DL之LSTM之UvP：基于TF利用LSTM基于DIY时间训练1200个数据预测后200个数据状态

小辣椒
小辣椒 2022-09-19 16:23:51 50910
分类专栏： 资讯

DL之LSTM之UvP：基于TF利用LSTM基于DIY时间训练1200个数据预测后200个数据状态

目录

输出结果

设计思路

训练记录全过程

输出结果

设计思路

训练记录全过程

  1. INFO:tensorflow:loss = 0.496935, step = 1
  2. INFO:tensorflow:global_step/sec: 7.44562
  3. INFO:tensorflow:loss = 0.0289763, step = 101 (13.432 sec)
  4. INFO:tensorflow:global_step/sec: 6.42037
  5. INFO:tensorflow:loss = 0.0200101, step = 201 (15.575 sec)
  6. INFO:tensorflow:global_step/sec: 5.56483
  7. INFO:tensorflow:loss = 0.0195363, step = 301 (17.971 sec)
  8. INFO:tensorflow:global_step/sec: 5.30867
  9. INFO:tensorflow:loss = 0.0141311, step = 401 (18.836 sec)
  10. INFO:tensorflow:global_step/sec: 5.41209
  11. INFO:tensorflow:loss = 0.014299, step = 501 (18.479 sec)
  12. INFO:tensorflow:global_step/sec: 4.92611
  13. INFO:tensorflow:loss = 0.0155927, step = 601 (20.298 sec)
  14. INFO:tensorflow:global_step/sec: 5.11247
  15. INFO:tensorflow:loss = 0.0130529, step = 701 (19.563 sec)
  16. INFO:tensorflow:global_step/sec: 4.71378
  17. INFO:tensorflow:loss = 0.0131998, step = 801 (21.211 sec)
  18. INFO:tensorflow:global_step/sec: 4.71155
  19. INFO:tensorflow:loss = 0.0143074, step = 901 (21.224 sec)
  20. INFO:tensorflow:global_step/sec: 5.07501
  21. INFO:tensorflow:loss = 0.0160928, step = 1001 (19.704 sec)
  22. INFO:tensorflow:global_step/sec: 4.85088
  23. INFO:tensorflow:loss = 0.00991265, step = 1101 (20.615 sec)
  24. INFO:tensorflow:global_step/sec: 4.93806
  25. INFO:tensorflow:loss = 0.0125441, step = 1201 (20.251 sec)
  26. INFO:tensorflow:global_step/sec: 5.40711
  27. INFO:tensorflow:loss = 0.0127672, step = 1301 (18.497 sec)
  28. INFO:tensorflow:global_step/sec: 4.92733
  29. INFO:tensorflow:loss = 0.0109727, step = 1401 (20.294 sec)
  30. INFO:tensorflow:global_step/sec: 4.42869
  31. INFO:tensorflow:loss = 0.0138402, step = 1501 (22.578 sec)
  32. INFO:tensorflow:global_step/sec: 4.902
  33. INFO:tensorflow:loss = 0.00974652, step = 1601 (20.401 sec)
  34. INFO:tensorflow:global_step/sec: 5.87293
  35. INFO:tensorflow:loss = 0.010258, step = 1701 (17.029 sec)
  36. INFO:tensorflow:global_step/sec: 5.88471
  37. INFO:tensorflow:loss = 0.0119193, step = 1801 (16.991 sec)
  38. INFO:tensorflow:global_step/sec: 5.89885
  39. INFO:tensorflow:loss = 0.0130985, step = 1901 (16.951 sec)
  40. INFO:tensorflow:Saving checkpoints for 2000 into C:\Users\----------\AppData\Local\Temp\tmpihfq7_j1\model.ckpt.
  41. INFO:tensorflow:Loss for final step: 0.0151946.
  42. INFO:tensorflow:Starting evaluation at 2018-10-17-02:30:52
  43. 2018-10-17 10:30:52.385626: I C:\tf_jenkins\home\workspace\rel-win\M\windows-gpu\PY\36\tensorflow\core\common_runtime\gpu\gpu_device.cc:1120] Creating TensorFlow device (/device:GPU:0) -> (device: 0, name: GeForce 940MX, pci bus id: 0000:01:00.0, compute capability: 5.0)
  44. INFO:tensorflow:Restoring parameters from C:\Users\------------\AppData\Local\Temp\tmpihfq7_j1\model.ckpt-2000
  45. INFO:tensorflow:Evaluation [1/1]
  46. INFO:tensorflow:Finished evaluation at 2018-10-17-02:30:54
  47. INFO:tensorflow:Saving dict for global step 2000: global_step = 2000, loss = 0.00669927, mean = [[[-0.00664094]
  48.   [ 1.0939678 ]
  49.   [ 1.05662227]
  50.   ..., 
  51.   [ 0.36486277]
  52.   [ 0.60855114]
  53.   [ 0.78335267]]], observed = [[[ 1.19162858]
  54.   [ 1.01151669]
  55.   [ 1.2492404 ]
  56.   ..., 
  57.   [ 0.58971846]
  58.   [ 0.59429663]
  59.   [ 0.75463229]]], start_tuple = (array([1199], dtype=int64), array([[ 0.49354312]], dtype=float32), [array([[  2.80782163e-01,  -2.79586822e-01,  -1.27018601e-01,
  60.          -1.37267247e-01,  -9.66532946e-01,   1.77575842e-01,
  61.           2.53590047e-01,  -1.71174794e-01,   3.26722264e-01,
  62.          -1.53287530e-01,   3.41674328e-01,  -2.82110858e+00,
  63.          -8.25344026e-02,  -6.24774337e-01,  -1.03143930e-01,
  64.           1.69074144e-02,   5.53107023e-01,   6.09656096e-01,
  65.           2.15942681e-01,   2.38117671e+00,  -4.35474813e-01,
  66.          -8.18751156e-02,  -8.21040720e-02,   5.50756678e-02,
  67.           3.19993496e-01,   4.17956561e-02,   3.75264943e-01,
  68.          -4.79493916e-01,   6.70328498e-01,  -2.11113644e+00,
  69.           7.29807839e-03,   4.77858186e-02,   6.35303259e-01,
  70.          -1.65449232e-01,   7.43012428e-01,  -3.35779548e-01,
  71.           1.10672331e+00,   8.13182443e-02,   3.63576859e-01,
  72.           2.60270387e-03,   1.08874297e+00,  -1.23278670e-01,
  73.           4.51275796e-01,   1.38471827e-01,  -2.19891405e+00,
  74.           4.55228150e-01,   3.76752585e-01,   4.18297976e-01,
  75.          -1.29674762e-01,  -5.27077794e-01,   2.10172087e-02,
