Comments (3)
Below is my configuration:
mnist = MNIST(data_root="./data", train_bs=32, num_clients=100) # built-in federated MNIST dataset
configuration parameters
conf_params = {
"dataset": mnist,
"aggregator": "krum", # aggregation
"aggregator_kws": {"num_clients": 100, # attacker parameters
"num_byzantine": 10},
"num_byzantine": 10, # number of Byzantine input
"attack": "noise", # attack strategy
# "attack_kws": {"num_clients": 100, # attacker parameters
# "num_byzantine": 10},
"num_actors": 4, # number of training actors
# "num_actors": 10, # number of training actors
"use_cuda": False,
"gpu_per_actor": 0.,
"seed": 1, # reproducibility
}
from blades.
Hi, this is because the dataset is dumped into a file to avoid unnecessary reconstruction. The code immediately loads the cache file if it exists. But we forgot to compare the detailed information with the new configuration. We will fix this issue soon.
So far, there is a quick solution to make it work: you can remove the "MNIST.obj" files in the data_root folder so that the dataset will be separated into your desired number of partitions.
from blades.
Thank you for your answer.
from blades.
Related Issues (20)
- [Feature] Support for configuration file
- Thanks for this AWESMOE platform HOT 1
- example/mnist_example.py HOT 2
- Example for Custom Attacker? HOT 1
- Consine Distance OR Consine Similarity? HOT 2
- How to install blades HOT 1
- Please add LFR and UNION of Fang's paper
- about the problem running the todo_cifar10_gpu.py HOT 2
- Awesome work!! HOT 2
- Outdated Examples HOT 3
- Adaptive Attacks: FangAttack
- Can python 3.8 install blades? HOT 1
- can u upload the new version or new simulation example?
- example question HOT 2
- How to run fltrust based on fedavg HOT 1
- about the experiments' result HOT 4
- runtime error
- Configuration file dataset config always uses IID splitter HOT 3
- Difference between the two versions of signflipping?
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from blades.