Stack Overflow
Stack Overflow

Questions tagged [federated-learning]

167 questions
0
votes
0 answers

IBM-federated-learning-lib_ModuleNotFound: No module named 'examples.constants'

for some days I got in touch with the IBM federated learning library from github. After finishing the setup, I wanted to run the files for the aggregator and parties in my jupyter notebook and ran into a ModuleNotFoundError as you can see on the…
Solaris
  • 11
  • 1
0
votes
0 answers

How to solve the Non-IID problem in Federated learning if we do not care about the communication overhead?

It seems that recent studies focued on how to minimize the communication overhead of Federated Learning and also improve the accuracy of models when facing NIID problems. However, compared with MPC, FL is quite effective. Thus, I am wondering…
Xinyu Tu
  • 36
  • 2
0
votes
0 answers

How do I resolve the error "IndexError: Dimension out of range (expected to be in range of [-1, 0], but got 1)"?

I tried my best to make a minimal reproducible example: there's an issue in my train() function where on the line output = model(data); I get the error IndexError: Dimension out of range (expected to be in range of [-1, 0], but got 1). I also get an…
S. Coughing
  • 176
  • 1
  • 11
0
votes
0 answers

Implementation of FedAvg used network in Communication Efficient Learning of Deep Networks from Decentralized Data

How to implement the network used in this paper, the only description of it is: "A CNN with two 5x5 convolution layers (the first with 32 channels, the second with 64, each followed with 2x2 max pooling), a fully connected layer with 512 units and…
SJ Chen
  • 1
  • 1
0
votes
0 answers

Adaptive top-k selection in machine learning

In federated/ distributed learning, the server will send initially a global model to clients, and each client will train the model locally and then select the top k values, and send only these values to the server. How I can select an adaptive k in…
user18969005
  • 87
  • 6
0
votes
1 answer

Federated learning

I have two kinds of covid 19 datasets as two clients (the first one ST Scan images and the second is XRays images) and I use federated learning approch. The question is can I use those dataset as two clients although they have different type to…
Madeleine Alabdah
  • 1
  • 1
0
votes
1 answer

Tensorflow Federated Learning on ResNet failse

I do some some experiments with the tensorflow federated learning API. Actualy I try to train a simple ResNet on 10 Clients. Based on the data and metrics, the training seems to be successful. But the evaluation as well as local and federated…
manuel
  • 1,127
  • 1
  • 8
  • 15
0
votes
1 answer

When switching from federated to centralized dataset -Error may indicate that you're trying to pass a Tensor to a NumPy call

I'm trying to switch from a federated setting to centralized learning. I've created a federated dataset, but I want to create a dataset for centralized learning with the create_tf_dataset_from_all_clients function. When I googled the error I found…
ana
  • 58
  • 4
0
votes
1 answer

unable to list "extensions/v1beta1, resource=ingresses

I was trying to use kubeFate with version 1.3.0 but after I applied the service with its original file as kubectl apply -f ./kubefate.yaml, it pops out the error saying Error from server (NotFound): Unable to list "extensions/v1beta1,…
CKJ
  • 9
  • 3
0
votes
1 answer

How can I use transfer learning in federated learning?

I tried to implement federated learning. (Using TensorFlow federated core) def create_keras_model(): model = Sequential() model.add(Conv2D(16, kernel_size=(3,3), strides=(1,1), padding='same', activation='relu', input_shape=(226,232,1))) …
hamid ebrahimi
  • 51
  • 5
0
votes
1 answer

Missing required positional argument:

I tried to implement federated learning based on the LSTM approach. def create_keras_model(): model = Sequential() model.add(LSTM(32, input_shape=(3,1))) model.add(Dense(1)) return model def model_fn(): keras_model =…
hamid ebrahimi
  • 51
  • 5
0
votes
1 answer

Accuracy 0% for binary classification

I am using the OpenFL framework for doing Federated Learning experiments. I run their tutorial notebooks without problems, so for example I am able to run classification on MNIST and everything is ok. Now I am using 2 clients with 2 different…
CasellaJr
  • 378
  • 2
  • 11
  • 26
0
votes
1 answer

Flower Framework is not showing federated loss

I am trying to use federated learning framework flower with TensorFlow. My code seems to compile fine but It's not showing federated loss and accuracy. What am I doing wrong? ServerSide Code : import flwr as fl import sys import numpy as np class…
Aurthur
  • 43
  • 5
0
votes
0 answers

Keras: How to save GAN model with optimiser state?

I know one use can be using Checkpoint and CheckpointManager tensorflow classes to save and resume training the GAN. I am looking for a way to save the Generator (G) , Discriminator(D) and their optimisation states such that I can manipulate the…
Bhavesh Neekhra
  • 1
  • 3
0
votes
1 answer

TypeError: __init__() got an unexpected keyword argument 'intialize_fn'

I use TFF v:0.18 I would like to load a pretrained network in the inside of create_keras_model() So I write this : def create_keras_model(): baseModel = tf.keras.models.load_model(model_path, compile=False) headModel = baseModel.output …
seni
  • 659
  • 1
  • 8
  • 20
1 2 3
…
11 12