Typo / spelling fixes (#20186)

* [*] Typo / spelling fixes

* [*] Typo / spelling fixes

* saveable => savable

* Saveable => Savable

.github/workflows/scripts/labeler.js

@@ -23,16 +23,16 @@ You may obtain a copy of the License at
 
 module.exports = async ({ github, context }) => {
     const issue_title = context.payload.issue ?  context.payload.issue.title : context.payload.pull_request.title
-    const issue_discription = context.payload.issue ? context.payload.issue.body : context.payload.pull_request.body
+    const issue_description = context.payload.issue ? context.payload.issue.body : context.payload.pull_request.body
     const issue_number = context.payload.issue ? context.payload.issue.number : context.payload.pull_request.number
     const keyword_label =  {
          gemma:'Gemma'
     }
     const labelsToAdd = []
-    console.log(issue_title,issue_discription,issue_number)
+    console.log(issue_title,issue_description,issue_number)
 
     for(const [keyword, label] of Object.entries(keyword_label)){
-     if(issue_title.toLowerCase().indexOf(keyword) !=-1 || issue_discription.toLowerCase().indexOf(keyword) !=-1 ){
+     if(issue_title.toLowerCase().indexOf(keyword) !=-1 || issue_description.toLowerCase().indexOf(keyword) !=-1 ){
         console.log(`'${keyword}'keyword is present inside the title or description. Pushing label '${label}' to row.`)
         labelsToAdd.push(label)
     }

guides/training_with_built_in_methods.py

@@ -650,7 +650,7 @@ def __getitem__(self, idx):
     `True` if your dataset can be safely pickled.
 - `max_queue_size`: Maximum number of batches to keep in the queue
     when iterating over the dataset in a multithreaded or
-    multipricessed setting.
+    multiprocessed setting.
     You can reduce this value to reduce the CPU memory consumption of
     your dataset. It defaults to 10.
 

keras/src/applications/efficientnet.py

@@ -325,9 +325,9 @@ def round_repeats(repeats):
     x = layers.Rescaling(1.0 / 255.0)(x)
     x = layers.Normalization(axis=bn_axis)(x)
     if weights == "imagenet":
-        # Note that the normaliztion layer uses square value of STDDEV as the
+        # Note that the normalization layer uses square value of STDDEV as the
         # variance for the layer: result = (input - mean) / sqrt(var)
-        # However, the original implemenetation uses (input - mean) / var to
+        # However, the original implementation uses (input - mean) / var to
         # normalize the input, we need to divide another sqrt(var) to match the
         # original implementation.
         # See https://github.com/tensorflow/tensorflow/issues/49930 for more

keras/src/backend/common/backend_utils.py

@@ -4,7 +4,7 @@
 import warnings
 
 
-def _convert_conv_tranpose_padding_args_from_keras_to_jax(
+def _convert_conv_transpose_padding_args_from_keras_to_jax(
     kernel_size, stride, dilation_rate, padding, output_padding
 ):
     """Convert the padding arguments from Keras to the ones used by JAX.
@@ -45,7 +45,7 @@ def _convert_conv_tranpose_padding_args_from_keras_to_jax(
     return left_pad, right_pad
 
 
-def _convert_conv_tranpose_padding_args_from_keras_to_torch(
+def _convert_conv_transpose_padding_args_from_keras_to_torch(
     kernel_size, stride, dilation_rate, padding, output_padding
 ):
     """Convert the padding arguments from Keras to the ones used by Torch.
@@ -134,7 +134,7 @@ def compute_conv_transpose_padding_args_for_jax(
         (
             pad_left,
             pad_right,
-        ) = _convert_conv_tranpose_padding_args_from_keras_to_jax(
+        ) = _convert_conv_transpose_padding_args_from_keras_to_jax(
             kernel_size=kernel_spatial_shape[i],
             stride=strides_i,
             dilation_rate=dilation_rate_i,
@@ -174,7 +174,7 @@ def compute_conv_transpose_padding_args_for_torch(
         (
             torch_padding,
             torch_output_padding,
-        ) = _convert_conv_tranpose_padding_args_from_keras_to_torch(
+        ) = _convert_conv_transpose_padding_args_from_keras_to_torch(
             kernel_size=kernel_spatial_shape[i],
             stride=strides_i,
             dilation_rate=dilation_rate_i,

keras/src/backend/common/backend_utils_test.py

@@ -1,8 +1,8 @@
 from keras.src.backend.common.backend_utils import (
-    _convert_conv_tranpose_padding_args_from_keras_to_jax,
+    _convert_conv_transpose_padding_args_from_keras_to_jax,
 )
 from keras.src.backend.common.backend_utils import (
-    _convert_conv_tranpose_padding_args_from_keras_to_torch,
+    _convert_conv_transpose_padding_args_from_keras_to_torch,
 )
 from keras.src.backend.common.backend_utils import (
     _get_output_shape_given_tf_padding,
@@ -22,7 +22,7 @@ def test_valid_padding_without_output_padding(self):
         (
             left_pad,
             right_pad,
-        ) = _convert_conv_tranpose_padding_args_from_keras_to_jax(
+        ) = _convert_conv_transpose_padding_args_from_keras_to_jax(
             kernel_size=3,
             stride=2,
             dilation_rate=1,
@@ -37,7 +37,7 @@ def test_same_padding_without_output_padding(self):
         (
             left_pad,
             right_pad,
-        ) = _convert_conv_tranpose_padding_args_from_keras_to_jax(
+        ) = _convert_conv_transpose_padding_args_from_keras_to_jax(
             kernel_size=3,
             stride=2,
             dilation_rate=1,
@@ -54,7 +54,7 @@ def test_valid_padding_without_output_padding(self):
         (
             torch_padding,
             torch_output_padding,
-        ) = _convert_conv_tranpose_padding_args_from_keras_to_torch(
+        ) = _convert_conv_transpose_padding_args_from_keras_to_torch(
             kernel_size=3,
             stride=2,
             dilation_rate=1,
@@ -69,7 +69,7 @@ def test_same_padding_without_output_padding(self):
         (
             torch_padding,
             torch_output_padding,
-        ) = _convert_conv_tranpose_padding_args_from_keras_to_torch(
+        ) = _convert_conv_transpose_padding_args_from_keras_to_torch(
             kernel_size=3,
             stride=2,
             dilation_rate=1,
@@ -145,7 +145,7 @@ def test_valid_padding_with_none_output_padding(self):
         (
             torch_padding,
             torch_output_padding,
-        ) = _convert_conv_tranpose_padding_args_from_keras_to_torch(
+        ) = _convert_conv_transpose_padding_args_from_keras_to_torch(
             kernel_size=3,
             stride=2,
             dilation_rate=1,
@@ -160,7 +160,7 @@ def test_valid_padding_with_output_padding(self):
         (
             torch_padding,
             torch_output_padding,
-        ) = _convert_conv_tranpose_padding_args_from_keras_to_torch(
+        ) = _convert_conv_transpose_padding_args_from_keras_to_torch(
             kernel_size=3,
             stride=2,
             dilation_rate=1,
@@ -211,7 +211,7 @@ def test_valid_padding_with_output_padding(self):
     def test_warning_for_inconsistencies(self):
         """Test that a warning is raised for potential inconsistencies"""
         with self.assertWarns(Warning):
-            _convert_conv_tranpose_padding_args_from_keras_to_torch(
+            _convert_conv_transpose_padding_args_from_keras_to_torch(
                 kernel_size=3,
                 stride=2,
                 dilation_rate=1,
@@ -224,7 +224,7 @@ def test_same_padding_without_output_padding_for_torch_(self):
         (
             torch_padding,
             torch_output_padding,
-        ) = _convert_conv_tranpose_padding_args_from_keras_to_torch(
+        ) = _convert_conv_transpose_padding_args_from_keras_to_torch(
             kernel_size=3,
             stride=2,
             dilation_rate=1,

keras/src/backend/common/variables_test.py

@@ -397,7 +397,7 @@ def test_variable_array(self):
         self.assertAllClose(v.__array__(), np.array([1, 2, 3]))
 
