DL之RNN：基于TF利用RNN算法实现~机器为你写诗~、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、test01
<unk><unk>风下，天上不相逢。一人不得别，不得不可寻。何事无时事，谁知一日年。一年多旧国，一处不相寻。白发何人见，清辉自有人。何当不知事，相送不相思。此去无相见，何年有旧年。相思一阳处，相送不能归。不得千株下，何时不得时。此心不可见，此日不相思。何事有归客，何言不见时。何处不知处，不知山上时。何当不可问，一事不知情。此去不知事，无人不有身。相逢何处见，不觉白云间。白云一相见，一月不知时。一夜一秋色，青楼不可知。江西山水下，山下白头心。此事何人见，孤舟向日深。何当无一事，此路不相亲。何必有山里，不知归去人。相知不相识，此地不能闻。白发千株树，秋风落日寒。
2、test02
不得无时人，何人不知别。不见一时人，相思何日在。一夜不可知，何时无一日。一人不自见，何处有人情。何处不知此，何人见此年。何时不得处，此日不知君。一日何人得，何由有此身。相思无不得，一去不知君。此日何人见，东风满月中。无知不得去，不见不相思。不得千峰上，相逢独不穷。何年不可待，一夜有春风。不见南江路，相思一夜归。何人知此路，此日更难归。白日无人处，秋光入水流。江南无限路，相忆在山城。何处知何事，孤城不可归。山边秋月尽，江水水风生。不有南江客，何时有故乡。山中山上水，山上水中风。何处不相访，何年有此心。江边秋雨尽，山水白云寒。
3、test03
一朝多不见，无处在人人。一里无人去，无人见故山。何年不知别，此地有相亲。白首何时去，春风不得行。不知归去去，谁见此来情。不有青山去，谁知不自知。一时何处去，此去有君人。不见南江路，何时是白云。不知归客去，相忆不成秋。不得东西去，何人有一身。不能知此事，不觉是人情。一里无时事，相逢不得心。江南秋雨尽，风落夜来深。何处不知别，春来不自知。一朝无一处，何处是江南。一里不相见，东西无一人。一朝归去处，何事见沧洲。此去无年处，何年有远心。不知山上客，不是故人心。一里不可得，无人有一年。何人不见处，不得一朝生。不见青云客，何人是此时。
模型监控
训练、测试过程全记录
1、训练过程
-10-13 22:31:33.935213:step: 10/10000... loss: 6.5868... 0.1901 sec/batchstep: 20/10000... loss: 6.4824... 0.2401 sec/batchstep: 30/10000... loss: 6.3176... 0.2401 sec/batchstep: 40/10000... loss: 6.2126... 0.2401 sec/batchstep: 50/10000... loss: 6.0081... 0.2301 sec/batchstep: 60/10000... loss: 5.7657... 0.2401 sec/batchstep: 70/10000... loss: 5.6694... 0.2301 sec/batchstep: 80/10000... loss: 5.6661... 0.2301 sec/batchstep: 90/10000... loss: 5.6736... 0.2301 sec/batchstep: 100/10000... loss: 5.5698... 0.2201 sec/batchstep: 110/10000... loss: 5.6083... 0.2301 sec/batchstep: 120/10000... loss: 5.5252... 0.2301 sec/batchstep: 130/10000... loss: 5.4708... 0.2301 sec/batchstep: 140/10000... loss: 5.4311... 0.2401 sec/batchstep: 150/10000... loss: 5.4571... 0.2701 sec/batchstep: 160/10000... loss: 5.5295... 0.2520 sec/batchstep: 170/10000... loss: 5.4211... 0.2401 sec/batchstep: 180/10000... loss: 5.4161... 0.2802 sec/batchstep: 190/10000... loss: 5.4389... 0.4943 sec/batchstep: 200/10000... loss: 5.3380... 0.4332 sec/batch……step: 790/10000... loss: 5.2031... 0.2301 sec/batchstep: 800/10000... loss: 5.2537... 0.2301 sec/batchstep: 810/10000... loss: 5.0923... 0.2301 sec/batchstep: 820/10000... loss: 5.1930... 0.2501 sec/batchstep: 830/10000... loss: 5.1636... 0.2535 sec/batchstep: 840/10000... loss: 5.1357... 0.2801 sec/batchstep: 850/10000... loss: 5.0844... 0.2236 sec/batchstep: 860/10000... loss: 5.... 0.2386 sec/batchstep: 870/10000... loss: 5.1894... 0.2401 sec/batchstep: 880/10000... loss: 5.1631... 0.2501 sec/batchstep: 890/10000... loss: 5.1297... 0.2477 sec/batchstep: 900/10000... loss: 5.1044... 0.2401 sec/batchstep: 910/10000... loss: 5.0738... 0.2382 sec/batchstep: 920/10000... loss: 5.0971... 0.2701 sec/batchstep: 930/10000... loss: 5.1829... 