Running flw baseline fedAVG_MNIST with recommended parameters on README gives accuracy better than the paper "best result" #3235
Labels
documentation
Improvements or additions to documentation
Describe what the documentation is missing.
On this part https://github.com/adap/flower/tree/main/baselines/flwr_baselines/flwr_baselines/publications/fedavg_mnist there is a README suggesting to run the code with
python main.py num_epochs=5 num_rounds=1000 iid=True
. When I did using the suggested string but with num_rounds=100 , I got a result plot with a baseline better than the "paper best result". I'm running locally in a Macbook M1 MaxSuggest your improvement.
I think is very confusing to have received a result plot with an accuracy better than the "paper best result". So I think an explanation on the README of
![image](https://private-user-images.githubusercontent.com/20215131/320294940-470f32b9-0d39-4ec1-8761-4557184469fa.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.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.WmhQ8sTiJL76ms85-mty8SlKkTyIvmUIbk5sOsXlhTU)
flwr_baselines/publications/fedavg_mnist
about this case will be nice.The text was updated successfully, but these errors were encountered: