训练LSTM模型时tensorflow.python.framework.errors_impl.AlreadyExistsError

分类：编程问答

如何解决训练LSTM模型时tensorflow.python.framework.errors_impl.AlreadyExistsError

在使用LSTM给出一系列单词的情况下，我正在尝试在keras中创建一个猜测下一个单词的机器学习模型。这是我的模型的代码：

gen=Sequential()
gen.add(Embedding(vocab_size,embed_dim))
gen.add(LSTM(vocab_size,activation='softmax'))
gen.compile(loss='categorical_crossentropy',optimizer='adam')
gen.summary()
(X_train,X_test,Y_train,Y_test)=train_test_split(X,Y,test_size=.2)
gen.fit(X_train,validation_data=(X_test,Y_test),batch_size=batch_size,epochs=epochs)

我的X数据是填充整数数组的数组，例如：[0,59,73,4]，而我的Y是一个热向量，其长度为我的唱头大小（在这种情况下为1994）。运行上面的代码将创建以下输出：

2020-08-23 11:19:34.390012: W tensorflow/stream_executor/platform/default/dso_loader.cc:55] Could not 

load dynamic library 'nvcuda.dll'; dlerror: nvcuda.dll not found
2020-08-23 11:19:34.391222: E tensorflow/stream_executor/cuda/cuda_driver.cc:313] failed call to cuInit: UNKNOWN ERROR (303)
2020-08-23 11:19:34.405184: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:169] retrieving CUDA diagnostic information for host: LAPTOP-J9AD5M4U
2020-08-23 11:19:34.406474: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:176] hostname: LAPTOP-J9AD5M4U
2020-08-23 11:19:34.407916: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2
2020-08-23 11:19:34.695283: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x20c4fc4a980 initialized for platform Host (this does not guarantee that XLA will be used). Devices:
2020-08-23 11:19:34.696499: I tensorflow/compiler/xla/service/service.cc:176]   StreamExecutor device (0): Host,Default Version
Model: "sequential"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
embedding (Embedding)        (None,None,32)          75040     
_________________________________________________________________
lstm (LSTM)                  (None,2345)              22305640  
=================================================================
Total params: 22,380,680
Trainable params: 22,680
Non-trainable params: 0
_________________________________________________________________
2020-08-23 11:20:30.730043: W tensorflow/core/framework/op_kernel.cc:1753] OP_REQUIRES failed at variable_ops.cc:104 : Already exists: Resource __per_step_0/gradient_tape/sequential/lstm/while/sequential/lstm/while_grad/body/_354/gradients/AddN_6/tmp_var/struct tensorflow::TemporaryVariableOp::TmpVar
2020-08-23 11:20:30.943137: W tensorflow/core/framework/op_kernel.cc:1753] OP_REQUIRES failed at variable_ops.cc:104 : Already exists: Resource __per_step_0/gradient_tape/sequential/lstm/while/sequential/lstm/while_grad/body/_354/gradients/AddN_6/tmp_var/struct tensorflow::TemporaryVariableOp::TmpVar
2020-08-23 11:20:31.469228: W tensorflow/core/framework/op_kernel.cc:1753] OP_REQUIRES failed at variable_ops.cc:104 : Already exists: Resource __per_step_0/gradient_tape/sequential/lstm/while/sequential/lstm/while_grad/body/_354/gradients/AddN_6/tmp_var/struct tensorflow::TemporaryVariableOp::TmpVar
2020-08-23 11:20:32.787365: W tensorflow/core/framework/op_kernel.cc:1753] OP_REQUIRES failed at variable_ops.cc:104 : Already exists: Resource __per_step_0/gradient_tape/sequential/lstm/while/sequential/lstm/while_grad/body/_354/gradients/AddN_6/tmp_var/struct tensorflow::TemporaryVariableOp::TmpVar
2020-08-23 11:20:34.014073: W tensorflow/core/framework/op_kernel.cc:1753] OP_REQUIRES failed at variable_ops.cc:104 : Already exists: Resource __per_step_0/gradient_tape/sequential/lstm/while/sequential/lstm/while_grad/body/_354/gradients/AddN_6/tmp_var/struct tensorflow::TemporaryVariableOp::TmpVar
2020-08-23 11:20:34.752033: W tensorflow/core/framework/op_kernel.cc:1753] OP_REQUIRES failed at variable_ops.cc:104 : Already exists: Resource __per_step_0/gradient_tape/sequential/lstm/while/sequential/lstm/while_grad/body/_354/gradients/AddN_6/tmp_var/struct tensorflow::TemporaryVariableOp::TmpVar
2020-08-23 11:20:35.980107: W tensorflow/core/framework/op_kernel.cc:1753] OP_REQUIRES failed at variable_ops.cc:104 : Already exists: Resource __per_step_0/gradient_tape/sequential/lstm/while/sequential/lstm/while_grad/body/_354/gradients/AddN_6/tmp_var/struct tensorflow::TemporaryVariableOp::TmpVar
2020-08-23 11:20:36.790928: W tensorflow/core/framework/op_kernel.cc:1753] OP_REQUIRES failed at variable_ops.cc:104 : Already exists: Resource __per_step_0/gradient_tape/sequential/lstm/while/sequential/lstm/while_grad/body/_354/gradients/AddN_6/tmp_var/struct tensorflow::TemporaryVariableOp::TmpVar
2020-08-23 11:20:37.396431: W tensorflow/core/framework/op_kernel.cc:1753] OP_REQUIRES failed at variable_ops.cc:104 : Already exists: Resource __per_step_0/gradient_tape/sequential/lstm/while/sequential/lstm/while_grad/body/_354/gradients/AddN_6/tmp_var/struct tensorflow::TemporaryVariableOp::TmpVar
2020-08-23 11:20:38.314946: W tensorflow/core/framework/op_kernel.cc:1753] OP_REQUIRES failed at variable_ops.cc:104 : Already exists: Resource __per_step_0/gradient_tape/sequential/lstm/while/sequential/lstm/while_grad/body/_354/gradients/AddN_6/tmp_var/struct tensorflow::TemporaryVariableOp::TmpVar
2020-08-23 11:20:39.111772: W tensorflow/core/framework/op_kernel.cc:1753] OP_REQUIRES failed at variable_ops.cc:104 : Already exists: Resource __per_step_0/gradient_tape/sequential/lstm/while/sequential/lstm/while_grad/body/_354/gradients/AddN_6/tmp_var/struct tensorflow::TemporaryVariableOp::TmpVar
2020-08-23 11:20:39.859069: W tensorflow/core/framework/op_kernel.cc:1753] OP_REQUIRES failed at variable_ops.cc:104 : Already exists: Resource __per_step_0/gradient_tape/sequential/lstm/while/sequential/lstm/while_grad/body/_354/gradients/AddN_6/tmp_var/struct tensorflow::TemporaryVariableOp::TmpVar
