Learning-Rate-Dropout
Pytorch implementation of Learning Rate Dropout.
Paper Link: https://arxiv.org/pdf/1912.00144.pdf
Train ResNet-34 for Cifar10:
run:
python main.py --model=resnet --optim=adam_lrd --lr=0.001 --LRD_p=0.5
python main.py --model=resnet --optim=adam --lr=0.001
python main.py --model=resnet --optim=sgd_lrd --lr=0.1 --LRD_p=0.5
python main.py --model=resnet --optim=sgd --lr=0.1
python main.py --model=resnet --optim=rmsprop_lrd --lr=0.001 --LRD_p=0.5
python main.py --model=resnet --optim=rmsprop --lr=0.001
After training, run "plot.py" to show the learning curves.
3.9k Dec 20, 2022
45 Nov 09, 2022
2 Jan 25, 2022
4 Sep 20, 2022
42 Dec 13, 2022
10 Jul 16, 2022
1.7k Jan 06, 2023
269 Nov 15, 2022
1.6k Jan 08, 2023
39 Jan 01, 2023
6 Nov 18, 2022
53 Nov 16, 2022
9 Mar 30, 2022
136 Jan 08, 2023
119 Jan 04, 2023
29 Nov 25, 2022
13 Nov 19, 2022
117 Dec 09, 2022
32 Nov 03, 2022
31 Oct 10, 2022