使用逻辑回归培训本地模型

发布于 2025-01-18 11:28:29 字数 756 浏览 0 评论 0原文

我正在使用 Tensorflow federated 构建联邦学习模型，并且正在遵循官方文档中提供的教程。正如我所看到的，提供的大多数实现都使用神经网络作为本地机器学习模型。正如我刚刚在下面的代码片段中所做的那样。

def create_keras_model():
  initializer = tf.keras.initializers.Zeros()
  return tf.keras.models.Sequential([
      tf.keras.layers.Input(shape=(9,)),
      tf.keras.layers.Dense(4, kernel_initializer=initializer),
      tf.keras.layers.Softmax(),
  ])
def model_fn():
  keras_model = create_keras_model()
  return tff.learning.from_keras_model(
      keras_model,
      input_spec=train_data[0].element_spec,
      loss=tf.keras.losses.SparseCategoricalCrossentropy(),
      metrics=[tf.keras.metrics.SparseCategoricalAccuracy()])

因为我正在构建一个具有 (9) 个特征和 (4) 个目标标签的多分类模型。我可以使用不同的 ML 模型进行本地训练，例如（逻辑回归）吗？我该如何调整？

原文

I am building a federated learning model using Tensorflow federated, and I am following the tutorials provided in the official documentation.
As I can see, most of the implementations provided are using a neural network as the local ML model. As I just did in the following snippet.

def create_keras_model():
  initializer = tf.keras.initializers.Zeros()
  return tf.keras.models.Sequential([
      tf.keras.layers.Input(shape=(9,)),
      tf.keras.layers.Dense(4, kernel_initializer=initializer),
      tf.keras.layers.Softmax(),
  ])
def model_fn():
  keras_model = create_keras_model()
  return tff.learning.from_keras_model(
      keras_model,
      input_spec=train_data[0].element_spec,
      loss=tf.keras.losses.SparseCategoricalCrossentropy(),
      metrics=[tf.keras.metrics.SparseCategoricalAccuracy()])

Since I am building a multi-classification model with (9) features and (4) target labels.
Can I use a different ML model for local training, like (logistic regression )? and how can I adjust that?

分享到QQ

分享到微博