Stack Overflow
Stack Overflow

Questions tagged [tensorflow-federated]

Federated Learning is a machine learning setting where the goal is to train a high-quality centralized model with training data distributed over a large number of clients each with unreliable and relatively slow network connections. https://research.google/pubs/pub49232/

412 questions
8
votes
2 answers

Create a custom federated data set in TensorFlow Federated

I'd like to adapt the recurrent autoencoder from this blog post to work in a federated environment. I've modified the model slightly to conform with the example shown in the TFF image classification tutorial. def create_compiled_keras_model(): …
Adam Hodgson
  • 325
  • 5
  • 12
6
votes
3 answers

How to create federated dataset from a CSV file?

I have selected this dataset: https://www.kaggle.com/karangadiya/fifa19 Now, I would like to convert this CSV file into the federated dataset to fit in the model. Tensorflow provided tutorials on federated learning where they have used a pre-defined…
Mahedi Hasan Jisan
  • 89
  • 1
  • 6
5
votes
2 answers

Learning rate setting when calling the function tff.learning.build_federated_averaging_process

I'm carrying out a federated learning process and use the function tff.learning.build_federated_averaging_process to create an iterative process of federated learning. As mentioned in the TFF tutorial, this function has two arguments called…
Qi Wang
  • 61
  • 2
5
votes
2 answers

What exactly happens when we call IterativeProcess.next on federated training data?

I went through the Federated Learning tutorial. I was wondering how .next function work when we call it on an iterative process. Assuming that we have train data which is a list of lists. The outer list is a list of clients and the inner lists are…
Sharare Zehtabian
  • 53
  • 3
5
votes
1 answer

Tensorflow Federated | tff.learning.from_keras_model() with a model with DenseFeature layer and multiple inputs

I am trying to federate a keras model which has multiple inputs. These some of these inputs are categorical and some of them are numerical, so I have some DenseFeature layers to embed the values. The problem is that using …
Alex
  • 245
  • 3
  • 12
4
votes
1 answer

Build Custom Federated averaging process with ValueError: Layer sequential expects 1 inputs, but it received 3 input tensors

i am trying to load a dataset from csv and perform some federated learning on the available data. i manage to load a federated dataset from a given csv file and load both the train and the test data. My question now is how to reproduce a working…
Mixalis Navridis
  • 181
  • 2
  • 15
4
votes
1 answer

Can Tensorflow Federated be installed on Apple Silicon M1?

I want install Tensorflow Federated in a macOS with Apple Silicon M1. I have tried installing Python 3.9.1 with pyenv and create a virtual environment. Then I installed the package. pip install tensorflow-federated Some errors raised because of…
jtr109
  • 94
  • 1
  • 7
4
votes
1 answer

TensorFlow Federated: How to tune non-IIDness in federated dataset?

I am testing some algorithms in TensorFlow Federated (TFF). In this regard, I would like to test and compare them on the same federated dataset with different "levels" of data heterogeneity, i.e. non-IIDness. Hence, I would like to know whether…
Alessio Mora
  • 276
  • 2
  • 10
4
votes
1 answer

How to load Fashion MNIST dataset in Tensorflow Fedarated?

I am working on a project with Tensorflow federated. I have managed to use the libraries provided by TensorFlow Federated Learning simulations in order to load, train, and test some datasets. For example, i load the emnist dataset emnist_train,…
Panagiotis Drakatos
  • 2,851
  • 4
  • 31
  • 43
4
votes
2 answers

Change of the dataset type in the execution stack

The problem is the change of the dataset from one type to another during different points of the execution stack. For example, if I add a new dataset class with more member properties of interest (which inherits from one of the classes in…
Ahmed Sayed
  • 43
  • 4
4
votes
1 answer

TFF Federated Learning, Evaluation Approach

Validating with typical AI/ML models is predicated on all the data being available locally. Splitting the data into e.g. 80/20 % split, 80% data for training, and 20% for test/evaluation. This scenario isn’t applicable to the FL paradigm. Using…
colin byrne
  • 81
  • 1
4
votes
1 answer

Implement data generator in federated training

(I have posted the question on https://github.com/tensorflow/federated/issues/793 and maybe also here!) I have customized my own data and model to federated interfaces and the training converged. But I am confused about an issue that in an images…
miaoz18
  • 41
  • 2
4
votes
1 answer

Is Tensorflow Federated-Learning only for simulating federated learning on one machine?

I read multiple guides on https://www.tensorflow.org/federated/federated_learning e.g. the image classification or text generation example. From what I have read I can not see how to use tensorflow federated-learning (tff) for a real world…
ovae
  • 129
  • 7
3
votes
1 answer

Accuracy does not increase in Tensorflow Federated Learning

I am running the code in tensorflow federated learning (10 epochs, 100 rounds), but the accuracy is not increasing and it's around 0.5. Part of my code is as follows: def create_compiled_keras_model(): layer1 =…
Dushi Fdz
  • 161
  • 3
  • 22
3
votes
0 answers

Pass y_true for Confusion Matrix of federated learning model

I am building a multi-classification federated learning model using TensorFlow. And I want to generate a confusion matrix for my model, but I don't know how to find the y_true and y_pred in my federated computation code. The federated computation…
Eden
  • 325
  • 3
  • 13
1
2 3
…
27 28