Stack Overflow
Stack Overflow

Questions tagged [federated-learning]

167 questions
2
votes
1 answer

MSE error different during training and evaluation in tensorflow federated

I am implementing a regression model in tensorflow federated. I started with a simple model used in this tutorial for keras: https://www.tensorflow.org/tutorials/keras/regression I changed the model to use federated learning. Here is my…
kosmo16
  • 166
  • 11
2
votes
1 answer

Operations performed on the communications between the server and clients

Part of federated learning research is based on operations performed on the communications between the server and clients such as dropping part of the updates (drop some gradients describing a model) exchanged between clients and server or…
Schneider
  • 67
  • 4
1
vote
1 answer

ERROR: Could not find a version that satisfies the requirement torchvision~=0.5.0 (from syft)

Last week iam working with syft==0.2.9 and it was working great! but this week when i tried to install syft==0.2.9 i have this error "ERROR: Could not find a version that satisfies the requirement torchvision~=0.5.0 (from syft) (from versions:…
Nwadher
  • 11
  • 1
1
vote
0 answers

why is api calls from the pysyft library causing a ModuleNotFoundError?

I am trying to work on a federated learning project and I am just at the beginning. I tried to import a class called "BaseDataset" from the pysyft library as shown in the following. import syft.frameworks.torch.fl.dataset as st dataset =…
Tomas
  • 11
  • 1
1
vote
0 answers

ImportError: sys.meta_path is None, Python is likely shutting down; OverflowError: timeout doesn't fit into C timeval; Exception in thread Thread-1

I got a series of error messages, the last one being the one mentioned first in the title, while I was trying to run this Github repo on my local machine. I need that project as a boilerplate for my own code later. I have pasted the dependencies and…
1201 Mansoor
  • 11
  • 2
1
vote
0 answers

Sending PyTorch model weights over network in a compressed manner

I have a PyTorch model that I am trying to integrate federated learning for. In order to do this, I need to send the model weights back and forth between a server and a client. When I get the size of the model weights, it is approximately 6kb, but…
ditty
  • 11
  • 1
1
vote
0 answers

Noise addition to weights using Opacus in a Federated Learning setting

I am planning to use Opacus to implement differential privacy in my federated learning model but I have a very basic doubt that I would love to have cleared before that. So as far as my understanding goes, using Opacus, we use an optimizer like…
Anirban Nath
  • 41
  • 1
  • 4
1
vote
1 answer

AttributeError: module 'syft' has no attribute 'FederatedDataLoader'

I have just started using pysyft to implement federated-learning. While following one of the tutorials, I got stuck on an error: Code which I have used: import torch import torch.nn as nn import torch.nn.functional as F import torch.optim as…
onapte
  • 217
  • 2
  • 8
1
vote
1 answer

TypeError: Expected keras.losses.Loss, found function

I want to build a TFF model for speech recognition systems. For this, I use the CNN-GRU model architecture with a CTC loss function. but I got error when I wanted to build_federated_averaging_process and think it's about the ctc_loss function but I…
hamid ebrahimi
  • 51
  • 5
1
vote
0 answers

How to build a federated system with CSV dataset with SparkNL library?

I am very interested in federated systems and i was trying one of the pre trained multilingual models such as this notebook Multi_Lingual_Training_and_models. I was looking for any tutorials using TFF or Flower frameworks that handle csv…
Kareem Shehata
  • 11
  • 2
1
vote
1 answer

How to save weights in tensorflow federated

I want to save weights only when loss is getting lower and reuse them for evaluation. lowest_loss = Inf if loss[round] < lowest_loss: lowest_loss = loss[round] model_weights =…
ana
  • 58
  • 4
1
vote
1 answer

Is it against privacy of clients if I have a global tokenizer in Federated Learning (TFF)?

I am currently stuck in a dead end. I am trying to make an image caption generator from a federated approach. My initial idea was to have a different tokenizer for each client. That poses these issues however: Every client will have a different…
ChaoS Adm
  • 715
  • 1
  • 5
  • 12
1
vote
1 answer

Why can't I see the local epochs output when training tensorflow federated learning model?

I am training a tensorflow federated learning model. I cannot see the output of epochs. Details are as follows: split = 4 NUM_ROUNDS = 5 NUM_EPOCHS = 10 BATCH_SIZE = 2 PREFETCH_BUFFER = 5 for round_num in range(1, NUM_ROUNDS+1): state,…
Dushi Fdz
  • 161
  • 3
  • 22
1
vote
0 answers

[flwr][sklearn] Trying to use Gradient Boosted Trees

for some day's now I try to implement gradient boosted tree's with flwr. I tried the example given by flwr. They use a LogisticRegression Model for the classification of MNIST, which works in my setup. This is where my problem arise: Simply…
Elias
  • 11
  • 1
1
vote
1 answer

How to access labels with TFF

I was following this Image classification tutorial and Text Generation tutorial. So I've implemented transfer learning with fine-tuning on my dataset but I don't know how to access labels whenever I am doing predictions. I transformed my data into…
ana
  • 58
  • 4
1 2
3
…
11 12