Questions tagged [federated-learning]
167 questions
0
votes
1 answer
Error while executing federated learning text generation tutorial in Colab
I am trying to follow this tutorial on federated learning TensorFlow and when executing this line I get an error:
train_data, test_data = tff.simulation.datasets.shakespeare.load_data()
The error:
Downloading shakespeare.sqlite.lzma: …
user8421958
- 15
- 4
0
votes
1 answer
How to split the dataset into train and test based on client number using "Federated learning"
I try to use np.array.split to split the dataset into 2 part, but it does not work well
Hope some one can give some advice on this issue
x` (images tensor) and `y` (labels) should have the same length. Found: x.shape = (14218, 32, 32, 3), y.shape =…
Jovan Mei
- 15
- 5
0
votes
1 answer
LSTM sequence prediction overfits on one specific value only
hello guys i am new in machine learning. I am implementing federated learning on with LSTM to predict the next label in a sequence. my sequence looks like this [2,3,5,1,4,2,5,7]. for example, the intention is predict the 7 in this sequence. So I…
user9137963
- 105
- 9
0
votes
2 answers
Converting CSV file data into federated data
I am trying to convert my CSV dataset into a federated data. Please find the code and the error I am getting while I am running my code
code: import collections
import numpy as np
import pandas as pd
import tensorflow as tf
import…
0
votes
2 answers
Using dart pigeon in a federated model
I"m looking at converting a dart package (https://pub.dev/packages/sounds) to a federated model using pigeon.
The documentation around combing these two pieces is a little sparse.
Looking at the video_player sample…
Brett Sutton
- 3,900
- 2
- 28
- 53
0
votes
1 answer
AttributeError: 'WebsocketServerWorker' object has no attribute 'add_dataset'
When I using pysyft to do some Federated Learning task, there is an error:
AttributeError: 'WebsocketServerWorker' object has no attribute 'add_dataset'
def start_websocket_server_worker(id, host, port, hook, verbose, training, dataset,…
gle Goo
- 1
0
votes
1 answer
tf_encrypted.player how to config?
While training the model federated learning with keras on syft,to start workers on different system as client workers, particular line of command to be exectued on terminal.
python -m tf_encrypted.player --config /tmp/tfe.config client name
this…
maddy23
- 138
- 2
- 13
0
votes
2 answers
Low evaluation accuracy of Resnet in TensorFlow Federated
I implemented Resnet34 model in federated images classification tutorial. After 10 rounds the training accuracy can be higher than 90%, however, the evaluation accuracy using the last round's state.model is always around 50%.
evaluation =…
miaoz18
- 41
- 2
-1
votes
0 answers
Unity mlagents training models on drive
I have thinking of a project where i will train AI in unity using Imitation Learning where models learn from the players movement and all. The model which was trained from player's movement will be saved on the web server like Google Drive or…
-1
votes
0 answers
Plot the accuracy and loss of the model
Hello how can i plut in this code. I want to graph the performance of the model on the train and test sets recorded during training using a line plot, one for each of the loss and the classification accuracy.
This is federeted learning. Please…
Ariaeimehr
- 3
- 3
-1
votes
1 answer
How Federated Learning would help to centralise Hospitals and clinical data cohorts (databases)? Especially Electronic Health Records datasets
What are the libraries we can use for federated learning process?
what are the data encryption techniques used to protect datasets?
I studied some articles and blogs but in health sector it's difficult to implement because health organisations are…
irfanRala
- 3
- 3
-1
votes
1 answer
I'm getting an **NumPyClient.fit did not return a tuple with 3 elements.** error when I run client.py file. What could be the problem?
I am using the Flower code example to try POC of Federated Learning but I keep getting the error below when I run the client.py file:
INFO flower 2022-07-04 15:27:37,301 | connection.py:102 | Opened insecure gRPC connection (no certificates were…
Frederico23
- 23
- 9
-1
votes
1 answer
Accuracy decreasing after iteration in federated learning setting
I am working on a federated learning to detect bad clients.
Brief about federated learning - Data is divided into various clients, training is done on client side and the results are then sent by each client to central server where aggregation of…
boost_insane
- 3
- 2
-1
votes
1 answer
Tensor Size Miss match on loss function
1:
when attempting to perfrom a pytorch training sequence using batch sizes, my loss function appears to error when the nn output and a batch are put through a MSEloss function.
2:
have tried to search about nn padding, however this is not a covnet…
GIGA-Money
- 33
- 6
-3
votes
1 answer
TypeError: expected at most 1 arguments, got 2....... data = collections.OrderedDict('data', distributed_data[i])
I am getting the following error related to this function definition what is wrong?
Convert_to_client_data() is a function in federated learning where I am trying to convert a dataset into the federated dataset.
Here is the declaration of the class…
divya reddy
- 1
- 2