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
2024-05-18 17:50:42
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
INFO:tensorflow:loss = 0.496935, step = 1
INFO:tensorflow:global_step/sec: 7.44562
INFO:tensorflow:loss = 0.0289763, step = 101 (13.432 sec)
INFO:tensorflow:global_step/sec: 6.42037
INFO:tensorflow:loss = 0.0200101, step = 201 (15.575 sec)
INFO:tensorflow:global_step/sec: 5.56483
INFO:tensorflow:loss = 0.0195363, step = 301 (17.971 sec)
INFO:tensorflow:global_step/sec: 5.30867
INFO:tensorflow:loss = 0.0141311, step = 401 (18.836 sec)
INFO:tensorflow:global_step/sec: 5.41209
INFO:tensorflow:loss = 0.014299, step = 501 (18.479 sec)
INFO:tensorflow:global_step/sec: 4.92611
INFO:tensorflow:loss = 0.0155927, step = 601 (20.298 sec)
INFO:tensorflow:global_step/sec: 5.11247
INFO:tensorflow:loss = 0.0130529, step = 701 (19.563 sec)
INFO:tensorflow:global_step/sec: 4.71378
INFO:tensorflow:loss = 0.0131998, step = 801 (21.211 sec)
INFO:tensorflow:global_step/sec: 4.71155
INFO:tensorflow:loss = 0.0143074, step = 901 (21.224 sec)
INFO:tensorflow:global_step/sec: 5.07501
INFO:tensorflow:loss = 0.0160928, step = 1001 (19.704 sec)
INFO:tensorflow:global_step/sec: 4.85088
INFO:tensorflow:loss = 0.00991265, step = 1101 (20.615 sec)
INFO:tensorflow:global_step/sec: 4.93806
INFO:tensorflow:loss = 0.0125441, step = 1201 (20.251 sec)
INFO:tensorflow:global_step/sec: 5.40711
INFO:tensorflow:loss = 0.0127672, step = 1301 (18.497 sec)
INFO:tensorflow:global_step/sec: 4.92733
INFO:tensorflow:loss = 0.0109727, step = 1401 (20.294 sec)
INFO:tensorflow:global_step/sec: 4.42869
INFO:tensorflow:loss = 0.0138402, step = 1501 (22.578 sec)
INFO:tensorflow:global_step/sec: 4.902
INFO:tensorflow:loss = 0.00974652, step = 1601 (20.401 sec)
INFO:tensorflow:global_step/sec: 5.87293
INFO:tensorflow:loss = 0.010258, step = 1701 (17.029 sec)
INFO:tensorflow:global_step/sec: 5.88471
INFO:tensorflow:loss = 0.0119193, step = 1801 (16.991 sec)
INFO:tensorflow:global_step/sec: 5.89885
INFO:tensorflow:loss = 0.0130985, step = 1901 (16.951 sec)
INFO:tensorflow:Saving checkpoints for 2000 into C:\Users\----------\AppData\Local\Temp\tmpihfq7_j1\model.ckpt.
INFO:tensorflow:Loss for final step: 0.0151946.
INFO:tensorflow:Starting evaluation at 2018-10-17-02:30:52
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)
INFO:tensorflow:Restoring parameters from C:\Users\------------\AppData\Local\Temp\tmpihfq7_j1\model.ckpt-2000
INFO:tensorflow:Evaluation [1/1]
INFO:tensorflow:Finished evaluation at 2018-10-17-02:30:54
INFO:tensorflow:Saving dict for global step 2000: global_step = 2000, loss = 0.00669927, mean = [[[-0.00664094][ 1.0939678 ][ 1.05662227]..., [ 0.36486277][ 0.60855114][ 0.78335267]]], observed = [[[ 1.19162858][ 1.01151669][ 1.2492404 ]..., [ 0.58971846][ 0.59429663][ 0.75463229]]], start_tuple = (array([1199], dtype=int64), array([[ 0.49354312]], dtype=float32), [array([[ 2.80782163e-01, -2.79586822e-01, -1.27018601e-01,-1.37267247e-01, -9.66532946e-01, 1.77575842e-01,2.53590047e-01, -1.71174794e-01, 3.26722264e-01,-1.53287530e-01, 3.41674328e-01, -2.82110858e+00,-8.25344026e-02, -6.24774337e-01, -1.03143930e-01,1.69074144e-02, 5.53107023e-01, 6.09656096e-01,2.15942681e-01, 2.38117671e+00, -4.35474813e-01,-8.18751156e-02, -8.21040720e-02, 5.50756678e-02,3.19993496e-01, 4.17956561e-02, 3.75264943e-01,-4.79493916e-01, 6.70328498e-01, -2.11113644e+00,7.29807839e-03, 4.77858186e-02, 6.35303259e-01,-1.65449232e-01, 7.43012428e-01, -3.35779548e-01,1.10672331e+00, 8.13182443e-02, 3.63576859e-01,2.60270387e-03, 1.08874297e+00, -1.23278670e-01,4.51275796e-01, 1.38471827e-01, -2.19891405e+00,4.55228150e-01, 3.76752585e-01, 4.18297976e-01,-1.29674762e-01, -5.27077794e-01, 2.10172087e-02,9.18253139e-02, -4.42963123e-01, 8.60494375e-01,-1.56141710e+00, 6.13127127e-02, 1.06652260e+00,-1.64958403e-01, -2.49342889e-01, -3.20325941e-02,6.25251114e-01, -9.56333756e-01, 6.22645095e-02,-1.85177767e+00, -1.18895024e-02, -1.25629926e+00,-8.09278548e-01, -1.56489462e-01, 4.20603305e-01,1.36081472e-01, 4.73593265e-01, -7.08300769e-02,-9.10878852e-02, 2.92861044e-01, -1.19632289e-01,6.10221215e-02, -4.23507988e-01, 1.39661419e+00,-3.00004274e-01, -2.10687280e-01, -1.49481639e-01,3.21967512e-01, 2.97538459e-01, -1.35252133e-01,1.09200977e-01, 1.85446128e-01, 3.46938014e-01,2.08598793e-01, -3.52784902e-01, -2.46544376e-01,7.78264701e-02, -3.51242304e-01, -3.57431412e-01,3.66707861e-01, 1.21410508e-02, -8.59300196e-01,4.11556125e-01, -6.82742074e-02, 1.10266757e+00,-4.94556457e-01, -5.72922267e-02, 3.00662041e-01,-1.90176621e-01, -6.88186646e-01, 1.37748182e-01,3.30467284e-01, 6.39625788e-01, -5.39625525e-01,3.10799032e-01, -1.74361169e-01, -1.03101039e+00,1.62974745e-01, -4.43051122e-02, -8.31307888e-01,-8.95474315e-01, 1.87550467e-02, -2.91507039e-02,-2.40048468e-01, -4.92638528e-01, 1.22031212e+00,-1.03123677e+00, 1.15175478e-01, -4.30590212e-01,3.07760298e-01, -2.37644076e+00, 6.80060592e-04,1.45029235e+00, -1.63179412e-01]], dtype=float32), array([[ 1.56333834e-01, -8.78753215e-02, -4.04292978e-02,-5.39183915e-02, -4.08501059e-01, 6.91992342e-02,1.21542148e-01, -7.25040585e-02, 1.23656943e-01,-6.08574860e-02, 1.73645392e-01, -5.46148360e-01,-3.08538955e-02, -2.52630085e-01, -4.92266566e-02,6.05375459e-03, 2.12676853e-01, 2.12552696e-01,9.57069546e-02, 6.01795316e-01, -1.65934741e-01,-2.18765661e-02, -2.14456674e-02, 2.04520095e-02,1.51839703e-01, 1.74900144e-02, 1.79528132e-01,-1.59714103e-01, 2.98072249e-01, -5.45185566e-01,2.36531044e-03, 1.51053490e-02, 3.07202935e-01,-5.08357324e-02, 2.96984106e-01, -1.09672762e-01,5.08848071e-01, 3.89396697e-02, 1.46594375e-01,5.78465813e-04, 4.44073975e-01, -5.69530763e-02,1.92802429e-01, 4.73112799e-02, -5.95022798e-01,1.91753775e-01, 1.71405807e-01, 1.87628955e-01,-5.02609573e-02, -2.27603659e-01, 8.66749138e-03,3.60240042e-02, -2.11831197e-01, 4.81612295e-01,-4.55988973e-01, 2.93113627e-02, 4.87764150e-01,-6.91987425e-02, -1.01128876e-01, -1.40920663e-02,2.75271446e-01, -4.79507029e-01, 2.70537268e-02,-4.76451099e-01, -4.29895753e-03, -4.62495953e-01,-3.31368059e-01, -7.12227523e-02, 2.01868847e-01,5.63942678e-02, 1.58110172e-01, -1.71409473e-02,-3.63412760e-02, 1.35076761e-01, -4.54869717e-02,1.97849423e-02, -2.08776698e-01, 5.99132776e-01,-9.71668810e-02, -8.88494924e-02, -5.91017641e-02,1.46009699e-01, 1.49578944e-01, -6.66293278e-02,4.50978763e-02, 5.90396933e-02, 1.33028805e-01,7.05365539e-02, -1.45839781e-01, -9.20177996e-02,3.21419686e-02, -1.38211146e-01, -1.18100852e-01,2.14208573e-01, 4.81602084e-03, -3.42105478e-01,1.84565291e-01, -2.92618871e-02, 3.88085902e-01,-2.48049170e-01, -2.79053152e-02, 1.52629077e-01,-6.13191538e-02, -3.08730781e-01, 4.58811522e-02,1.47217959e-01, 2.71202058e-01, -2.18348011e-01,1.24512725e-01, -5.67152649e-02, -5.15142381e-01,5.49797714e-02, -1.24295102e-02, -4.49374735e-01,-3.59201699e-01, 7.46859424e-03, -1.10175423e-02,-1.09787628e-01, -2.06070423e-01, 3.97450179e-01,-3.43233734e-01, 2.82084029e-02, -2.50802487e-01,1.35858551e-01, -7.15136528e-01, 1.41225886e-04,3.52943033e-01, -5.17948419e-02]], dtype=float32)]), times = [[ 0 1 2 ..., 1197 1198 1199]]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个数据状态相关推荐
- DL之LSTM之MvP：基于TF利用LSTM基于DIY时间训练csv文件数据预测后100个数据(多值预测)状态
DL之LSTM之MvP:基于TF利用LSTM基于DIY时间训练csv文件数据预测后100个数据(多值预测)状态 目录 数据集csv文件内容 输出结果 设计思路 训练记录全过程 数据集csv文件内容 输 ...
