Yuang Jiang
Yuang Jiang
Hi @wizard1203, we simply use the first 100 classes of ImageNet. Sorry for the delayed response.
@lahmuller Thanks for the question. In our documentation (also see our Arxiv paper Section C.3), we stated >extension: the extension.cpp c++ file extends the current PyTorch implementation with sparse kernels...
@Karry-Xu We experimented the models mentioned in our paper on Raspberry Pi (version 4), where packaged such as MKL are automatically not used since Pi's use Arm-based CPUs. In the...
@Karry-Xu Sorry for the late response! Please find our simulation code here: https://github.com/jiangyuang/PruneFL