0.2501 sec/batchstep: 940/10000... loss: 5.1822... 0.2364 sec/batchstep: 950/10000... loss: 5.1883... 0.2401 sec/batchstep: 960/10000... loss: 5.0521... 0.2301 sec/batchstep: 970/10000... loss: 5.0848... 0.2201 sec/batchstep: 980/10000... loss: 5.0598... 0.2201 sec/batchstep: 990/10000... loss: 5.0421... 0.2701 sec/batchstep: 1000/10000... loss: 5.1234... 0.2323 sec/batchstep: 1010/10000... loss: 5.0744... 0.2356 sec/batchstep: 1020/10000... loss: 5.0408... 0.2401 sec/batchstep: 1030/10000... loss: 5.1138... 0.2417 sec/batchstep: 1040/10000... loss: 4.9961... 0.2601 sec/batchstep: 1050/10000... loss: 4.9691... 0.2401 sec/batchstep: 1060/10000... loss: 4.9938... 0.2601 sec/batchstep: 1070/10000... loss: 4.9778... 0.2601 sec/batchstep: 1080/10000... loss: 5.0157... 0.3600 sec/batch……step: 4440/10000... loss: 4.7136... 0.2757 sec/batchstep: 4450/10000... loss: 4.5896... 0.2767 sec/batchstep: 4460/10000... loss: 4.6408... 0.3088 sec/batchstep: 4470/10000... loss: 4.6901... 0.2737 sec/batchstep: 4480/10000... loss: 4.5717... 0.2707 sec/batchstep: 4490/10000... loss: 4.7523... 0.2838 sec/batchstep: 4500/10000... loss: 4.7592... 0.2998 sec/batchstep: 4510/10000... loss: 4.6054... 0.2878 sec/batchstep: 4520/10000... loss: 4.7039... 0.2868 sec/batchstep: 4530/10000... loss: 4.6380... 0.2838 sec/batchstep: 4540/10000... loss: 4.5378... 0.2777 sec/batchstep: 4550/10000... loss: 4.7376... 0.3098 sec/batchstep: 4560/10000... loss: 4.7103... 0.2797 sec/batchstep: 4570/10000... loss: 4.7170... 0.2767 sec/batchstep: 4580/10000... loss: 4.7307... 0.3168 sec/batchstep: 4590/10000... loss: 4.7139... 0.3108 sec/batchstep: 4600/10000... loss: 4.7419... 0.3028 sec/batchstep: 4610/10000... loss: 4.7980... 0.2918 sec/batchstep: 4620/10000... loss: 4.7127... 0.2797 sec/batchstep: 4630/10000... loss: 4.7264... 0.2858 sec/batchstep: 4640/10000... loss: 4.6384... 0.3419 sec/batchstep: 4650/10000... loss: 4.6761... 0.2978 sec/batchstep: 4660/10000... loss: 4.8158... 0.3590 sec/batchstep: 4670/10000... loss: 4.7579... 0.2828 sec/batchstep: 4680/10000... loss: 4.7702... 0.2777 sec/batchstep: 4690/10000... loss: 4.6909... 0.2607 sec/batchstep: 4700/10000... loss: 4.6037... 0.2808 sec/batchstep: 4710/10000... loss: 4.6775... 0.2848 sec/batchstep: 4720/10000... loss: 4.6074... 0.2838 sec/batchstep: 4730/10000... loss: 4.7280... 0.3088 sec/batchstep: 4740/10000... loss: 4.7241... 0.3539 sec/batchstep: 4750/10000... loss: 4.5496... 0.2948 sec/batchstep: 4760/10000... loss: 4.6488... 0.3189 sec/batchstep: 4770/10000... loss: 4.6698... 0.3048 sec/batchstep: 4780/10000... loss: 4.6410... 0.3068 sec/batchstep: 4790/10000... loss: 4.7408... 0.3329 sec/batchstep: 4800/10000... loss: 4.6425... 