tensorflow federated error module 'tensorflow_federated.python.learning' has no attribute 'build_federated_averaging_process'

Question

I have a ML code

import pandas as pd
import numpy as np
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler

import tensorflow as tf
import tensorflow_federated as tff

iris = load_iris()
df = pd.DataFrame(iris.data,columns=iris.feature_names)
df['Species']=iris.target

# Splitting the dataframe into input features and target variables

x = df.drop('Species',axis=1)
y = df['Species']
# Function to create client datasets (assuming data is pre-partitioned)
def create_tf_dataset(client_data):
  """Creates a tf.data.Dataset from the provided client data (features, labels)."""
  features, labels = client_data
  return tf.data.Dataset.from_tensor_slices((features, labels))

# Split data into cliendatasets (simulating data partitioning)
client_datasets = []
num_clients = 5
for i in range(num_clients):
  start_index = int(i * (len(x) / num_clients))
  end_index = int((i + 1) * (len(x) / num_clients))
  client_features = x[start_index:end_index]
  client_labels = y[start_index:end_index]
  client_datasets.append(create_tf_dataset((client_features, client_labels)))
  # Define the model architecture (replace with your desired model complexity)
def model_fn(inputs):
   features, _ = inputs  # We only use features for classification
   dense1 = tf.keras.layers.Dense(10, activation='relu')(features)
   dense2 = tf.keras.layers.Dense(3, activation='softmax')(dense1)  # 3 units for 3 Iris classes
   return tf.keras.Model(inputs=features, outputs=dense2)

# Define the client optimizer
client_optimizer = tf.keras.optimizers.SGD(learning_rate=0.1)

# Define the server optimizer (for server-sided aggregation)
server_optimizer = tf.keras.optimizers.SGD(learning_rate=0.01)
fed_learning_model = tff.learning.build_federated_averaging_process(
     model_fn,
     client_optimizer_fn=client_optimizer,
     server_optimizer_fn=server_optimizer)

But I am getting this error consistently.

---------------------------------------------------------------------------
AttributeError                            Traceback (most recent call last)
<ipython-input-13-e5966e29fc79> in <cell line: 1>()
----> 1 fed_learning_model = tff.learning.build_federated_averaging_process(
      2      model_fn,
      3      client_optimizer_fn=client_optimizer,
      4      server_optimizer_fn=server_optimizer)

AttributeError: module 'tensorflow_federated.python.learning' has no attribute 'build_federated_averaging_process'

I dont know whether my version suites. my tensorflow federated version is 0.76.0 my tensorflow version is 2.14.1 and python version is 3.10.12

When i search through the internet i saw that this code doesnot support for tensorflow version 0.21.0 onwards. but i dont know what to use in the latest version

Martina · Accepted Answer · 2024-08-20 17:00:11Z

2

You should use tff.learning.algorithms.build_weighted_fed_avg() instead.

This function takes in input a FunctionalModel: for this reason, you have to call tff.learning.models.functional_model_from_keras() to convert your Keras model in a Functional one before creating the trainer

model = tff.learning.models.functional_model_from_keras(
        model_fn(),
        loss_fn=tf.keras.losses.CategoricalCrossentropy(),
        input_spec=(
              tf.TensorSpec(shape=[None, 4], dtype=tf.float32),
              tf.TensorSpec(shape=[None, 3], dtype=tf.float32)
        ),
        metrics_constructor=collections.OrderedDict(
              accuracy=tf.keras.metrics.BinaryAccuracy,
              precision=tf.keras.metrics.Precision,
              recall=tf.keras.metrics.Recall,
            )
  )

fed_learning_model = tff.learning.algorithms.build_weighted_fed_avg(
                      model_fn= model,
                      client_optimizer_fn=client_optimizer,
                      server_optimizer_fn=server_optimizer
                    )

answered Aug 20, 2024 at 17:00

Martina

458 bronze badges

Sign up to request clarification or add additional context in comments.

1 Comment

yu yang Jian Apr 23 at 19:06

github.com/google-parfait/tensorflow-federated/blob/…

Collectives™ on Stack Overflow

tensorflow federated error module 'tensorflow_federated.python.learning' has no attribute 'build_federated_averaging_process'

1 Answer 1

1 Comment

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

1 Comment

Your Answer

Sign up or log in

Post as a guest

Related