Merge pull request #1517 from rstudio/retether-3-11-3-take2

Retether Keras to v3.11.3

Author: t-kalinowski

.tether/man/Layer.txt

@@ -1,6 +1,6 @@
 Help on class Layer in module keras.src.layers.layer:
 
-class Layer(keras.src.backend.tensorflow.layer.TFLayer, keras.src.ops.operation.Operation, keras.src.saving.keras_saveable.KerasSaveable)
+class Layer(keras.src.backend.tensorflow.layer.TFLayer, keras.src.ops.operation.Operation)
  |  Layer(*args, **kwargs)
  |
  |  This is the class from which all layers inherit.
@@ -243,6 +243,7 @@ class Layer(keras.src.backend.tensorflow.layer.TFLayer, keras.src.ops.operation.
  |    regularizer=None,
  |    constraint=None,
  |    aggregation='none',
+ |    overwrite_with_gradient=False,
  |    name=None
  |  )
  |      Add a weight variable to the layer.
@@ -274,6 +275,9 @@ class Layer(keras.src.backend.tensorflow.layer.TFLayer, keras.src.ops.operation.
  |              the type of multi-replica aggregation to be used for this
  |              variable when writing custom data parallel training loops.
  |              Defaults to `"none"`.
+ |          overwrite_with_gradient: Boolean, whether to overwrite the variable
+ |              with the computed gradient. This is useful for float8 training.
+ |              Defaults to `False`.
  |          name: String name of the variable. Useful for debugging purposes.
  |
  |  build(self, input_shape)
@@ -448,6 +452,12 @@ class Layer(keras.src.backend.tensorflow.layer.TFLayer, keras.src.ops.operation.
  |          ref_var.assign(value)
  |      ```
  |
+ |  symbolic_call(
+ |    self,
+ |    *args,
+ |    **kwargs
+ |  )
+ |
  |  ----------------------------------------------------------------------
  |  Static methods defined here:
  |

.tether/man/activation_elu.txt

@@ -19,6 +19,7 @@ and the information that is propagated to the next layer.
 
 Args:
     x: Input tensor.
+    alpha: A scalar, slope of positive section. Defaults to `1.0`.
 
 Reference:
 

.tether/man/activation_sparse_sigmoid.txt

@@ -0,0 +1,18 @@
+__signature__
+keras.activations.sparse_sigmoid(x)
+__doc__
+Sparse sigmoid activation function.
+
+It is defined as
+
+`f(x) = 0` for `x <= -1`,
+`f(x) = 0.5 * (x + 1)` for `-1 < x < 1`,
+`f(x) = 1` for `x >= 1`.
+
+Args:
+    x: Input tensor.
+
+Reference:
+
+- [M. Blondel, A. F. T. Martins, V. Niculae, 2019](https://arxiv.org/pdf/1901.02324)
+

.tether/man/callback_early_stopping.txt

@@ -1,6 +1,6 @@
 Help on class EarlyStopping in module keras.src.callbacks.early_stopping:
 
-class EarlyStopping(keras.src.callbacks.callback.Callback)
+class EarlyStopping(keras.src.callbacks.monitor_callback.MonitorCallback)
  |  EarlyStopping(monitor='val_loss', min_delta=0, patience=0, verbose=0, mode='auto', baseline=None, restore_best_weights=False, start_from_epoch=0)
  |
  |  Stop training when a monitored metric has stopped improving.
@@ -60,6 +60,7 @@ class EarlyStopping(keras.src.callbacks.callback.Callback)
  |
  |  Method resolution order:
  |      EarlyStopping
+ |      keras.src.callbacks.monitor_callback.MonitorCallback
  |      keras.src.callbacks.callback.Callback
  |      builtins.object
  |

.tether/man/callback_lambda.txt

@@ -13,8 +13,8 @@ class LambdaCallback(keras.src.callbacks.callback.Callback)
  |        `epoch`, `logs`
  |      - `on_train_begin` and `on_train_end` expect one positional argument:
  |        `logs`
- |      - `on_train_batch_begin` and `on_train_batch_end` expect two positional
- |        arguments: `batch`, `logs`
+ |      - `on_train_batch_begin` and `on_train_batch_end` expect a positional
+ |        argument `batch` and a keyword argument `logs`
  |      - See `Callback` class definition for the full list of functions and their
  |        expected arguments.
  |
@@ -79,3 +79,4 @@ class LambdaCallback(keras.src.callbacks.callback.Callback)
  |  )
  |      Initialize self.  See help(type(self)) for accurate signature.
  |
+

