Merge pull request #1447 from rstudio/retether-3.3.3

Retether to Keras 3.3.3

.tether/man/Constraint.txt

@@ -52,7 +52,7 @@ class Constraint(builtins.object)
  |  ----------------------------------------------------------------------
  |  Class methods defined here:
  |
- |  from_config(config) from builtins.type
+ |  from_config(config)
  |      Instantiates a weight constraint from a configuration dictionary.
  |
  |      Example:

.tether/man/InputLayer.txt

@@ -11,6 +11,7 @@ class InputLayer(keras.src.layers.layer.Layer)
  |      tensorflow.python.trackable.autotrackable.AutoTrackable
  |      tensorflow.python.trackable.base.Trackable
  |      keras.src.ops.operation.Operation
+ |      keras.src.saving.keras_saveable.KerasSaveable
  |      builtins.object
  |
  |  Methods defined here:

.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)
+class Layer(keras.src.backend.tensorflow.layer.TFLayer, keras.src.ops.operation.Operation, keras.src.saving.keras_saveable.KerasSaveable)
  |  Layer(*args, **kwargs)
  |
  |  This is the class from which all layers inherit.
@@ -161,6 +161,7 @@ class Layer(keras.src.backend.tensorflow.layer.TFLayer, keras.src.ops.operation.
  |      tensorflow.python.trackable.autotrackable.AutoTrackable
  |      tensorflow.python.trackable.base.Trackable
  |      keras.src.ops.operation.Operation
+ |      keras.src.saving.keras_saveable.KerasSaveable
  |      builtins.object
  |
  |  Methods defined here:

.tether/man/LearningRateSchedule.txt

@@ -52,7 +52,7 @@ class LearningRateSchedule(builtins.object)
  |  ----------------------------------------------------------------------
  |  Class methods defined here:
  |
- |  from_config(config) from builtins.type
+ |  from_config(config)
  |      Instantiates a `LearningRateSchedule` from its config.
  |
  |      Args:

.tether/man/Loss.txt

@@ -1,11 +1,7 @@
 Help on class Loss in module keras.src.losses.loss:
 
-class Loss(builtins.object)
- |  Loss(
- |    name=None,
- |    reduction='sum_over_batch_size',
- |    dtype=None
- |  )
+class Loss(keras.src.saving.keras_saveable.KerasSaveable)
+ |  Loss(name=None, reduction='sum_over_batch_size', dtype=None)
  |
  |  Loss base class.
  |
@@ -22,6 +18,11 @@ class Loss(builtins.object)
  |          return ops.mean(ops.square(y_pred - y_true), axis=-1)
  |  ```
  |
+ |  Method resolution order:
+ |      Loss
+ |      keras.src.saving.keras_saveable.KerasSaveable
+ |      builtins.object
+ |
  |  Methods defined here:
  |
  |  __call__(
@@ -51,14 +52,6 @@ class Loss(builtins.object)
  |  ----------------------------------------------------------------------
  |  Class methods defined here:
  |
- |  from_config(config) from builtins.type
- |
- |  ----------------------------------------------------------------------
- |  Data descriptors defined here:
- |
- |  __dict__
- |      dictionary for instance variables
+ |  from_config(config)
  |
- |  __weakref__
- |      list of weak references to the object
 

.tether/man/Metric.txt

@@ -1,6 +1,6 @@
 Help on class Metric in module keras.src.metrics.metric:
 
-class Metric(builtins.object)
+class Metric(keras.src.saving.keras_saveable.KerasSaveable)
  |  Metric(dtype=None, name=None)
  |
  |  Encapsulates metric logic and state.
@@ -77,6 +77,11 @@ class Metric(builtins.object)
  |          return self.true_positives
  |  ```
  |
+ |  Method resolution order:
+ |      Metric
+ |      keras.src.saving.keras_saveable.KerasSaveable
+ |      builtins.object
+ |
  |  Methods defined here:
  |
  |  __call__(
@@ -159,7 +164,7 @@ class Metric(builtins.object)
  |  ----------------------------------------------------------------------
  |  Class methods defined here:
  |
- |  from_config(config) from builtins.type
+ |  from_config(config)
  |
  |  ----------------------------------------------------------------------
  |  Readonly properties defined here:
@@ -168,12 +173,4 @@ class Metric(builtins.object)
  |
  |  variables
  |
- |  ----------------------------------------------------------------------
- |  Data descriptors defined here:
- |
- |  __dict__
- |      dictionary for instance variables
- |
- |  __weakref__
- |      list of weak references to the object
 

.tether/man/callback_early_stopping.txt

@@ -44,7 +44,6 @@ class EarlyStopping(keras.src.callbacks.callback.Callback)
  |          improvement is expected and thus training will not be stopped.
  |          Defaults to `0`.
  |
- |
  |  Example:
  |
  |  >>> callback = keras.callbacks.EarlyStopping(monitor='loss',
@@ -118,3 +117,4 @@ class EarlyStopping(keras.src.callbacks.callback.Callback)
  |            `on_epoch_end()` is passed to this argument for this method but
  |            that may change in the future.
  |
+

.tether/man/clone_model.txt

@@ -0,0 +1,123 @@
+__signature__
+keras.models.clone_model(
+  model,
+  input_tensors=None,
+  clone_function=None,
+  call_function=None,
+  recursive=False,
+  **kwargs
+)
+__doc__
+Clone a Functional or Sequential `Model` instance.
+
+Model cloning is similar to calling a model on new inputs,
+except that it creates new layers (and thus new weights) instead
+of sharing the weights of the existing layers.
+
+Note that
+`clone_model` will not preserve the uniqueness of shared objects within the
+model (e.g. a single variable attached to two distinct layers will be
+restored as two separate variables).
+
+Args:
+    model: Instance of `Model`
+        (could be a Functional model or a Sequential model).
+    input_tensors: optional list of input tensors or InputLayer objects
+        to build the model upon. If not provided,
+        new `Input` objects will be created.
+    clone_function: Callable with signature `fn(layer)`
+        to be used to clone each layer in the target
+        model (except `Input` instances). It takes as argument the
+        layer instance to be cloned, and returns the corresponding layer
+        instance to be used in the model copy. If unspecified, this callable
+        defaults to the following serialization/deserialization function:
+        `lambda layer: layer.__class__.from_config(layer.get_config())`.
+        By passing a custom callable, you can customize your copy of the
+        model, e.g. by wrapping certain layers of interest (you might want
+        to replace all `LSTM` instances with equivalent
+        `Bidirectional(LSTM(...))` instances, for example).
+        Defaults to `None`.
+    call_function: Callable with signature
+        `fn(layer, *args, **kwargs)` to be used to call each
+        cloned layer and a set of inputs. It takes the layer instance,
+        the call arguments and keyword arguments, and returns the
+        call outputs. If unspecified, this callable defaults to
+        the regular `__call__()` method:
+        `def fn(layer, *args, **kwargs): return layer(*args, **kwargs)`.
+        By passing a custom callable, you can insert new layers before or
+        after a given layer. Note: this argument can only be used with
+        Functional models.
+    recursive: Boolean. Whether to recursively clone any Sequential
+        or Functional models encountered in the original
+        Sequential/Functional model. If `False`,
+        then inner models are cloned by calling `clone_function()`.
+        If `True`, then inner models are cloned by calling `clone_model()`
+        with the same `clone_function`, `call_function`, and `recursive`
+        arguments. Note that in this case, `call_function`
+        will not be propagated to any Sequential model
+        (since it is not applicable to Sequential models).
+
+Returns:
+    An instance of `Model` reproducing the behavior
+    of the original model, on top of new inputs tensors,
+    using newly instantiated weights. The cloned model may behave
+    differently from the original model if a custom `clone_function`
+    or `call_function` modifies a layer or layer call.
+
+Example:
+
+```python
+# Create a test Sequential model.
+model = keras.Sequential([
+    keras.layers.Input(shape=(728,)),
+    keras.layers.Dense(32, activation='relu'),
+    keras.layers.Dense(1, activation='sigmoid'),
+])
+# Create a copy of the test model (with freshly initialized weights).
+new_model = clone_model(model)
+```
+
+Using a `clone_function` to make a model deterministic by setting the
+random seed everywhere:
+
+```python
+def clone_function(layer):
+    config = layer.get_config()
+    if "seed" in config:
+        config["seed"] = 1337
+    return layer.__class__.from_config(config)
+
+new_model = clone_model(model)
+```
+
+Using a `call_function` to add a `Dropout` layer after each `Dense` layer
+(without recreating new layers):
+
+```python
+def call_function(layer, *args, **kwargs):
+    out = layer(*args, **kwargs)
+    if isinstance(layer, keras.layers.Dense):
+        out = keras.layers.Dropout(0.5)(out)
+    return out
+
+new_model = clone_model(
+    model,
+    clone_function=lambda x: x,  # Reuse the same layers.
+    call_function=call_function,
+)
+```
+
+Note that subclassed models cannot be cloned by default,
+since their internal layer structure is not known.
+To achieve equivalent functionality
+as `clone_model` in the case of a subclassed model, simply make sure
+that the model class implements `get_config()`
+(and optionally `from_config()`), and call:
+
+```python
+new_model = model.__class__.from_config(model.get_config())
+```
+
+In the case of a subclassed model, you cannot using a custom
+`clone_function`.
+

