Learning Rate Schedules
Step Decay
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
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Object Detection | 39 | 18.14% |
| Image Classification | 38 | 17.67% |
| General Classification | 17 | 7.91% |
| Object | 16 | 7.44% |
| Semantic Segmentation | 11 | 5.12% |
| Classification | 8 | 3.72% |
| Real-Time Object Detection | 6 | 2.79% |
| Object Recognition | 6 | 2.79% |
| Instance Segmentation | 5 | 2.33% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