.tether/man/callback_model_checkpoint.txt

@@ -1,6 +1,6 @@
 Help on class ModelCheckpoint in module keras.src.callbacks.model_checkpoint:
 
-class ModelCheckpoint(keras.src.callbacks.callback.Callback)
+class ModelCheckpoint(keras.src.callbacks.monitor_callback.MonitorCallback)
  |  ModelCheckpoint(filepath, monitor='val_loss', verbose=0, save_best_only=False, save_weights_only=False, mode='auto', save_freq='epoch', initial_value_threshold=None)
  |
  |  Callback to save the Keras model or model weights at some frequency.
@@ -95,9 +95,8 @@ class ModelCheckpoint(keras.src.callbacks.callback.Callback)
  |          decision to overwrite the current save file is made based on either
  |          the maximization or the minimization of the monitored quantity.
  |          For `val_acc`, this should be `"max"`, for `val_loss` this should be
- |          `"min"`, etc. In `"auto"` mode, the mode is set to `"max"` if the
- |          quantities monitored are `"acc"` or start with `"fmeasure"` and are
- |          set to `"min"` for the rest of the quantities.
+ |          `"min"`, etc. In `"auto"` mode, the direction is automatically
+ |          inferred from the name of the monitored quantity.
  |      save_weights_only: if `True`, then only the model's weights will be
  |          saved (`model.save_weights(filepath)`), else the full model is
  |          saved (`model.save(filepath)`).
@@ -116,6 +115,7 @@ class ModelCheckpoint(keras.src.callbacks.callback.Callback)
  |
  |  Method resolution order:
  |      ModelCheckpoint
+ |      keras.src.callbacks.monitor_callback.MonitorCallback
  |      keras.src.callbacks.callback.Callback
  |      builtins.object
  |

.tether/man/callback_reduce_lr_on_plateau.txt

@@ -1,6 +1,6 @@
 Help on class ReduceLROnPlateau in module keras.src.callbacks.reduce_lr_on_plateau:
 
-class ReduceLROnPlateau(keras.src.callbacks.callback.Callback)
+class ReduceLROnPlateau(keras.src.callbacks.monitor_callback.MonitorCallback)
  |  ReduceLROnPlateau(monitor='val_loss', factor=0.1, patience=10, verbose=0, mode='auto', min_delta=0.0001, cooldown=0, min_lr=0.0, **kwargs)
  |
  |  Reduce learning rate when a metric has stopped improving.
@@ -39,6 +39,7 @@ class ReduceLROnPlateau(keras.src.callbacks.callback.Callback)
  |
  |  Method resolution order:
  |      ReduceLROnPlateau
+ |      keras.src.callbacks.monitor_callback.MonitorCallback
  |      keras.src.callbacks.callback.Callback
  |      builtins.object
  |

.tether/man/config_is_nnx_enabled.txt

@@ -0,0 +1,9 @@
+__signature__
+keras.config.is_nnx_enabled()
+__doc__
+Checks whether NNX specific features are enabled for the JAX backend.
+
+Returns:
+    bool: `True` if NNX backend features are enabled, `False` otherwise.
+    Defaults to `False`.
+

.tether/man/config_max_epochs.txt

@@ -0,0 +1,13 @@
+__signature__
+keras.config.max_epochs()
+__doc__
+Get the maximum number of epochs for any call to fit.
+
+Retrieves the limit on the number of epochs set by
+`keras.config.set_max_epochs` or the `KERAS_MAX_EPOCHS` environment
+variable.
+
+Returns:
+    The integer limit on the number of epochs or `None`, if no limit has
+    been set.
+

.tether/man/config_max_steps_per_epoch.txt

@@ -0,0 +1,13 @@
+__signature__
+keras.config.max_steps_per_epoch()
+__doc__
+Get the maximum number of steps for any call to fit/evaluate/predict.
+
+Retrieves the limit on the number of epochs set by
+`keras.config.set_max_steps_per_epoch` or the `KERAS_MAX_STEPS_PER_EPOCH`
+environment variable.
+
+Args:
+    max_epochs: The integer limit on the number of epochs or `None`. If
+        `None`, no limit is applied.
+