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.
81 Nov 22, 2022
310 Dec 13, 2022
4 Jul 21, 2022
24 Oct 26, 2022
10 Nov 30, 2022
158 Dec 21, 2022
956 Dec 19, 2022
2 Dec 19, 2022
8 Oct 07, 2022
6 Sep 28, 2022
1 Dec 06, 2022
7 Apr 17, 2022
45 Oct 07, 2022
220 Jan 05, 2023
101 Nov 09, 2022
79 Dec 01, 2022
2 Feb 03, 2022
111 Dec 13, 2022
47 Nov 02, 2022
1k Jan 01, 2023