diaoenmao/HeteroFL-Computation-and-Communication-Efficient-Federated-Learning-for-Heterogeneous-Clients

Model training on custom dataset

Closed this issue · 5 comments

chillum-codeX commented

Hey
I wants to do a custom model training
For example taking covid, Ctscan and Mri data
Can you please guide me

diaoenmao commented

I think you can write your own dataset files like the ones in ./dataset/mnist.py, ./dataset/cifar.py. A more clear pipeline I used can be found in RPipe.

chillum-codeX commented

Hey
thanks for reply
can you provide an example with COVID Images dataset
how can we train the moel on covid images and CT MRI dataset
please proovie a running script , it would be great and helpful for me

diaoenmao commented

Sorry. I don't have access to these resources.

chillum-codeX commented

Hey
this is the resource link for data
i need an working idea rest i will do
https://github.com/ml-workgroup/covid-19-image-repository

diaoenmao commented

Sorry. I think this is beyond the scope of this repository. The source code only provides support for datasets used in the paper.