Step Decay is a learning rate schedule that drops the learning rate by a factor every few epochs, where the number of epochs is a hyperparameter.
Image Credit: Suki Lau
Paper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Image Classification | 38 | 20.54% |
Object Detection | 37 | 20.00% |
General Classification | 17 | 9.19% |
Semantic Segmentation | 11 | 5.95% |
Classification | 8 | 4.32% |
Real-Time Object Detection | 6 | 3.24% |
Instance Segmentation | 5 | 2.70% |
Object Recognition | 5 | 2.70% |
Domain Generalization | 4 | 2.16% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |