Francisco J. Solis
Francisco J. Solis
Bumped as this is very relevant and could bring more developers to the project. Related pull request for this issue is https://github.com/adap/flower/pull/816. ## gRPC C++ Client We could use our...
Could you kindly share the error line? as it contains module information. Thank you.
Certainly the model is loaded in the _Android_ client side as shown in the next source code portion of `examples/android/client/app/src/main/java/flwr/android_client/TransferLearningModelWrapper.java`: ```java TransferLearningModelWrapper(Context context) { model = new TransferLearningModel( new AssetModelLoader(context,...
On the question about **why the federated learning is over after a certain number of rounds?** The answer to that is found at the `num_rounds` configuration parameter for the server;...
As you wisely pointed out, we are really returning parameters from the `FedAvg` (which is the super class for this strategy) `aggregate_fit()` function as it could be seen in `src/py/flwr/server/strategy/fedavg.py:257`....
Is this proposal somehow related to https://github.com/tf-encrypted/tf-encrypted project? It that is the case we could clone our `examples/quickstart_tensorflow` into `examples/quickstart_tensorflow_encrypted` to use the syntax shown in the https://github.com/tf-encrypted/tf-encrypted/tree/master/examples/mnist example project.
The _FedProx_ baseline should be implemented as pointed out in https://flower.dev/docs/using-baselines.html. However, I could not find the cited folder `flower/baselines/flwr_baselines/publications/fedprox/system_heterogeneity` in any branch. However, I could find the following reference...
As you pointed out, we currently have the next FitIns definition: ```python @dataclass class FitIns: """Fit instructions for a client.""" parameters: Parameters config: Dict[str, Scalar] ``` In this sense, we...
We need to ensure that the changes do not affect the native client execution for _Raspberry Pi_ and _Jetson_ by testing under those environments, could you please check it up...
It seems that the _Docker image_ is not based on your current platform. Could you gently show a `docker version` output so we could know about the OS/Arch of your...