2020-08-23 11:20:40.938812: W tensorflow/core/framework/op_kernel.cc:1753] OP_REQUIRES failed at variable_ops.cc:104 : Already exists: Resource __per_step_0/gradient_tape/sequential/lstm/while/sequential/lstm/while_grad/body/_354/gradients/AddN_6/tmp_var/struct tensorflow::TemporaryVariableOp::TmpVar
2020-08-23 11:20:42.485426: W tensorflow/core/framework/op_kernel.cc:1753] OP_REQUIRES failed at variable_ops.cc:104 : Already exists: Resource __per_step_0/gradient_tape/sequential/lstm/while/sequential/lstm/while_grad/body/_354/gradients/AddN_6/tmp_var/struct tensorflow::TemporaryVariableOp::TmpVar
2020-08-23 11:20:43.183461: W tensorflow/core/framework/op_kernel.cc:1753] OP_REQUIRES failed at variable_ops.cc:104 : Already exists: Resource __per_step_0/gradient_tape/sequential/lstm/while/sequential/lstm/while_grad/body/_354/gradients/AddN_6/tmp_var/struct tensorflow::TemporaryVariableOp::TmpVar
Traceback (most recent call last):
  File "C:\Users\jsmith\Desktop\Code\JohnWorkspaces\Machine_Learning\Next Word\train.py",line 45,in <module>
    gen.fit(X_train,epochs=epochs)
  File "C:\Users\jsmith\anaconda3\lib\site-packages\tensorflow\python\keras\engine\training.py",line 66,in _method_wrapper
    return method(self,*args,**kwargs)
  File "C:\Users\jsmith\anaconda3\lib\site-packages\tensorflow\python\keras\engine\training.py",line 848,in fit
    tmp_logs = train_function(iterator)
  File "C:\Users\jsmith\anaconda3\lib\site-packages\tensorflow\python\eager\def_function.py",line 580,in __call__
    result = self._call(*args,**kwds)
  File "C:\Users\jsmith\anaconda3\lib\site-packages\tensorflow\python\eager\def_function.py",line 644,in _call
    return self._stateless_fn(*args,**kwds)
  File "C:\Users\jsmith\anaconda3\lib\site-packages\tensorflow\python\eager\function.py",line 2420,in __call__
    return graph_function._filtered_call(args,kwargs)  # pylint: disable=protected-access
  File "C:\Users\jsmith\anaconda3\lib\site-packages\tensorflow\python\eager\function.py",line 1665,in _filtered_call
    self.captured_inputs)
  File "C:\Users\jsmith\anaconda3\lib\site-packages\tensorflow\python\eager\function.py",line 1746,in _call_flat
    ctx,args,cancellation_manager=cancellation_manager))
  File "C:\Users\jsmith\anaconda3\lib\site-packages\tensorflow\python\eager\function.py",line 598,in call
    ctx=ctx)
  File "C:\Users\jsmith\anaconda3\lib\site-packages\tensorflow\python\eager\execute.py",line 60,in quick_execute
    inputs,attrs,num_outputs)
tensorflow.python.framework.errors_impl.AlreadyExistsError:  Resource __per_step_0/gradient_tape/sequential/lstm/while/sequential/lstm/while_grad/body/_354/gradients/AddN_6/tmp_var/struct tensorflow::TemporaryVariableOp::TmpVar
     [[{{node gradient_tape/sequential/lstm/while/sequential/lstm/while_grad/body/_354/gradients/AddN_6/tmp_var}}]] [Op:__inference_train_function_3777]

