nshtrainer 1.0.0b48__py3-none-any.whl → 1.0.0b50__py3-none-any.whl

nshtrainer/lr_scheduler/reduce_lr_on_plateau.py

@@ -7,6 +7,7 @@ from torch.optim.lr_scheduler import ReduceLROnPlateau
 from typing_extensions import final, override
 
 from ..metrics._config import MetricConfig
+from ..util.config import EpochsConfig
 from .base import LRSchedulerConfigBase, LRSchedulerMetadata, lr_scheduler_registry
 
 
@@ -21,13 +22,13 @@ class ReduceLROnPlateauConfig(LRSchedulerConfigBase):
     """Metric to monitor.
     If not provided, the primary metric of the runner will be used."""
 
-    patience: int
+    patience: int | EpochsConfig
     r"""Number of epochs with no improvement after which learning rate will be reduced."""
 
     factor: float
     r"""Factor by which the learning rate will be reduced. new_lr = lr * factor."""
 
-    cooldown: int = 0
+    cooldown: int | EpochsConfig = 0
     r"""Number of epochs to wait before resuming normal operation after lr has been reduced."""
 
     min_lr: float | list[float] = 0.0
@@ -57,14 +58,20 @@ class ReduceLROnPlateauConfig(LRSchedulerConfigBase):
                 "Primary metric must be provided if metric is not specified."
             )
 
+        if isinstance(patience := self.patience, EpochsConfig):
+            patience = int(patience.value)
+
+        if isinstance(cooldown := self.cooldown, EpochsConfig):
+            cooldown = int(cooldown.value)
+
         lr_scheduler = ReduceLROnPlateau(
             optimizer,
             mode=metric.mode,
             factor=self.factor,
-            patience=self.patience,
+            patience=patience,
             threshold=self.threshold,
             threshold_mode=self.threshold_mode,
-            cooldown=self.cooldown,
+            cooldown=cooldown,
             min_lr=self.min_lr,
             eps=self.eps,
         )

nshtrainer/model/mixins/logger.py

@@ -1,16 +1,16 @@
 from __future__ import annotations
 
-import copy
 import dataclasses
 from collections import deque
-from collections.abc import Callable, Generator
+from collections.abc import Callable, Generator, Mapping
 from contextlib import contextmanager
 from typing import Any, ClassVar
 
+import torchmetrics
 from lightning.pytorch import LightningModule
 from lightning.pytorch.utilities.types import _METRIC
 from lightning_utilities.core.rank_zero import rank_zero_warn
-from typing_extensions import Self, override
+from typing_extensions import override
 
 from ...util.typing_utils import mixin_base_type
 
@@ -33,23 +33,6 @@ class _LogContextKwargs:
     batch_size: int | None = None
     rank_zero_only: bool | None = None
 
-    def copy_from(self, other: Self):
-        kwargs = copy.deepcopy(self)
-
-        # Copy over all the not-None values from the other object
-        updates = {}
-        for field in dataclasses.fields(self):
-            # Ignore disabled fields
-            if field.name in self.__ignore_fields__:
-                continue
-
-            if (value := getattr(other, field.name, None)) is None:
-                continue
-            # setattr(kwargs, field.name, value)
-            updates[field.name] = value
-
-        return dataclasses.replace(kwargs, **updates)
-
     def to_dict(self):
         d = dataclasses.asdict(self)
         for field in self.__ignore_fields__:
@@ -135,6 +118,16 @@ class LoggerLightningModuleMixin(mixin_base_type(LightningModule)):
         finally:
             _ = self._logger_prefix_stack.pop()
 