0.2928 sec/batchstep: 4810/10000... loss: 4.6900... 0.2978 sec/batchstep: 4820/10000... loss: 4.5715... 0.3499 sec/batchstep: 4830/10000... loss: 4.7289... 0.2868 sec/batchstep: 4840/10000... loss: 4.7500... 0.2998 sec/batchstep: 4850/10000... loss: 4.7674... 0.2968 sec/batchstep: 4860/10000... loss: 4.6832... 0.3078 sec/batchstep: 4870/10000... loss: 4.7478... 0.3008 sec/batchstep: 4880/10000... loss: 4.7895... 0.2817 sec/batch……step: 9710/10000... loss: 4.5839... 0.2601 sec/batchstep: 9720/10000... loss: 4.4666... 0.2401 sec/batchstep: 9730/10000... loss: 4.6392... 0.2201 sec/batchstep: 9740/10000... loss: 4.5415... 0.2201 sec/batchstep: 9750/10000... loss: 4.6513... 0.2201 sec/batchstep: 9760/10000... loss: 4.6485... 0.2201 sec/batchstep: 9770/10000... loss: 4.5317... 0.2201 sec/batchstep: 9780/10000... loss: 4.5547... 0.2301 sec/batchstep: 9790/10000... loss: 4.3995... 0.2301 sec/batchstep: 9800/10000... loss: 4.5596... 0.2301 sec/batchstep: 9810/10000... loss: 4.5636... 0.2301 sec/batchstep: 9820/10000... loss: 4.4348... 0.2201 sec/batchstep: 9830/10000... loss: 4.5268... 0.2201 sec/batchstep: 9840/10000... loss: 4.5790... 0.2201 sec/batchstep: 9850/10000... loss: 4.6265... 0.2301 sec/batchstep: 9860/10000... loss: 4.6017... 0.2401 sec/batchstep: 9870/10000... loss: 4.4009... 0.2301 sec/batchstep: 9880/10000... loss: 4.4448... 0.2201 sec/batchstep: 9890/10000... loss: 4.5858... 0.2201 sec/batchstep: 9900/10000... loss: 4.5622... 0.2201 sec/batchstep: 9910/10000... loss: 4.4015... 0.2301 sec/batchstep: 9920/10000... loss: 4.5220... 0.2301 sec/batchstep: 9930/10000... loss: 4.5207... 0.2201 sec/batchstep: 9940/10000... loss: 4.4752... 0.2201 sec/batchstep: 9950/10000... loss: 4.4572... 0.2301 sec/batchstep: 9960/10000... loss: 4.5389... 0.2201 sec/batchstep: 9970/10000... loss: 4.5561... 0.2301 sec/batchstep: 9980/10000... loss: 4.4487... 0.2401 sec/batchstep: 9990/10000... loss: 4.4851... 0.2301 sec/batchstep: 10000/10000... loss: 4.5944... 0.2201 sec/batch
2、测试过程
训练的数据集
1、大量的五言唐诗
寒随穷律变，春逐鸟声开。初风飘带柳，晚雪间花梅。碧林青旧竹，绿沼翠新苔。芝田初雁去，绮树巧莺来。晚霞聊自怡，初晴弥可喜。日晃百花色，风动千林翠。池鱼跃不同，园鸟声还异。寄言博通者，知予物外志。一朝春夏改，隔夜鸟花迁。阴阳深浅叶，晓夕重轻烟。哢莺犹响殿，横丝正网天。珮高兰影接，绶细草纹连。碧鳞惊棹侧，玄燕舞檐前。何必汾阳处，始复有山泉。夏律昨留灰，秋箭今移晷。峨嵋岫初出，洞庭波渐起。桂白发幽岩，菊黄开灞涘。运流方可叹，含毫属微理。寒惊蓟门叶，秋发小山枝。松阴背日转，竹影避风移。提壶菊花岸，高兴芙蓉池。欲知凉气早，巢空燕不窥。山亭秋色满，岩牖凉风度。疏兰尚染烟，残菊犹承露。古石衣新苔，新巢封古树。历览情无极，咫尺轮光暮。慨然抚长剑，济世岂邀名。星旗纷电举，日羽肃天行。遍野屯万骑，临原驻五营。登山麾武节，背水纵神兵。在昔戎戈动，今来宇宙平。翠野驻戎轩，卢龙转征旆。遥山丽如绮，长流萦似带。海气百重楼，岩松千丈盖。兹焉可游赏，何必襄城外。玄兔月初明，澄辉照辽碣。映云光暂隐，隔树花如缀。魄满桂枝圆，轮亏镜彩缺。临城却影散，带晕重围结。驻跸俯九都，停观妖氛灭。碧原开雾隰，绮岭峻霞城。烟峰高下翠，日浪浅深明。斑红妆蕊树，圆青压溜荆。迹岩劳傅想，窥野访莘情。巨川何以济，舟楫伫时英。春蒐驰骏骨，总辔俯长河。霞处流萦锦，风前漾卷罗。水花翻照树，堤兰倒插波。岂必汾阴曲，秋云发棹歌。重峦俯渭水，碧嶂插遥天。……
DL之RNN：人工智能为你写诗——基于TF利用RNN算法实现【机器为你写诗】 训练测试过程全记录
如果觉得《DL之RNN：人工智能为你写诗——基于TF利用RNN算法实现【机器为你写诗】 训练测试过程》对你有帮助，请点赞、收藏，并留下你的观点哦！
