION //两种模式,MATCH为选择去匹配获取深度图,RECOGNITION为识别 cnn1.dumped是c++识别使用的训练好的模型和权重文件。 whole_model.h5是python识别使用的训练好的模型和权重文件。
资源推荐
资源详情
资源评论

























收起资源包目录


















































共 42 条
- 1
资源评论

- Lottomr2025-05-24终于找到了超赞的宝藏资源,果断冲冲冲,支持!

onnx
- 粉丝: 1w+
上传资源 快速赚钱
我的内容管理 展开
我的资源 快来上传第一个资源
我的收益
登录查看自己的收益我的积分 登录查看自己的积分
我的C币 登录后查看C币余额
我的收藏
我的下载
下载帮助


最新资源
- 大学毕业论文---基于java的航空票务系统的设计与实现(1).doc
- 软件产品代理合同书(1).docx
- 新环境下的计算机网络信息安全及其防火墙技术应用(1)(1).docx
- 嵌入式实操作系统uCOS分析讲课文档(1).ppt
- 软件实习报告(3篇)(1).docx
- 施工组织设平坏准锹100429A1GCWG施工组织设计交底aspanclass=(1).docx
- 电大C语言程序设计第3章流程控制语句(1).ppt
- 外文翻译--PLC简介(1)(1).doc
- 促进深度学习的教学过程和策略研究(1).docx
- MATLAB改进欧拉法与四阶龙格-库塔求解一阶常微分方程(1).doc
- 基于51单片机的多功能计算器设计课程设计(1)(1).doc
- 城市燃气GIS中清管模块的设计与应用(1).docx
- 互联网+背景下英语专业大学生网络资源使用情况的调查研究(1).docx
- 互联网商业合作协议书(1).docx
- 科脉商业管理软件说明书(1).doc
- 基于互联网+的大学生创业研究(1).docx
资源上传下载、课程学习等过程中有任何疑问或建议,欢迎提出宝贵意见哦~我们会及时处理!
点击此处反馈



安全验证
文档复制为VIP权益,开通VIP直接复制
