AdaBelief

class lib.model.optimizers.adabelief.AdaBelief(params: Iterable, lr: float = 0.001, betas: tuple[float, float] = (0.9, 0.999), eps: float = 1e-16, weight_decay: float = 0.0, amsgrad: bool = False, weight_decouple: bool = True, fixed_decay: bool = False, rectify: bool = True, degenerated_to_sgd: bool = True)

Bases: Optimizer

Implements AdaBelief algorithm. Modified from Adam in PyTorch

Parameters:

params (Iterable) – Iterable of parameters to optimize or dicts defining parameter groups
lr (float) – Learning rate. Default: 1e-3
betas (tuple[float, float]) – Coefficients used for computing running averages of gradient and its square. Default: (0.9, 0.999)
eps (float) – Term added to the denominator to improve numerical stability. Default: 1e-16
weight_decay (float) – Weight decay (L2 penalty). Default: 0
amsgrad (bool) – Whether to use the AMSGrad variant of this algorithm from the paper On the Convergence of Adam and Beyond. Default: False
weight_decouple (bool) – If set as True, then the optimizer uses decoupled weight decay as in AdamW. Default: True
fixed_decay (bool) – This is used when weight_decouple is set as True. - When fixed_decay == True, the weight decay is performed as W_{new} = W_{old} - W_{old} * decay. - When fixed_decay == False, the weight decay is performed as W_{new} = W_{old} - W_{old} * decay * lr. Note that in this case, the weight decay ratio decreases with learning rate (lr). Default: False
rectify (bool) – If set as True, then perform the rectified update similar to RAdam. Default: True
degenerated_to_sgd (bool) – If set as True, then perform SGD update when variance of gradient is high. Default: True
Reference
---------
Optimizer (AdaBelief)
gradients (adapting step sizes by the belief in observed)
2020 (NeurIPS)
https (//github.com/juntang-zhuang/Adabelief-Optimizer)

Attributes Summary

`OptimizerPostHook`
`OptimizerPreHook`

Methods Summary

`add_param_group`(param_group)	Add a param group to the `Optimizer` s param_groups.
`load_state_dict`(state_dict)	Load the optimizer state.
`profile_hook_step`(func)
`register_load_state_dict_post_hook`(hook[, ...])	Register a load_state_dict post-hook which will be called after `load_state_dict()` is called. It should have the following signature::.
`register_load_state_dict_pre_hook`(hook[, ...])	Register a load_state_dict pre-hook which will be called before `load_state_dict()` is called. It should have the following signature::.
`register_state_dict_post_hook`(hook[, prepend])	Register a state dict post-hook which will be called after `state_dict()` is called.
`register_state_dict_pre_hook`(hook[, prepend])	Register a state dict pre-hook which will be called before `state_dict()` is called.
`register_step_post_hook`(hook)	Register an optimizer step post hook which will be called after optimizer step.
`register_step_pre_hook`(hook)	Register an optimizer step pre hook which will be called before optimizer step.
`reset`()	Reset parameters
`state_dict`()	Return the state of the optimizer as a `dict`.
`step`([closure])	Performs a single optimization step.
`zero_grad`([set_to_none])	Reset the gradients of all optimized `torch.Tensor` s.

Attributes Documentation

OptimizerPostHook: TypeAlias: alias of Callable[[Self, tuple[Any, …], dict[str, Any]], None]

OptimizerPreHook: TypeAlias: alias of Callable[[Self, tuple[Any, …], dict[str, Any]], tuple[tuple[Any, …], dict[str, Any]] | None]

Methods Documentation

add_param_group(param_group: dict[str, Any]) → None

Add a param group to the Optimizer s param_groups.

This can be useful when fine tuning a pre-trained network as frozen layers can be made trainable and added to the Optimizer as training progresses.

Parameters:: param_group (dict) – Specifies what Tensors should be optimized along with group specific optimization options.
Return type:: None

load_state_dict(state_dict: dict[str, Any]) → None

Load the optimizer state.

Parameters:: state_dict (dict) – optimizer state. Should be an object returned from a call to state_dict().
Return type:: None

Warning

Make sure this method is called after initializing torch.optim.lr_scheduler.LRScheduler, as calling it beforehand will overwrite the loaded learning rates.