  76.           9.18253139e-02,  -4.42963123e-01,   8.60494375e-01,
  77.          -1.56141710e+00,   6.13127127e-02,   1.06652260e+00,
  78.          -1.64958403e-01,  -2.49342889e-01,  -3.20325941e-02,
  79.           6.25251114e-01,  -9.56333756e-01,   6.22645095e-02,
  80.          -1.85177767e+00,  -1.18895024e-02,  -1.25629926e+00,
  81.          -8.09278548e-01,  -1.56489462e-01,   4.20603305e-01,
  82.           1.36081472e-01,   4.73593265e-01,  -7.08300769e-02,
  83.          -9.10878852e-02,   2.92861044e-01,  -1.19632289e-01,
  84.           6.10221215e-02,  -4.23507988e-01,   1.39661419e+00,
  85.          -3.00004274e-01,  -2.10687280e-01,  -1.49481639e-01,
  86.           3.21967512e-01,   2.97538459e-01,  -1.35252133e-01,
  87.           1.09200977e-01,   1.85446128e-01,   3.46938014e-01,
  88.           2.08598793e-01,  -3.52784902e-01,  -2.46544376e-01,
  89.           7.78264701e-02,  -3.51242304e-01,  -3.57431412e-01,
  90.           3.66707861e-01,   1.21410508e-02,  -8.59300196e-01,
  91.           4.11556125e-01,  -6.82742074e-02,   1.10266757e+00,
  92.          -4.94556457e-01,  -5.72922267e-02,   3.00662041e-01,
  93.          -1.90176621e-01,  -6.88186646e-01,   1.37748182e-01,
  94.           3.30467284e-01,   6.39625788e-01,  -5.39625525e-01,
  95.           3.10799032e-01,  -1.74361169e-01,  -1.03101039e+00,
  96.           1.62974745e-01,  -4.43051122e-02,  -8.31307888e-01,
  97.          -8.95474315e-01,   1.87550467e-02,  -2.91507039e-02,
  98.          -2.40048468e-01,  -4.92638528e-01,   1.22031212e+00,
  99.          -1.03123677e+00,   1.15175478e-01,  -4.30590212e-01,
  100.           3.07760298e-01,  -2.37644076e+00,   6.80060592e-04,
  101.           1.45029235e+00,  -1.63179412e-01]], dtype=float32), array([[  1.56333834e-01,  -8.78753215e-02,  -4.04292978e-02,
  102.          -5.39183915e-02,  -4.08501059e-01,   6.91992342e-02,
  103.           1.21542148e-01,  -7.25040585e-02,   1.23656943e-01,
  104.          -6.08574860e-02,   1.73645392e-01,  -5.46148360e-01,
  105.          -3.08538955e-02,  -2.52630085e-01,  -4.92266566e-02,
  106.           6.05375459e-03,   2.12676853e-01,   2.12552696e-01,
  107.           9.57069546e-02,   6.01795316e-01,  -1.65934741e-01,
  108.          -2.18765661e-02,  -2.14456674e-02,   2.04520095e-02,
  109.           1.51839703e-01,   1.74900144e-02,   1.79528132e-01,
  110.          -1.59714103e-01,   2.98072249e-01,  -5.45185566e-01,
  111.           2.36531044e-03,   1.51053490e-02,   3.07202935e-01,
  112.          -5.08357324e-02,   2.96984106e-01,  -1.09672762e-01,
  113.           5.08848071e-01,   3.89396697e-02,   1.46594375e-01,
  114.           5.78465813e-04,   4.44073975e-01,  -5.69530763e-02,
  115.           1.92802429e-01,   4.73112799e-02,  -5.95022798e-01,
  116.           1.91753775e-01,   1.71405807e-01,   1.87628955e-01,
  117.          -5.02609573e-02,  -2.27603659e-01,   8.66749138e-03,
  118.           3.60240042e-02,  -2.11831197e-01,   4.81612295e-01,
  119.          -4.55988973e-01,   2.93113627e-02,   4.87764150e-01,
  120.          -6.91987425e-02,  -1.01128876e-01,  -1.40920663e-02,
  121.           2.75271446e-01,  -4.79507029e-01,   2.70537268e-02,
  122.          -4.76451099e-01,  -4.29895753e-03,  -4.62495953e-01,
  123.          -3.31368059e-01,  -7.12227523e-02,   2.01868847e-01,
  124.           5.63942678e-02,   1.58110172e-01,  -1.71409473e-02,
  125.          -3.63412760e-02,   1.35076761e-01,  -4.54869717e-02,
  126.           1.97849423e-02,  -2.08776698e-01,   5.99132776e-01,
  127.          -9.71668810e-02,  -8.88494924e-02,  -5.91017641e-02,
  128.           1.46009699e-01,   1.49578944e-01,  -6.66293278e-02,
  129.           4.50978763e-02,   5.90396933e-02,   1.33028805e-01,
  130.           7.05365539e-02,  -1.45839781e-01,  -9.20177996e-02,
  131.           3.21419686e-02,  -1.38211146e-01,  -1.18100852e-01,
  132.           2.14208573e-01,   4.81602084e-03,  -3.42105478e-01,
  133.           1.84565291e-01,  -2.92618871e-02,   3.88085902e-01,
  134.          -2.48049170e-01,  -2.79053152e-02,   1.52629077e-01,
  135.          -6.13191538e-02,  -3.08730781e-01,   4.58811522e-02,
  136.           1.47217959e-01,   2.71202058e-01,  -2.18348011e-01,
  137.           1.24512725e-01,  -5.67152649e-02,  -5.15142381e-01,
  138.           5.49797714e-02,  -1.24295102e-02,  -4.49374735e-01,
  139.          -3.59201699e-01,   7.46859424e-03,  -1.10175423e-02,
  140.          -1.09787628e-01,  -2.06070423e-01,   3.97450179e-01,
  141.          -3.43233734e-01,   2.82084029e-02,  -2.50802487e-01,
  142.           1.35858551e-01,  -7.15136528e-01,   1.41225886e-04,
  143.           3.52943033e-01,  -5.17948419e-02]], dtype=float32)]), times = [[   0    1    2 ..., 1197 1198 1199]]

