https://github.com/unshun0120/apply-federatedlearning-into-autoencoder
Apply Federated Learning into Autoencoder and its variants to train their models
https://github.com/unshun0120/apply-federatedlearning-into-autoencoder
autoencoder federated-averaging federated-learning fully-connected-autoencoder mnist pytorch
Last synced: 8 months ago
JSON representation
Apply Federated Learning into Autoencoder and its variants to train their models
- Host: GitHub
- URL: https://github.com/unshun0120/apply-federatedlearning-into-autoencoder
- Owner: unshun0120
- Created: 2025-02-08T09:38:17.000Z (8 months ago)
- Default Branch: main
- Last Pushed: 2025-02-09T13:38:25.000Z (8 months ago)
- Last Synced: 2025-02-09T14:23:39.337Z (8 months ago)
- Topics: autoencoder, federated-averaging, federated-learning, fully-connected-autoencoder, mnist, pytorch
- Language: Python
- Homepage:
- Size: 32.2 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Apply Federated Learning into Autoencoder and its variants
this project is based on :
*Federated Learning*
+ https://github.com/AshwinRJ/Federated-Learning-PyTorch
*Autoencoder*
+ https://github.com/L1aoXingyu/pytorch-beginner/tree/master
---
## Before Running
1. Create a new folder called **"Dataset"** outside the downloaded folder
2. Create a new folder called **"logs"** outside the downloaded folder
3. Create a new folder called **"save_objects"** outside the downloaded folder
4. Create a new folder called **"save_models"** outside the downloaded folder
---
## Run
### Train (train.py include the test)
+ using CPU
```
python train.py
```
+ using GPU
```
python train.py --gpu=0
```
+ e.g. global epoch = 1, model = Convolutional Autoencoder
```
python train.py --gpu=0 --global_ep=1 --model=cnnae
```
### Test
+ using CPU
```
python test.py
```
+ using GPU
```
python test.py --gpu=0
```
+ e.g. test Autoencoder model
```
python test.py --gpu=0 --model=ae
```