Improve "Defaults to" by putting to end of arg in docstring and ensuring backticks have proper spacing

keras/src/callbacks/backup_and_restore.py

@@ -63,11 +63,11 @@ class BackupAndRestore(Callback):
           When set to an integer, the callback saves the checkpoint every
           `save_freq` batches. Set `save_freq=False` only if using
           preemption checkpointing (i.e. with `save_before_preemption=True`).
-        delete_checkpoint: Boolean, defaults to `True`. This `BackupAndRestore`
+        delete_checkpoint: Boolean. This `BackupAndRestore`
           callback works by saving a checkpoint to back up the training state.
           If `delete_checkpoint=True`, the checkpoint will be deleted after
           training is finished. Use `False` if you'd like to keep the checkpoint
-          for future usage.
+          for future usage. Defaults to `True`.
     """
 
     def __init__(

keras/src/ops/math.py

@@ -40,7 +40,7 @@ def segment_sum(data, segment_ids, num_segments=None, sorted=False):
             segments. If not specified, it is inferred from the maximum
             value in `segment_ids`.
         sorted: A boolean indicating whether `segment_ids` is sorted.
-            Defaults to`False`.
+            Defaults to `False`.
 
     Returns:
         A tensor containing the sum of segments, where each element
@@ -93,7 +93,7 @@ def segment_max(data, segment_ids, num_segments=None, sorted=False):
             segments. If not specified, it is inferred from the maximum
             value in `segment_ids`.
         sorted: A boolean indicating whether `segment_ids` is sorted.
-            Defaults to`False`.
+            Defaults to `False`.
 
     Returns:
         A tensor containing the max of segments, where each element
@@ -141,7 +141,7 @@ def top_k(x, k, sorted=True):
         x: Input tensor.
         k: An integer representing the number of top elements to retrieve.
         sorted: A boolean indicating whether to sort the output in
-        descending order. Defaults to`True`.
+        descending order. Defaults to `True`.
 
     Returns:
         A tuple containing two tensors. The first tensor contains the
@@ -225,9 +225,9 @@ def logsumexp(x, axis=None, keepdims=False):
         x: Input tensor.
         axis: An integer or a tuple of integers specifying the axis/axes
             along which to compute the sum. If `None`, the sum is computed
-            over all elements. Defaults to`None`.
+            over all elements. Defaults to `None`.
         keepdims: A boolean indicating whether to keep the dimensions of
-            the input tensor when computing the sum. Defaults to`False`.
+            the input tensor when computing the sum. Defaults to `False`.
 
     Returns:
         A tensor containing the logarithm of the sum of exponentials of

keras/src/ops/nn.py

@@ -1298,8 +1298,8 @@ def one_hot(x, num_classes, axis=-1, dtype=None, sparse=False):
         x: Integer tensor to be encoded. The shape can be
             arbitrary, but the dtype should be integer.
         num_classes: Number of classes for the one-hot encoding.
-        axis: Axis along which the encoding is performed. Defaults to
-            `-1`, which represents the last axis.
+        axis: Axis along which the encoding is performed.
+            `-1` represents the last axis. Defaults to `-1`.
         dtype: (Optional) Data type of the output tensor. If not
             provided, it defaults to the default data type of the backend.
         sparse: Whether to return a sparse tensor; for backends that support
@@ -1377,7 +1377,7 @@ def binary_crossentropy(target, output, from_logits=False):
             probabilities.
             Set it to `True` if `output` represents logits; otherwise,
             set it to `False` if `output` represents probabilities.
-            Defaults to`False`.
+            Defaults to `False`.
 
     Returns:
         Integer tensor: The computed binary cross-entropy loss between
@@ -1452,7 +1452,7 @@ def categorical_crossentropy(target, output, from_logits=False, axis=-1):
             probabilities.
             Set it to `True` if `output` represents logits; otherwise,
             set it to `False` if `output` represents probabilities.
-            Defaults to`False`.
+            Defaults to `False`.
         axis: (optional) The axis along which the categorical cross-entropy
             is computed.
             Defaults to `-1`, which corresponds to the last dimension of
@@ -1540,7 +1540,7 @@ class labels instead of one-hot encoded vectors. It measures the
             or probabilities.
             Set it to `True` if `output` represents logits; otherwise,
             set it to `False` if `output` represents probabilities.
-            Defaults to`False`.
+            Defaults to `False`.
         axis: (optional) The axis along which the sparse categorical
             cross-entropy is computed.
             Defaults to `-1`, which corresponds to the last dimension

keras/src/ops/numpy.py

@@ -940,7 +940,7 @@ def argsort(x, axis=-1):
 
     Args:
         x: Input tensor.
-        axis: Axis along which to sort. Defaults to`-1` (the last axis). If
+        axis: Axis along which to sort. Defaults to `-1` (the last axis). If
             `None`, the flattened tensor is used.
 