Note

The names of the parameters (if they exist under the “param_names” key of each param group in state_dict()) will not affect the loading process. To use the parameters’ names for custom cases (such as when the parameters in the loaded state dict differ from those initialized in the optimizer), a custom register_load_state_dict_pre_hook should be implemented to adapt the loaded dict accordingly. If param_names exist in loaded state dict param_groups they will be saved and override the current names, if present, in the optimizer state. If they do not exist in loaded state dict, the optimizer param_names will remain unchanged.

Example

>>> # xdoctest: +SKIP
>>> model = torch.nn.Linear(10, 10)
>>> optim = torch.optim.SGD(model.parameters(), lr=3e-4)
>>> scheduler1 = torch.optim.lr_scheduler.LinearLR(
...     optim,
...     start_factor=0.1,
...     end_factor=1,
...     total_iters=20,
... )
>>> scheduler2 = torch.optim.lr_scheduler.CosineAnnealingLR(
...     optim,
...     T_max=80,
...     eta_min=3e-5,
... )
>>> lr = torch.optim.lr_scheduler.SequentialLR(
...     optim,
...     schedulers=[scheduler1, scheduler2],
...     milestones=[20],
... )
>>> lr.load_state_dict(torch.load("./save_seq.pt"))
>>> # now load the optimizer checkpoint after loading the LRScheduler
>>> optim.load_state_dict(torch.load("./save_optim.pt"))

static profile_hook_step(func: Callable[[_P], R]) → Callable[[_P], R]

Parameters:: func (Callable[[~_P], R])
Return type:: Callable[[~_P], R]

register_load_state_dict_post_hook(hook: Callable[[Optimizer], None], prepend: bool = False) → RemovableHandle

Register a load_state_dict post-hook which will be called after load_state_dict() is called. It should have the following signature:

hook(optimizer) -> None

The optimizer argument is the optimizer instance being used.

The hook will be called with argument self after calling load_state_dict on self. The registered hook can be used to perform post-processing after load_state_dict has loaded the state_dict.

Parameters:

hook (Callable) – The user defined hook to be registered.
prepend (bool) – If True, the provided post hook will be fired before all the already registered post-hooks on load_state_dict. Otherwise, the provided hook will be fired after all the already registered post-hooks. (default: False)

Returns:

a handle that can be used to remove the added hook by calling handle.remove()

Return type:

torch.utils.hooks.RemovableHandle

register_load_state_dict_pre_hook(hook: Callable[[Optimizer, dict[str, Any]], dict[str, Any] | None], prepend: bool = False) → RemovableHandle

Register a load_state_dict pre-hook which will be called before load_state_dict() is called. It should have the following signature:

hook(optimizer, state_dict) -> state_dict or None

The optimizer argument is the optimizer instance being used and the state_dict argument is a shallow copy of the state_dict the user passed in to load_state_dict. The hook may modify the state_dict inplace or optionally return a new one. If a state_dict is returned, it will be used to be loaded into the optimizer.

The hook will be called with argument self and state_dict before calling load_state_dict on self. The registered hook can be used to perform pre-processing before the load_state_dict call is made.

Parameters:

hook (Callable) – The user defined hook to be registered.
prepend (bool) – If True, the provided pre hook will be fired before all the already registered pre-hooks on load_state_dict. Otherwise, the provided hook will be fired after all the already registered pre-hooks. (default: False)

Returns:

a handle that can be used to remove the added hook by calling handle.remove()

Return type:

torch.utils.hooks.RemovableHandle

register_state_dict_post_hook(hook: Callable[[Optimizer, dict[str, Any]], dict[str, Any] | None], prepend: bool = False) → RemovableHandle

Register a state dict post-hook which will be called after state_dict() is called.

It should have the following signature:

hook(optimizer, state_dict) -> state_dict or None

The hook will be called with arguments self and state_dict after generating a state_dict on self. The hook may modify the state_dict inplace or optionally return a new one. The registered hook can be used to perform post-processing on the state_dict before it is returned.

Parameters:

hook (Callable) – The user defined hook to be registered.
prepend (bool) – If True, the provided post hook will be fired before all the already registered post-hooks on state_dict. Otherwise, the provided hook will be fired after all the already registered post-hooks. (default: False)

Returns:

a handle that can be used to remove the added hook by calling handle.remove()

Return type:

torch.utils.hooks.RemovableHandle

register_state_dict_pre_hook(hook: Callable[[Optimizer], None], prepend: bool = False) → RemovableHandle

Register a state dict pre-hook which will be called before state_dict() is called.

It should have the following signature:

hook(optimizer) -> None

The optimizer argument is the optimizer instance being used. The hook will be called with argument self before calling state_dict on self. The registered hook can be used to perform pre-processing before the state_dict call is made.

