Stack Overflow
Stack Overflow

Questions tagged [federated-learning]

167 questions
1
vote
1 answer

Pysyft Federated learning, Error with Websockets

I am trying to run a federated learning from pysyft (https://github.com/OpenMined/PySyft/blob/dev/examples/tutorials/advanced/websockets-example-MNIST-parallel/Asynchronous-federated-learning-on-MNIST.ipynb) that creates remote workers and connect…
santhosh mohan
  • 43
  • 6
1
vote
2 answers

ResNet model in Tensorflow Federated

I tried to customize the model in "Image classification" tutorial in Tensorflow Federated. (It originally used a sequential model) I use Keras ResNet50 but when it began to train, there is always an error "Incompatible shapes" Here are my…
Miao Zhang
  • 31
  • 1
  • 3
1
vote
1 answer

PureFrameworkTensorFoundError, Runtime error -FedeartedLearning

I am trying a Linear Regression algorithm with Federated learning using Pytorch and I face the following error. I am implementing it on Colab. According to me this error might be due to some code line in the train() function. Kindly help is you have…
COCO.J
  • 103
  • 2
  • 6
1
vote
1 answer

ValueError: The name "Sequential" is used 4 times in the model. All the layer names should be unique?

Let's consider, I have four models following as M1 (client 1), M2 (client 2), M3 (client 3), and M4 (client 4). Each model has a similar structure. Model Structure After training for each client model. I have aggregated these models together and…
Mahedi Hasan Jisan
  • 89
  • 1
  • 6
1
vote
2 answers

How to implement my own federated algorithm Usinsg tensorflow federated

I have read all the documents on the tensorflow federated available at tensorflow.org, but I am not sure how to implement my own federated algorithm. For example, I have a compiled keras model, I know how to convert this to tff.computation. It seems…
Mahdi Morafah
  • 29
  • 3
1
vote
1 answer

How to use TFF api's for custom usage?

I have read and studied the TFF guide and APIs pages precisely. But I am confused in some detail parts. For example, when I want to wrap/decorate a TF/python function, use these two below APIs: 1. tff.tf_computation() 2.…
user10985800
0
votes
0 answers

Could not connect to the docker container

I have a federated server (flower framework) running in a docker container in the raspberry pi device in the same network as the client (My laptop). The client is not able to establish a connection with the server. Raspberry pi host ip address:…
Karthik R
  • 1
0
votes
0 answers

Federated Learning: Flower Client is not connectiong to Server in Encrypted Overlay Network with Docker Swarm on Google Cloud VMs

I want to set up federated learning with the python package flwr (https://flower.dev/). For this purpose I use Docker Swarm on Google Cloud (3 VMs, 1 server/manager, 2 clients/workers, all based on the docker image python:3.9-slim). I use an overlay…
Hans H.
  • 53
  • 5
0
votes
0 answers

Add Edge computing server between the clients and server

I am trying to add a Edge Computing layar between Clients and server in flwr. I realized there is a problem here afterwhile. The first messages communicate properly but the FL procedure not started and stucks. My edge code: edge_server =…
Amir Hosseini
  • 11
  • 3
0
votes
0 answers

Pytorch: Calculating the loss with respect to alpha, which is a nn.Paramter

I am trying to implement the following algorithm . In step 18, the gradient of the loss with respect to alpha is being computed and when i try to access this .grad atribute for alpha, I get None, which means that there is no gradient computed for…
aks
  • 25
  • 6
0
votes
1 answer

Is there an library to get weights of each local model every round of Federated Learning?

In federated learning, I want to get weights of each local model every round, then I will cluster local clients based on their weights, but I can just use training_process.get_model_weights(train_state) to get global weights only. I did use…
baodvo
  • 1
0
votes
1 answer

Cannot install shfl in python

I am trying to use shfl python library. When I import shfl, I get the error ModuleNotFoundError: No module named 'shfl', and apparently I cannot install it. I have used three following commands and all are unsuccessful with the errors I mention…
azLe
  • 19
  • 3
0
votes
0 answers

How can i convert my dataset which works exactly same as the tff.simulation.datasets.emnist.load_data() dataset?

How can i convert my dataset which works exactly same as the tff.simulation.datasets.emnist.load_data() dataset? Is there any predefined function that will do the job with my dataset? I have parkinson drawing dataset from kaggel which have two type…
Shihab Kamel
  • 1
0
votes
1 answer

Choosing the optimal network communication protocol for Federated Learning with TFF

I am working on a federated learning project for my university, and my goal is to implement it using TensorFlow Federated (TFF) to enable collaboration among multiple clients. However, TFF currently only supports simulation on a single machine, and…
Milos Jovanovic
  • 47
  • 3
  • 7
0
votes
0 answers

Differential Privacy error in PyTorch using Opacus PrivacyEngine - how to troubleshoot?

The problem of the given code is: line 25, in privacy_engine = PrivacyEngine(model, batch_size=64, sample_size=60000, alphas=range(2,32), noise_multiplier=1.3, max_grad_norm=1.0) TypeError: __init__() got an unexpected keyword argument…
Abdus Sahid
  • 1
  • 4
1 2 3
…
11 12