.tether/man/initializer_constant.txt

@@ -52,7 +52,7 @@ class Constant(keras.src.initializers.initializer.Initializer)
  |  ----------------------------------------------------------------------
  |  Class methods defined here:
  |
- |  from_config(config) from builtins.type
+ |  from_config(config)
  |      Instantiates an initializer from a configuration dictionary.
  |
  |      Example:
@@ -69,3 +69,4 @@ class Constant(keras.src.initializers.initializer.Initializer)
  |      Returns:
  |          An `Initializer` instance.
  |
+

.tether/man/keras.losses.txt

@@ -77,7 +77,7 @@ CosineSimilarity(
   name='cosine_similarity'
 )
 ctc(y_true, y_pred)
-CTC(reduction='sum_over_batch_size', name='sparse_categorical_crossentropy')
+CTC(reduction='sum_over_batch_size', name='ctc')
 deserialize(name, custom_objects=None)
 dice(y_true, y_pred)
 Dice(reduction='sum_over_batch_size', name='dice')

.tether/man/keras.models.txt

@@ -1,7 +1,10 @@
 clone_model(
   model,
   input_tensors=None,
-  clone_function=None
+  clone_function=None,
+  call_function=None,
+  recursive=False,
+  **kwargs
 )
 load_model(
   filepath,

.tether/man/keras.ops.nn.txt

@@ -45,7 +45,7 @@ conv_transpose(
 ctc_decode(
   inputs,
   sequence_lengths,
-  strategy,
+  strategy='greedy',
   beam_width=100,
   top_paths=1,
   merge_repeated=True,
@@ -107,6 +107,11 @@ one_hot(
   dtype=None,
   sparse=False
 )
+psnr(
+  x1,
+  x2,
+  max_val
+)
 relu(x)
 relu6(x)
 selu(x)

.tether/man/keras.ops.numpy.txt

@@ -269,6 +269,7 @@ sign(x)
 sin(x)
 sinh(x)
 size(x)
+slogdet(x)
 sort(x, axis=-1)
 split(
   x,

.tether/man/keras.ops.txt

@@ -149,7 +149,7 @@ cross(
 ctc_decode(
   inputs,
   sequence_lengths,
-  strategy,
+  strategy='greedy',
   beam_width=100,
   top_paths=1,
   merge_repeated=True,
@@ -412,6 +412,11 @@ prod(
   keepdims=False,
   dtype=None
 )
+psnr(
+  x1,
+  x2,
+  max_val
+)
 qr(x, mode='reduced')
 quantile(
   x,
@@ -493,6 +498,7 @@ slice_update(
   start_indices,
   updates
 )
+slogdet(x)
 softmax(x, axis=-1)
 softplus(x)
 softsign(x)

.tether/man/keras_model.txt

@@ -116,6 +116,7 @@ class Model(keras.src.backend.tensorflow.trainer.TensorFlowTrainer, keras.src.tr
  |      tensorflow.python.trackable.autotrackable.AutoTrackable
  |      tensorflow.python.trackable.base.Trackable
  |      keras.src.ops.operation.Operation
+ |      keras.src.saving.keras_saveable.KerasSaveable
  |      builtins.object
  |
  |  Methods defined here:
@@ -127,13 +128,6 @@ class Model(keras.src.backend.tensorflow.trainer.TensorFlowTrainer, keras.src.tr
  |  )
  |      Initialize self.  See help(type(self)) for accurate signature.
  |
- |  __reduce__(self)
- |      __reduce__ is used to customize the behavior of `pickle.pickle()`.
- |
- |      The method returns a tuple of two elements: a function, and a list of
- |      arguments to pass to that function.  In this case we just leverage the
- |      keras saving library.
- |
  |  build_from_config(self, config)
  |      Builds the layer's states with the supplied config dict.
  |
@@ -360,7 +354,7 @@ class Model(keras.src.backend.tensorflow.trainer.TensorFlowTrainer, keras.src.tr
  |  ----------------------------------------------------------------------
  |  Class methods defined here:
  |
- |  from_config(config, custom_objects=None) from builtins.type
+ |  from_config(config, custom_objects=None)
  |      Creates a layer from its config.
  |
  |      This method is the reverse of `get_config`,