+    def _make_prefix_and_kwargs_dict(self, kwargs: _LogContextKwargs):
+        prefix = "".join(c.prefix for c in self._logger_prefix_stack if c.prefix)
+
+        fn_kwargs: dict[str, Any] = {}
+        for c in self._logger_prefix_stack:
+            fn_kwargs.update(c.to_dict())
+
+        fn_kwargs.update(kwargs.to_dict())
+        return prefix, fn_kwargs
+
     @override
     def log(
         self,
@@ -153,18 +146,117 @@ class LoggerLightningModuleMixin(mixin_base_type(LightningModule)):
         metric_attribute: str | None = None,
         rank_zero_only: bool | None = None,
     ) -> None:
+        """Log a key, value pair.
+
+        Example::
+
+            self.log('train_loss', loss)
+
+        The default behavior per hook is documented here: :ref:`extensions/logging:Automatic Logging`.
+
+        Args:
+            name: key to log. Must be identical across all processes if using DDP or any other distributed strategy.
+            value: value to log. Can be a ``float``, ``Tensor``, or a ``Metric``.
+            prog_bar: if ``True`` logs to the progress bar.
+            logger: if ``True`` logs to the logger.
+            on_step: if ``True`` logs at this step. The default value is determined by the hook.
+                See :ref:`extensions/logging:Automatic Logging` for details.
+            on_epoch: if ``True`` logs epoch accumulated metrics. The default value is determined by the hook.
+                See :ref:`extensions/logging:Automatic Logging` for details.
+            reduce_fx: reduction function over step values for end of epoch. :meth:`torch.mean` by default.
+            enable_graph: if ``True``, will not auto detach the graph.
+            sync_dist: if ``True``, reduces the metric across devices. Use with care as this may lead to a significant
+                communication overhead.
+            sync_dist_group: the DDP group to sync across.
+            add_dataloader_idx: if ``True``, appends the index of the current dataloader to
+                the name (when using multiple dataloaders). If False, user needs to give unique names for
+                each dataloader to not mix the values.
+            batch_size: Current batch_size. This will be directly inferred from the loaded batch,
+                but for some data structures you might need to explicitly provide it.
+            metric_attribute: To restore the metric state, Lightning requires the reference of the
+                :class:`torchmetrics.Metric` in your model. This is found automatically if it is a model attribute.
+            rank_zero_only: Tells Lightning if you are calling ``self.log`` from every process (default) or only from
+                rank 0. If ``True``, you won't be able to use this metric as a monitor in callbacks
+                (e.g., early stopping). Warning: Improper use can lead to deadlocks! See
+                :ref:`Advanced Logging <visualize/logging_advanced:rank_zero_only>` for more details.
+
+        """
         # If logging is disabled, then do nothing.
         if not self.logging_enabled:
             return
 
-        # join all prefixes
-        prefix = "".join(c.prefix for c in self._logger_prefix_stack if c.prefix)
+        prefix, fn_kwargs = self._make_prefix_and_kwargs_dict(
+            _LogContextKwargs(
+                prog_bar=prog_bar,
+                logger=logger,
+                on_step=on_step,
+                on_epoch=on_epoch,
+                reduce_fx=reduce_fx,
+                enable_graph=enable_graph,
+                sync_dist=sync_dist,
+                sync_dist_group=sync_dist_group,
+                add_dataloader_idx=add_dataloader_idx,
+                batch_size=batch_size,
+                rank_zero_only=rank_zero_only,
+            )
+        )
         name = f"{prefix}{name}"
+        return super().log(name, value, metric_attribute=metric_attribute, **fn_kwargs)
 
