时间戳

首页 > 解决方案 > TFF：具有自定义数据集的自定义输入规范 - TypeError：“TensorSpec”类型的对象没有 len()

tensorflow-federated - TFF：具有自定义数据集的自定义输入规范 - TypeError：“TensorSpec”类型的对象没有 len()

问题描述

1：问题：我需要在 tff 模拟中使用自定义数据集。我建立在 tff/python/research/compression 示例“run_experiment.py”的基础上。错误：

  File "B:\tools and software\Anaconda\envs\bookProjects\lib\site-packages\IPython\core\interactiveshell.py", line 3331, in run_code
    exec(code_obj, self.user_global_ns, self.user_ns)
  File "<ipython-input-2-47998fd56829>", line 1, in <module>
    runfile('B:/projects/openProjects/githubprojects/BotnetTrafficAnalysisFederaedLearning/anomaly-detection/train_v04.py', args=['--experiment_name=temp', '--client_batch_size=20', '--client_optimizer=sgd', '--client_learning_rate=0.2', '--server_optimizer=sgd', '--server_learning_rate=1.0', '--total_rounds=200', '--rounds_per_eval=1', '--rounds_per_checkpoint=50', '--rounds_per_profile=0', '--root_output_dir=B:/projects/openProjects/githubprojects/BotnetTrafficAnalysisFederaedLearning/anomaly-detection/logs/fed_out/'], wdir='B:/projects/openProjects/githubprojects/BotnetTrafficAnalysisFederaedLearning/anomaly-detection')
  File "B:\tools and software\PyCharm 2020.1\plugins\python\helpers\pydev\_pydev_bundle\pydev_umd.py", line 197, in runfile
    pydev_imports.execfile(filename, global_vars, local_vars)  # execute the script
  File "B:\tools and software\PyCharm 2020.1\plugins\python\helpers\pydev\_pydev_imps\_pydev_execfile.py", line 18, in execfile
    exec(compile(contents+"\n", file, 'exec'), glob, loc)
  File "B:/projects/openProjects/githubprojects/BotnetTrafficAnalysisFederaedLearning/anomaly-detection/train_v04.py", line 292, in <module>
    app.run(main)
  File "B:\tools and software\Anaconda\envs\bookProjects\lib\site-packages\absl\app.py", line 299, in run
    _run_main(main, args)
  File "B:\tools and software\Anaconda\envs\bookProjects\lib\site-packages\absl\app.py", line 250, in _run_main
    sys.exit(main(argv))
  File "B:/projects/openProjects/githubprojects/BotnetTrafficAnalysisFederaedLearning/anomaly-detection/train_v04.py", line 285, in main
    train_main()
  File "B:/projects/openProjects/githubprojects/BotnetTrafficAnalysisFederaedLearning/anomaly-detection/train_v04.py", line 244, in train_main
    input_spec=input_spec),
  File "B:/projects/openProjects/githubprojects/BotnetTrafficAnalysisFederaedLearning/anomaly-detection/train_v04.py", line 193, in model_builder
    metrics=[tf.keras.metrics.Accuracy()]
  File "B:\tools and software\Anaconda\envs\bookProjects\lib\site-packages\tensorflow_federated\python\learning\keras_utils.py", line 125, in from_keras_model
    if len(input_spec) != 2:
TypeError: object of type 'TensorSpec' has no len()

突出显示：TypeError：“TensorSpec”类型的对象没有 len()

2：已尝试：我查看了对以下内容的响应：TensorFlow Federated：如何为具有多个输入的模型编写输入规范， 描述生成自定义输入规范所需的内容。我可能会想念理解输入规范。

如果我不需要这样做，并且有更好的方法，请告诉。

3：来源：

    df = get_train_data(sysarg)
    x_train, x_opt, x_test = np.split(df.sample(frac=1,
                                                random_state=17),
                                      [int(1 / 3 * len(df)), int(2 / 3 * len(df))])

    x_train, x_opt, x_test = create_scalar(x_opt, x_test, x_train)
    input_spec = tf.nest.map_structure(tf.TensorSpec.from_tensor, tf.convert_to_tensor(x_train))

标签： tensorflow-federated

解决方案

TFF 的模型声明的输入规范与您预期的略有不同；他们通常期望the和xvalues 作为参数（IE、数据和y标签）。不幸的是，您遇到了AttributeError，因为在这种情况下， ValueErrorTFF的加注可能更有帮助。在此处内联消息的操作部分：

The top-level structure in `input_spec` must contain exactly two elements,
as it must specify type information for both inputs to and predictions from the model.

您的特定示例中的 TLDR 是：如果您也可以访问标签（y_train如下），只需将您的input_spec定义更改为：

input_spec = tf.nest.map_structure(
    tf.TensorSpec.from_tensor,
    [tf.convert_to_tensor(x_train), tf.convert_to_tensor(y_train)])

推荐阅读