- DL之RNN：基于TF利用RNN实现简单的序列数据类型(DIY序列数据集)的二分类(线性序列随机序列)
DL之RNN:基于TF利用RNN实现简单的序列数据类型(DIY序列数据集)的二分类(线性序列&随机序列) 目录 序列数据类型&输出结果 设计思路 序列数据类型&输出结果 1.t ...
- DL之RNN：人工智能为你写代码——基于TF利用RNN算法实现生成编程语言代码(C++语言)、训练测试过程全记录
DL之RNN:基于TF利用RNN算法实现生成编程语言代码(C语言).训练&测试过程全记录 目录 输出结果 监控模型 训练&测试过程全记录 训练的数据集展示 输出结果 1.test01 ...
- DL之CycleGAN：基于TF利用CycleGAN模型对apple2orange数据集实现图像转换—训练测试过程全记录
DL之CycleGAN:基于TF利用CycleGAN模型对apple2orange数据集实现图像转换-训练&测试过程全记录 目录 apple2orange数据集 输出结果 训练&测试过 ...
- DL之pix2pix：基于TF利用pix2pix模型对food_resized数据集实现Auto Color自动上色技术—训练测试过程全记录
DL之pix2pix:基于TF利用pix2pix模型对food_resized数据集实现Auto Color自动上色技术 目录 训练 food_resized数据集展示 TB过程监控 1.SCALAR ...
- DL之DCGNN：基于TF利用DCGAN实现在MNIST数据集上训练生成新样本
DL之DCGNN:基于TF利用DCGAN实现在MNIST数据集上训练生成新样本 目录 输出结果 设计思路 实现部分代码 说明:所有图片文件丢失 输出结果 更新-- 设计思路 更新-- 实现部分代码 更 ...
- DL之RNN：人工智能为你写周董歌词——基于TF利用RNN算法实现【机器为你作词】、训练测试过程全记录
DL之RNN:人工智能为你写周董歌词--基于TF利用RNN算法实现~机器为你作词~.训练&测试过程全记录 目录 输出结果 模型监控 训练.测试过程全记录 训练的数据集 输出结果 1.test0 ...
- DL之RNN：人工智能为你写小说——基于TF利用RNN算法训练数据集(William Shakespeare的《Coriolanus》)替代你写英语小说短文、训练测试过程全记录
DL之RNN:基于TF利用RNN算法训练数据集(William Shakespeare的<Coriolanus>)替代你写英语小说短文.测试过程全记录 目录 输出结果 监控模型 训练过程全 ...
- RL之PG：基于TF利用策略梯度算法玩Cartpole游戏实现智能得高分
RL之PG:基于TF利用策略梯度算法玩Cartpole游戏实现智能得高分 目录 输出结果 设计思路 测试过程 输出结果 视频观看地址:强化学习-基于TF利用策略梯度算法玩Cartpole游戏实现智能得 ...
最新文章
- 20151024学习内容：安全相关
- MySQL读取Binlog日志常见的3种错误
- ASP.NET浏览器跨域
- BottomNavigationView处理只有2个tab的情况
- webpack实用配置
- 【TensorFlow】TensorFlow从浅入深系列之十一 -- 教你深入理解卷积神经网络中的卷积层
- 面试官问你HashMap底层你用线程安全吊打他
- jep-java-4.0-trial.jar 下载
- 游戏开发中的向量数学
- python selenium下载图片_selenium下载图片(原图)
- 机器学习（周志华） 第七章贝叶斯分类器
- 深入浅出理解输入输出阻抗-音频电路输入输出阻抗
- 2020-12-29 G003-186-16
- 随机抽取一名同学回答问题，7/4更新一次
- Mysql之DDL(数据定义语言)
- 微信小程序怎么制作自己的程序呢？简单明了的步骤分享
- ConcurrentHashMap源码分析，轻取面试Offer（一）
- 知识付费，下半场怎么走（附大会PPT下载）
- HTML嵌入三维仿真 .ezo文件的方法
- 逐句回答,流式返回,ChatGPT采用的Server-sent events后端实时推送协议Python3.10实现,基于Tornado6.1