-        fn_kwargs = _LogContextKwargs()
-        for c in self._logger_prefix_stack:
-            fn_kwargs = fn_kwargs.copy_from(c)
-        fn_kwargs = fn_kwargs.copy_from(
+    def log_dict(
+        self,
+        dictionary: Mapping[str, _METRIC] | torchmetrics.MetricCollection,
+        prog_bar: bool | None = None,
+        logger: bool | None = None,
+        on_step: bool | None = None,
+        on_epoch: bool | None = None,
+        reduce_fx: str | Callable | None = None,
+        enable_graph: bool | None = None,
+        sync_dist: bool | None = None,
+        sync_dist_group: Any | None = None,
+        add_dataloader_idx: bool | None = None,
+        batch_size: int | None = None,
+        rank_zero_only: bool | None = None,
+    ) -> None:
+        """Log a dictionary of values at once.
+
+        Example::
+
+            values = {'loss': loss, 'acc': acc, ..., 'metric_n': metric_n}
+            self.log_dict(values)
+
+        Args:
+            dictionary: key value pairs.
+                Keys must be identical across all processes if using DDP or any other distributed strategy.
+                The values can be a ``float``, ``Tensor``, ``Metric``, or ``MetricCollection``.
+            prog_bar: if ``True`` logs to the progress base.
+            logger: if ``True`` logs to the logger.
+            on_step: if ``True`` logs at this step.
+                ``None`` auto-logs for training_step but not validation/test_step.
+                The default value is determined by the hook.
+                See :ref:`extensions/logging:Automatic Logging` for details.
+            on_epoch: if ``True`` logs epoch accumulated metrics.
+                ``None`` auto-logs for val/test step but not ``training_step``.
+                The default value is determined by the hook.
+                See :ref:`extensions/logging:Automatic Logging` for details.
+            reduce_fx: reduction function over step values for end of epoch. :meth:`torch.mean` by default.
+            enable_graph: if ``True``, will not auto-detach the graph
+            sync_dist: if ``True``, reduces the metric across GPUs/TPUs. Use with care as this may lead to a significant
+                communication overhead.
+            sync_dist_group: the ddp group to sync across.
+            add_dataloader_idx: if ``True``, appends the index of the current dataloader to
+                the name (when using multiple). If ``False``, user needs to give unique names for
+                each dataloader to not mix values.
+            batch_size: Current batch size. This will be directly inferred from the loaded batch,
+                but some data structures might need to explicitly provide it.
+            rank_zero_only: Tells Lightning if you are calling ``self.log`` from every process (default) or only from
+                rank 0. If ``True``, you won't be able to use this metric as a monitor in callbacks
+                (e.g., early stopping). Warning: Improper use can lead to deadlocks! See
+                :ref:`Advanced Logging <visualize/logging_advanced:rank_zero_only>` for more details.
+
+        """
+
+        _, fn_kwargs = self._make_prefix_and_kwargs_dict(
             _LogContextKwargs(
                 prog_bar=prog_bar,
                 logger=logger,
@@ -179,9 +271,5 @@ class LoggerLightningModuleMixin(mixin_base_type(LightningModule)):
                 rank_zero_only=rank_zero_only,
             )
         )
-        return super().log(
-            name,
-            value,
-            metric_attribute=metric_attribute,
-            **fn_kwargs.to_dict(),
-        )
+        # NOTE: Prefix will be handled by the individual log calls.
+        return super().log_dict(dictionary, **fn_kwargs)

{nshtrainer-1.0.0b48.dist-info → nshtrainer-1.0.0b50.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: nshtrainer
-Version: 1.0.0b48
+Version: 1.0.0b50
 Summary: 
 Author: Nima Shoghi
 Author-email: nimashoghi@gmail.com