Function call stack:
train_function

有时它会分批训练，然后得到错误，而其他时候它会在根本不进行任何学习之前生成错误。我不知道它是否与LSTM的输入和输出形状有关，但是我希望这是否会在gen.compile而不是gen.fit上出现。

解决方法

所以我只是尝试了一个实验，发现它是LSTM的输出形状，并具有较小的输出长度，然后使用密集层进行扩展可以消除错误。

版权声明：本文内容由互联网用户自发贡献，该文观点与技术仅代表作者本人。本站仅提供信息存储空间服务，不拥有所有权，不承担相关法律责任。如发现本站有涉嫌侵权/违法违规的内容， 请发送邮件至 dio@foxmail.com 举报，一经查实，本站将立刻删除。

相关推荐

导入项目后报错问题
依赖报错 idea导入项目后依赖报错，解决方案：https://blog.csdn.net/weixin_42420249/article/details/81191861 依赖版本报错：更换其他版本 无法下载依赖可参考：https://blog.csdn.net/weixin_42628809/a
idea不能识别yaml文件
使用mybatis plus常见错误
错误1：代码生成器依赖和mybatis依赖冲突 启动项目时报错如下 2021-12-03 13:33:33.927 ERROR 7228 [ main] o.s.b.d.LoggingFailureAnalysisReporter : *************************** APPL
gradle常见问题与错误
错误1：gradle项目控制台输出为乱码 # 解决方案：https://blog.csdn.net/weixin_43501566/article/details/112482302 # 在gradle-wrapper.properties 添加以下内容 org.gradle.jvmargs=-Df
Mybatis Plus传入参数0不起作用
错误还原：在查询的过程中，传入的workType为0时，该条件不起作用 &lt;select id=&quot;xxx&quot;&gt; SELECT di.id, di.name, di.work_type, di.updated... &lt;where&gt; &lt;if test=&qu
linux中make编译源码包失败
报错如下，gcc版本太低 ^ server.c:5346:31: 错误：‘struct redisServer’没有名为‘server_cpulist’的成员 redisSetCpuAffinity(server.server_cpulist); ^ server.c: 在函数‘hasActiveC
微服务启动错误：Command line is too long. Shorten command line for
解决方案1 1、改项目中.idea/workspace.xml配置文件，增加dynamic.classpath参数 2、搜索PropertiesComponent，添加如下 &lt;property name=&quot;dynamic.classpath&quot; value=&quot;tru
vue常见错误
删除根组件app.vue中的默认代码后报错：Module Error (from ./node_modules/eslint-loader/index.js): 解决方案：关闭ESlint代码检测，在项目根目录创建vue.config.js，在文件中添加 module.exports = { lin
spark常见错误
查看spark默认的python版本 [root@master day27]# pyspark /home/software/spark-2.3.4-bin-hadoop2.7/conf/spark-env.sh: line 2: /usr/local/hadoop/bin/hadoop: No s
matplotlib报错：AttributeError: module 'backend_interagg' has no attribute 'FigureCanvas'. Did you mean: 'FigureCanvasAgg'?
使用本地python环境可以成功执行 import pandas as pd import matplotlib.pyplot as plt # 设置字体 plt.rcParams[&#39;font.sans-serif&#39;] = [&#39;SimHei&#39;] # 能正确显示负号 p
gitlab登录失败，报错：This challenge page was accidentally cached by an intermediary and is no longer available.
设置时间 控制面板
后端开发常见错误
错误1：Request method ‘DELETE‘ not supported 错误还原：controller层有一个接口，访问该接口时报错：Request method ‘DELETE‘ not supported 错误原因：没有接收到前端传入的参数，修改为如下 参考 错误2：cannot r
docker常见错误
错误1：启动docker镜像时报错：Error response from daemon: driver failed programming external connectivity on endpoint quirky_allen 解决方法：重启docker -&gt; systemctl r
idea常见错误
错误1：private field ‘xxx‘ is never assigned 按Altʾnter快捷键，选择第2项 参考：https://blog.csdn.net/shi_hong_fei_hei/article/details/88814070 错误2：启动时报错，不能找到主启动类 #
pip安装依赖失败
报错如下，通过源不能下载，最后警告pip需升级版本 Requirement already satisfied: pip in c:\users\ychen\appdata\local\programs\python\python310\lib\site-packages (22.0.4) Coll
maven常见错误
错误1：maven打包报错 错误还原：使用maven打包项目时报错如下 [ERROR] Failed to execute goal org.apache.maven.plugins:maven-resources-plugin:3.2.0:resources (default-resources)
cloud项目中常见错误
错误1：服务调用时报错 服务消费者模块assess通过openFeign调用服务提供者模块hires 如下为服务提供者模块hires的控制层接口 @RestController @RequestMapping(&quot;/hires&quot;) public class FeignControl
springboot常见错误
错误1：运行项目后报如下错误 解决方案 报错2：Failed to execute goal org.apache.maven.plugins:maven-compiler-plugin:3.8.1:compile (default-compile) on project sb 解决方案：在pom.
springmvc拦截器中使用redisTemplate报空指针异常
参考 错误原因 过滤器或拦截器在生效时，redisTemplate还没有注入 解决方案：在注入容器时就生效 @Component //项目运行时就注入Spring容器 public class RedisBean { @Resource private RedisTemplate&lt;String
vite报错：npm ERR! command C:WINDOWSsystem32cmd.exe /d /s /c C:UsersychenAppDataLocalTempnpx-dde1c848.cmd
使用vite构建项目报错 C:\Users\ychen\work&gt;npm init @vitejs/app @vitejs/create-app is deprecated, use npm init vite instead C:\Users\ychen\AppData\Local\npm-
pythonJavaScriptjavaHTMLPHPreactjsC#AndroidCSSNode.jssqlrpython-3.xMysqLjQueryc++pandasFlutterangularIOSdjangolinuxswifttypescript路由器JSON路由器设置无线路由器h3c华三华三路由器设置华三路由器电脑软件教程arraysdocker软件图文教程Cvue.jslaravelspring-boot