Parameters:

hook (Callable) – The user defined hook to be registered.
prepend (bool) – If True, the provided pre hook will be fired before all the already registered pre-hooks on state_dict. Otherwise, the provided hook will be fired after all the already registered pre-hooks. (default: False)

Returns:

a handle that can be used to remove the added hook by calling handle.remove()

Return type:

torch.utils.hooks.RemovableHandle

register_step_post_hook(hook: Callable[[Self, tuple[Any, ...], dict[str, Any]], None]) → RemovableHandle

Register an optimizer step post hook which will be called after optimizer step.

It should have the following signature:

hook(optimizer, args, kwargs) -> None

The optimizer argument is the optimizer instance being used.

Parameters:: hook (Callable) – The user defined hook to be registered.
Returns:: a handle that can be used to remove the added hook by calling handle.remove()
Return type:: torch.utils.hooks.RemovableHandle

register_step_pre_hook(hook: Callable[[Self, tuple[Any, ...], dict[str, Any]], tuple[tuple[Any, ...], dict[str, Any]] | None]) → RemovableHandle

Register an optimizer step pre hook which will be called before optimizer step.

It should have the following signature:

hook(optimizer, args, kwargs) -> None or modified args and kwargs

The optimizer argument is the optimizer instance being used. If args and kwargs are modified by the pre-hook, then the transformed values are returned as a tuple containing the new_args and new_kwargs.

Parameters:: hook (Callable) – The user defined hook to be registered.
Returns:: a handle that can be used to remove the added hook by calling handle.remove()
Return type:: torch.utils.hooks.RemovableHandle

reset() → None

Reset parameters

Return type:: None

state_dict() → dict[str, Any]

Return the state of the optimizer as a dict.

It contains two entries:

state: a Dict holding current optimization state. Its content
differs between optimizer classes, but some common characteristics hold. For example, state is saved per parameter, and the parameter itself is NOT saved. state is a Dictionary mapping parameter ids to a Dict with state corresponding to each parameter.
param_groups: a List containing all parameter groups where each
parameter group is a Dict. Each parameter group contains metadata specific to the optimizer, such as learning rate and weight decay, as well as a List of parameter IDs of the parameters in the group. If a param group was initialized with named_parameters() the names content will also be saved in the state dict.

NOTE: The parameter IDs may look like indices but they are just IDs associating state with param_group. When loading from a state_dict, the optimizer will zip the param_group params (int IDs) and the optimizer param_groups (actual nn.Parameter s) in order to match state WITHOUT additional verification.

A returned state dict might look something like:

{
    'state': {
        0: {'momentum_buffer': tensor(...), ...},
        1: {'momentum_buffer': tensor(...), ...},
        2: {'momentum_buffer': tensor(...), ...},
        3: {'momentum_buffer': tensor(...), ...}
    },
    'param_groups': [
        {
            'lr': 0.01,
            'weight_decay': 0,
            ...
            'params': [0]
            'param_names' ['param0']  (optional)
        },
        {
            'lr': 0.001,
            'weight_decay': 0.5,
            ...
            'params': [1, 2, 3]
            'param_names': ['param1', 'layer.weight', 'layer.bias'] (optional)
        }
    ]
}

Return type:: dict[str, Any]

step(closure: Callable | None = None) → Tensor

Performs a single optimization step.

Parameters:: closure (Callable | None) – A closure that reevaluates the model and returns the loss. Default: None
Return type:: Tensor

zero_grad(set_to_none: bool = True) → None

Reset the gradients of all optimized torch.Tensor s.

Parameters:

set_to_none (bool, optional) –

Instead of setting to zero, set the grads to None. Default: True

This will in general have lower memory footprint, and can modestly improve performance. However, it changes certain behaviors. For example:

When the user tries to access a gradient and perform manual ops on it, a None attribute or a Tensor full of 0s will behave differently.
If the user requests zero_grad(set_to_none=True) followed by a backward pass, .grads are guaranteed to be None for params that did not receive a gradient.
torch.optim optimizers have a different behavior if the gradient is 0 or None (in one case it does the step with a gradient of 0 and in the other it skips the step altogether).

Return type:

None

reset() → None

Reset parameters

Return type:: None

step(closure: Callable | None = None) → Tensor

Performs a single optimization step.

Parameters:: closure (Callable | None) – A closure that reevaluates the model and returns the loss. Default: None
Return type:: Tensor