ValueError：输入“input_2”缺少数据。您传递了一个带有键 ['y', 'x'] 的数据字典。需要以下键：['input_2']

发布于 2025-01-14 18:36:09 字数 1217 浏览 1 评论 0原文

按照前面的代码此处我正在评估联邦学习模型，但遇到了几个问题。这是评估代码

central_test = test.create_tf_dataset_from_all_clients()
test_data = central_test.map(reshape_data)

# function that accepts a server state, and uses 
#Keras to evaluate on the test dataset.
def evaluate(server_state):
  keras_model = create_keras_model()
  keras_model.compile(
      loss=tf.keras.losses.SparseCategoricalCrossentropy(),
      metrics=[tf.keras.metrics.SparseCategoricalAccuracy()]  
  )
  keras_model.set_weights(server_state)
  keras_model.evaluate(central_test)

server_state = federated_algorithm.initialize()
evaluate(server_state)

这是错误消息

ValueError: Missing data for input "input_2". You passed a data dictionary with keys ['y', 'x']. Expected the following keys: ['input_2']

那么这里会出现什么问题呢？ create_tf_dataset_from_all_clients 方法的使用是否在正确的位置？因为-正如教程中所写的那样-用于创建一个集中式评估数据集。为什么我们需要使用集中式数据集？

原文

Following the previous code here I am in process to evaluate the federated learning model and I got couple of issues.
This is the code for evaluation

central_test = test.create_tf_dataset_from_all_clients()
test_data = central_test.map(reshape_data)

# function that accepts a server state, and uses 
#Keras to evaluate on the test dataset.
def evaluate(server_state):
  keras_model = create_keras_model()
  keras_model.compile(
      loss=tf.keras.losses.SparseCategoricalCrossentropy(),
      metrics=[tf.keras.metrics.SparseCategoricalAccuracy()]  
  )
  keras_model.set_weights(server_state)
  keras_model.evaluate(central_test)

server_state = federated_algorithm.initialize()
evaluate(server_state)

this is the error message

ValueError: Missing data for input "input_2". You passed a data dictionary with keys ['y', 'x']. Expected the following keys: ['input_2']

So what would be the problem here?
and is the use of the method create_tf_dataset_from_all_clients in its right place? since -as it is written in the tutorial- used for create a centralized evaluation dataset. why do we need to use centralized dataset?

分享到QQ

分享到微博

如果你对这篇内容有疑问，欢迎到本站社区发帖提问参与讨论，获取更多帮助，或者扫码二维码加入 Web 技术交流群。

发布评论

需要登录才能够评论，你可以免费注册一个本站的账号。

不必在意 2025-01-21 18:36:09

test 数据集在评估期间具有不同的格式。尝试：

test_data = test.create_tf_dataset_from_all_clients().map(reshape_data).batch(2)
test_data = test_data.map(lambda x: (x['x'], x['y']))

def evaluate(server_state):
  keras_model = create_keras_model()
  keras_model.compile(
      loss=tf.keras.losses.SparseCategoricalCrossentropy(),
      metrics=[tf.keras.metrics.SparseCategoricalAccuracy()]  
  )
  keras_model.set_weights(server_state)
  keras_model.evaluate(test_data)

server_state = federated_algorithm.initialize()
evaluate(server_state)

The test dataset has a different format during evaluation. Try:

test_data = test.create_tf_dataset_from_all_clients().map(reshape_data).batch(2)
test_data = test_data.map(lambda x: (x['x'], x['y']))

def evaluate(server_state):
  keras_model = create_keras_model()
  keras_model.compile(
      loss=tf.keras.losses.SparseCategoricalCrossentropy(),
      metrics=[tf.keras.metrics.SparseCategoricalAccuracy()]  
  )
  keras_model.set_weights(server_state)
  keras_model.evaluate(test_data)

server_state = federated_algorithm.initialize()
evaluate(server_state)

回复收藏 0 原文

~没有更多了~