One Cycle¶
Category: optimization.scheduler.generic
Version: 1.0.0
UUID: 4f16fde207844ea92f67ea379e3c364ac2bf72c23626a678917c3714f0f2e7ae
Execution context: leip_af
Choice Priority: 100.0
Value Parameters¶
| Name | Synonyms | Type | Values | Help |
|---|---|---|---|---|
| Div Factor | optimization.scheduler.initial_learning_rate_divisor |
scalar | float, min: 1.0 | Determines the initial learning rate via initial_lr = max_lr/div_factor. Refer here for more details. |
| Final Div Factor | optimization.scheduler.final_learning_rate_divisor |
scalar | float, min: 1.0 | Determines the minimum learning rate via min_lr = initial_lr/final_div_factor. Refer here for more details. |
| Percentage of Cycle increasing LR | optimization.scheduler.percentage_cycle_increasing_learning_rate |
scalar | float, min: 0.0, max: 1.0 | The percentage of the cycle (in number of steps) spent increasing the learning rate. Refer here for more details. |
This component fits into¶
| Name | UUID | Synonyms |
|---|---|---|
| EfficientDet | 39e6c2... |
optimization.scheduler |
| NanoDet | 447eea... |
optimization.scheduler |
| DeepLab v3 + | 3c98d2... |
optimization.scheduler |
| SSD | 0aefd3... |
optimization.scheduler |
| U-Net | 77f467... |
optimization.scheduler |
| PSPNet | fcb1a3... |
optimization.scheduler |
| Yolo v5 | 033e98... |
optimization.scheduler |
| UL Yolo v5 | 338ee9... |
optimization.scheduler |
| Classifier | 1ac7e3... |
optimization.scheduler |