Closed khawar-islam closed 1 year ago
Hello, yes it's right. It's due to the step learning rate scheduling at 120 epoch. The vanilla training has the same accuracy increase patterns.
The smooth learning rate scheduling, such as cosine or polynimial, results in the smooth increase in accuracies, however it will have the similar converged performance.
Dear @Janghyun1230,
I am training simple WRN28-10 to reproduce your paper results mentioned in Table 2. After 120 epoch, accuracy is directly jumped to 69 to 79%. Is that correct?![image](https://user-images.githubusercontent.com/11488932/212609406-65b9c280-71b2-457f-8b8d-d1b238efdb69.png)
python3 main.py --arch wrn28_10 --dataset cifar100 --epochs 200 --schedule 120 170 --learning_rate 0.2