Residual Network Experiments with CIFAR Datasets.

Update(2018/06/15)

We used a new learning rate scheduler called HTD.
You can see the toy demo code here or our papar in arXiv.

Original Repository

This repository is about some experiments of learning rate with CIFAR-10 & CIFAR-100.

The original paper start with a learning rate of 0.1, divide it by 10 at 32k(81 epoch) and 48k(122 epoch) iterations, and terminate training at 64k iterations(200 epochs total).

I ran other experiments based on the same architecture. The only difference is learning rate schedule.
All of the tensorboard logs & pretrained models are available at BIGBALLON/pretrained_models

How to run

You can run the script run.sh to start all the experiments.
Or just run the command like:

python3 ResNet_keras.py --epochs 200 --stack_n 3  --lr_scheduler 1 --dataset cifar100

Accuracy of Experiments

Please feel free to contact me if you have any questions! 😸