[Q&A] NVFlare/tree/main/research/quantifying-data-leakage cifar10

[mstc-xqp]

Python version (python3 -V)

3.10

NVFlare version (python3 -m pip list | grep "nvflare")

2.5

NVFlare branch (if running examples, please use the branch that corresponds to the NVFlare version, git branch)

2.5

Operating system

22.04

Have you successfully run any of the following examples?

• hello-numpy-sag with simulator
• hello-pt with simulator
• hello-numpy-sag with POC
• hello-pt with POC

Please describe your question

I run into the following issue and don't know what to do ...
"I'd like to modify this project to work with the CIFAR-10 dataset instead of the chest X-ray dataset. Could you help me adapt the code for CIFAR-10?"

[chesterxgchen]

@holgerroth

[holgerroth]

Hi, sorry for the late reply. You should be able to run the code using the CIFAR10Learner instead of CXRLearner. You can take the cifar 10 code from here. Just make sure that the inversion code uses the same model architecture as your learner code.