-
class
DecayOnStep(decay_ratio: float, decay_freq: int) Bases:
ai4med.components.lr_policies.lr_policy.LRPolicyReduce learning rate based on configured ratio and step frequency.
- Parameters
decay_ratio (float) – ratio of LR adjustment
decay_freq (int) – adjustment frequency in number of training steps
-
evaluate(train_ctx: ai4med.common.train_ctx.TrainContext) Compute the new LR.
The LR is adjusted to
current_lr * ratioevery decay_freq number of steps.- Parameters
train_ctx – training context
Returns: new LR value
-
class
LRPolicy Bases:
abc.ABCDefines the interface for Learning Rate (LR) Policy components
-
abstract
evaluate(train_ctx: ai4med.common.train_ctx.TrainContext) Compute the new learning rate based on information in train_ctx. This is the required method that a LRPolicy subclass must implement.
- Parameters
train_ctx – training contextual data
Returns: a new learning rate
-
abstract
-
class
ReduceCosine(rate=0.5) Bases:
ai4med.components.lr_policies.lr_policy.LRPolicyThis LR policy reduces the LR based on initial LR, current epoch and total number of epochs.
- Parameters
rate (float) – rate of reduction (Default: 0.5)
-
evaluate(train_ctx: ai4med.common.train_ctx.TrainContext) Computes the new LR value.
Implemented with the
ai4med.libs.lr_policies.cos_reducer.CosineReducer.reduce()- Parameters
train_ctx – training context
Returns: new LR value
-
class
ReduceOnPlateau(plateau_count_trigger: int, reduction_rate: float) Bases:
ai4med.components.lr_policies.lr_policy.LRPolicyReduce LR when validation metric stops improving.
- Parameters
plateau_count_trigger (int) – length of non-improving period
reduction_rate (float) – rate of LR reduction
-
evaluate(train_ctx: ai4med.common.train_ctx.TrainContext) Computes the new LR value.
Implemented with the ‘reduce’ method defined in the OnPlateauReducer class.
- Parameters
train_ctx – training context
Returns: new LR value
-
class
ReducePoly(poly_power) Bases:
ai4med.components.lr_policies.lr_policy.LRPolicy-
evaluate(train_ctx: ai4med.common.train_ctx.TrainContext) Compute the new learning rate based on information in train_ctx. This is the required method that a LRPolicy subclass must implement.
- Parameters
train_ctx – training contextual data
Returns: a new learning rate
-