     Returns:
@@ -4098,7 +4098,7 @@ def pad(x, pad_width, mode="constant", constant_values=None):
         mode: One of `"constant"`, `"edge"`, `"linear_ramp"`,
             `"maximum"`, `"mean"`, `"median"`, `"minimum"`,
             `"reflect"`, `"symmetric"`, `"wrap"`, `"empty"`,
-            `"circular"`. Defaults to`"constant"`.
+            `"circular"`. Defaults to `"constant"`.
         constant_values: value to pad with if `mode == "constant"`.
             Defaults to `0`. A `ValueError` is raised if not None and
             `mode != "constant"`.

keras/src/utils/audio_dataset_utils.py

@@ -82,8 +82,9 @@ def audio_dataset_from_directory(
             length of the longest sequence in the batch.
         ragged: Whether to return a Ragged dataset (where each sequence has its
             own length). Defaults to `False`.
-        shuffle: Whether to shuffle the data. Defaults to `True`.
+        shuffle: Whether to shuffle the data.
             If set to `False`, sorts the data in alphanumeric order.
+            Defaults to `True`.
         seed: Optional random seed for shuffling and transformations.
         validation_split: Optional float between 0 and 1, fraction of data to
             reserve for validation.

keras/src/utils/image_dataset_utils.py

@@ -83,15 +83,15 @@ def image_dataset_from_directory(
             (must match names of subdirectories). Used to control the order
             of the classes (otherwise alphanumerical order is used).
         color_mode: One of `"grayscale"`, `"rgb"`, `"rgba"`.
-            Defaults to `"rgb"`. Whether the images will be converted to
-            have 1, 3, or 4 channels.
+            Whether the images will be converted to
+            have 1, 3, or 4 channels. Defaults to `"rgb"`.
         batch_size: Size of the batches of data. Defaults to 32.
             If `None`, the data will not be batched
             (the dataset will yield individual samples).
         image_size: Size to resize images to after they are read from disk,
-            specified as `(height, width)`. Defaults to `(256, 256)`.
+            specified as `(height, width)`.
             Since the pipeline processes batches of images that must all have
-            the same size, this must be provided.
+            the same size, this must be provided. Defaults to `(256, 256)`.
         shuffle: Whether to shuffle the data. Defaults to `True`.
             If set to `False`, sorts the data in alphanumeric order.
         seed: Optional random seed for shuffling and transformations.
@@ -103,9 +103,10 @@ def image_dataset_from_directory(
             When `subset="both"`, the utility returns a tuple of two datasets
             (the training and validation datasets respectively).
         interpolation: String, the interpolation method used when
-            resizing images. Defaults to `"bilinear"`.
+            resizing images.
             Supports `"bilinear"`, `"nearest"`, `"bicubic"`, `"area"`,
             `"lanczos3"`, `"lanczos5"`, `"gaussian"`, `"mitchellcubic"`.
+            Defaults to `"bilinear"`.
         follow_links: Whether to visit subdirectories pointed to by symlinks.
             Defaults to `False`.
         crop_to_aspect_ratio: If `True`, resize the images without aspect

keras/src/utils/image_utils.py

@@ -350,9 +350,9 @@ def smart_resize(
             or `(batch_size, height, width, channels)`.
         size: Tuple of `(height, width)` integer. Target size.
         interpolation: String, interpolation to use for resizing.
-            Defaults to `'bilinear'`.
-            Supports `bilinear`, `nearest`, `bicubic`,
-            `lanczos3`, `lanczos5`.
+            Supports `"bilinear"`, `"nearest"`, `"bicubic"`,
+            `"lanczos3"`, `"lanczos5"`.
+            Defaults to `"bilinear"`.
         data_format: `"channels_last"` or `"channels_first"`.
         backend_module: Backend module to use (if different from the default
             backend).

keras/src/utils/sequence_utils.py

@@ -69,7 +69,7 @@ def pad_sequences(
         truncating: String, "pre" or "post" (optional, defaults to `"pre"`):
             remove values from sequences larger than
             `maxlen`, either at the beginning or at the end of the sequences.
-        value: Float or String, padding value. (Optional, defaults to 0.)
+        value: Float or String, padding value. (Optional, defaults to `0.`)
 
     Returns:
         NumPy array with shape `(len(sequences), maxlen)`

keras/src/utils/text_dataset_utils.py

@@ -72,13 +72,15 @@ def text_dataset_from_directory(
             This is the explicit list of class names
             (must match names of subdirectories). Used to control the order
             of the classes (otherwise alphanumerical order is used).
-        batch_size: Size of the batches of data. Defaults to 32.
+        batch_size: Size of the batches of data.
             If `None`, the data will not be batched
             (the dataset will yield individual samples).
+            Defaults to `32`.
         max_length: Maximum size of a text string. Texts longer than this will
             be truncated to `max_length`.
-        shuffle: Whether to shuffle the data. Defaults to `True`.
+        shuffle: Whether to shuffle the data.
             If set to `False`, sorts the data in alphanumeric order.
+            Defaults to `True`.
         seed: Optional random seed for shuffling and transformations.
         validation_split: Optional float between 0 and 1,
             fraction of data to reserve for validation.