{nshtrainer-1.0.0b48.dist-info → nshtrainer-1.0.0b50.dist-info}/RECORD

@@ -111,14 +111,14 @@ nshtrainer/loggers/wandb.py,sha256=KZXAUWrrmdX_L8rqej77oUHaM0JxZRM8y9z6JP9PISw,6
 nshtrainer/lr_scheduler/__init__.py,sha256=daMMK3erUcNXGGd_nZB8AWu3ZTYqfS1RSWeK4FV2udw,851
 nshtrainer/lr_scheduler/base.py,sha256=LE53JRBTuAlA1fqbMgCZ7m39D1z0rGj2TizhJ62CPvE,3756
 nshtrainer/lr_scheduler/linear_warmup_cosine.py,sha256=MsoXgCcWTKsrkNZiGnKS6yC-slRuleuwFxeM_lmG_pQ,5560
-nshtrainer/lr_scheduler/reduce_lr_on_plateau.py,sha256=zKO_4Cl28m3TopoNFmc5H6GSUuVUGYUoAlXpMh_EJIk,2931
+nshtrainer/lr_scheduler/reduce_lr_on_plateau.py,sha256=irPyDjfUX843ze4bJM9sW8WSeEcU643QJ30JN2hz9Rc,3206
 nshtrainer/metrics/__init__.py,sha256=Nqkn_jsDf3n5WtfMcnaaEftYjIIT2b-S7rmsB1MOMkU,86
 nshtrainer/metrics/_config.py,sha256=ox_ScK6V0J9nzIMhEB0qpToNKpt83VVgOVSRFCV-wBc,595
 nshtrainer/model/__init__.py,sha256=3G-bwPPSRStWdsdwG9-rn0bXcRpEiP1BiQpF_qavtls,97
 nshtrainer/model/base.py,sha256=bZMNap0rkxRbAbu2BOHV_6YS2iZZnvy6wVSMOXGa_ZM,8680
 nshtrainer/model/mixins/callback.py,sha256=0LPgve4VszHbLipid4mpI1qnnmdGS2spivs0dXLvqHw,3154
 nshtrainer/model/mixins/debug.py,sha256=ydLuAAaa7M5bX0gougZ5gWuZnvn4Ra9assal3IZ9hq8,2086
-nshtrainer/model/mixins/logger.py,sha256=IYfyyW_1VAD_HiTsfX28P-XNgz_SMb07t5lwb5rjlZ0,6221
+nshtrainer/model/mixins/logger.py,sha256=7u9fQig-SVFA9RFIB4U0gqJAzruh49mgmXXvZ6VkDUk,11694
 nshtrainer/nn/__init__.py,sha256=5Gg3nieGSC5_dXaI9KUVUUbM13hHexH9831m4hcf6no,1475
 nshtrainer/nn/mlp.py,sha256=nYUgAISzuhC8sav6PloAdyz0PdEoikwppiXIuToEVdE,7550
 nshtrainer/nn/module_dict.py,sha256=9plb8aQUx5TUEPhX5jI9u8LrpTeKe7jZAHi8iIqcN8w,2365
@@ -154,6 +154,6 @@ nshtrainer/util/seed.py,sha256=diMV8iwBKN7Xxt5pELmui-gyqyT80_CZzomrWhNss0k,316
 nshtrainer/util/slurm.py,sha256=HflkP5iI_r4UHMyPjw9R4dD5AHsJUpcfJw5PLvGYBRM,1603
 nshtrainer/util/typed.py,sha256=Xt5fUU6zwLKSTLUdenovnKK0N8qUq89Kddz2_XeykVQ,164
 nshtrainer/util/typing_utils.py,sha256=MjY-CUX9R5Tzat-BlFnQjwl1PQ_W2yZQoXhkYHlJ_VA,442
-nshtrainer-1.0.0b48.dist-info/METADATA,sha256=b26a0GYVQcEszYiodjGF34N7gvEKONBVuB1bXTv35U4,988
-nshtrainer-1.0.0b48.dist-info/WHEEL,sha256=XbeZDeTWKc1w7CSIyre5aMDU_-PohRwTQceYnisIYYY,88
-nshtrainer-1.0.0b48.dist-info/RECORD,,
+nshtrainer-1.0.0b50.dist-info/METADATA,sha256=KgNg6AHzL9uCAc1tzfM0gbQl5Bu9QhQFFtecE75KIn0,988
+nshtrainer-1.0.0b50.dist-info/WHEEL,sha256=XbeZDeTWKc1w7CSIyre5aMDU_-PohRwTQceYnisIYYY,88
+nshtrainer-1.0.0b50.dist-info/RECORD,,