Can only achieve 93% accuracy on CIFAR10

quark0 / darts

Differentiable architecture search for convolutional and recurrent networks

https://arxiv.org/abs/1806.09055

Apache License 2.0

3.92k stars 843 forks source link

Closed tianyic closed 1 year ago

tianyic commented 1 year ago

Thanks for the great work!

I tried to reproduce the accuracy that reported in the paper on CIFAR10. But I only obtained around 93% accuracy via running

python train.py --auxiliary --cutout

Any idea how to recap the significant accuracy gap? Thanks! My experiment setting is A100 server torch 1.13.