网站声明：如果转载，请联系本站管理员。否则一切后果自行承担。

本文链接：https://www.xckfsq.com/news/show.html?id=3566
赞同 0
评论 0 条

相关文章

小辣椒
小辣椒L0
粉丝 0 发表 10 + 关注 私信
上周热门
如何使用 StarRocks 管理和优化数据湖中的数据？  2944
【软件正版化】软件正版化工作要点  2863
统信UOS试玩黑神话：悟空  2823
信刻光盘安全隔离与信息交换系统  2717
镜舟科技与中启乘数科技达成战略合作，共筑数据服务新生态  1251
grub引导程序无法找到指定设备和分区  1217
华为全联接大会2024丨软通动力分论坛精彩议程抢先看！  163
点击报名 | 京东2025校招进校行程预告  162
2024海洋能源产业融合发展论坛暨博览会同期活动-海洋能源与数字化智能化论坛成功举办  160
华为纯血鸿蒙正式版9月底见！但Mate 70的内情还得接着挖...  157
本周热议
我的信创开放社区兼职赚钱历程 40
今天你签到了吗？ 27
信创开放社区邀请他人注册的具体步骤如下 15
如何玩转信创开放社区—从小白进阶到专家 15
方德桌面操作系统 14
我有15积分有什么用? 13
用抖音玩法闯信创开放社区——用平台宣传企业产品服务 13
如何让你先人一步获得悬赏问题信息？（创作者必看） 12
2024中国信创产业发展大会暨中国信息科技创新与应用博览会 9
中央国家机关政府采购中心：应当将CPU、操作系统符合安全可靠测评要求纳入采购需求 8
热门标签更多

加入交流群

请使用微信扫一扫!