- Prototyping for FLHub
- FLHub server
- FLHub CLI client
- Centralized vs. Federated
- The number of clients
- Data type: Balanced / NonIID
-
Protobuf generator
python3 01-create_protobuf.py
-
Dynamic classification model
- Model ckpt saver / restorer
python3 00-Preprocessing.py
- Image with 375 x 4 x 1 from ip layer
02-TCBaselineCNN.ipynb
- Models
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
conv2d_1 (Conv2D) (None, 39, 37, 32) 320
_________________________________________________________________
flatten_1 (Flatten) (None, 46176) 0
_________________________________________________________________
dense (Dense) (None, 15) 692655
=================================================================
Total params: 692,975
Trainable params: 692,975
Non-trainable params: 0
pip3 install --upgrade -r requirements.txt
- Install scrcpy
- Preprocessing pcap files for creating feature vectors
python3 01-preprocess.py -i INPUTDIR -o OUTPUTDIR
- Make dataset for federated learning
-
python3 02-...
pip3 install -r requirements.txt
- ...
Federated Optimization: Distributed Optimization Beyond the Datacenter Communication-Efficient Learning of Deep Networks from Decentralized Data
- LuHa ([email protected])