 
-class VariableOpsCorrentnessTest(test_case.TestCase):
+class VariableOpsCorrectnessTest(test_case.TestCase):
     """Tests for operations on KerasVariable."""
 
     def test_int(self):

keras/src/backend/jax/distribution_lib.py

@@ -58,7 +58,7 @@ def distribute_variable(value, layout):
     if layout.is_fully_addressable:
         return jax.device_put(value, layout)
     else:
-        # Need to only distribute the value to local addressible devices, and
+        # Need to only distribute the value to local addressable devices, and
         # repack them back into global format.
         mapping = layout.addressable_devices_indices_map(value.shape)
         local_values = jax.device_put(
@@ -94,7 +94,7 @@ def distribute_tensor(tensor, layout):
     if layout.is_fully_addressable:
         return jax.device_put(tensor, layout)
     else:
-        # Need to only distribute the value to local addressible devices, and
+        # Need to only distribute the value to local addressable devices, and
         # repack them back into global format.
         mapping = layout.addressable_devices_indices_map(tensor.shape)
         local_values = jax.device_put(

keras/src/backend/jax/distribution_lib_test.py

@@ -47,9 +47,9 @@ def test_device_conversion(self):
             self.assertEqual(jax_d, converted_jax_device)
 
     @mock.patch.object(jax.distributed, "initialize", return_value=None)
-    def test_initialize_with_all_job_addresses(self, mock_jax_initialze):
+    def test_initialize_with_all_job_addresses(self, mock_jax_initialize):
         backend_dlib.initialize("10.0.0.1:1234,10.0.0.2:2345", 2, 0)
-        mock_jax_initialze.assert_called_once_with(
+        mock_jax_initialize.assert_called_once_with(
             coordinator_address="10.0.0.1:1234", num_processes=2, process_id=0
         )
 
@@ -60,9 +60,9 @@ def test_initialize_validate_job_and_process(self):
             backend_dlib.initialize("10.0.0.1:1234,10.0.0.2:2345", 3, 0)
 
     @mock.patch.object(jax.distributed, "initialize", return_value=None)
-    def test_initialize_with_coordinater_address(self, mock_jax_initialze):
+    def test_initialize_with_coordinator_address(self, mock_jax_initialize):
         backend_dlib.initialize("10.0.0.1:1234", 2, 0)
-        mock_jax_initialze.assert_called_once_with(
+        mock_jax_initialize.assert_called_once_with(
             coordinator_address="10.0.0.1:1234", num_processes=2, process_id=0
         )
 

keras/src/backend/tensorflow/numpy.py

@@ -2131,7 +2131,7 @@ def round(x, decimals=0):
         # int
         if decimals > 0:
             return x
-        # temporarilaly convert to floats
+        # temporarily convert to floats
         factor = tf.cast(math.pow(10, decimals), config.floatx())
         x = tf.cast(x, config.floatx())
     else:

keras/src/backend/tensorflow/random.py

@@ -47,15 +47,15 @@ def categorical(logits, num_samples, dtype="int64", seed=None):
 
 
 def randint(shape, minval, maxval, dtype="int32", seed=None):
-    intemediate_dtype = dtype
+    intermediate_dtype = dtype
     if standardize_dtype(dtype) not in ["int32", "int64"]:
-        intemediate_dtype = "int64"
+        intermediate_dtype = "int64"
     seed = _cast_seed(draw_seed(seed))
     output = tf.random.stateless_uniform(
         shape=shape,
         minval=minval,
         maxval=maxval,
-        dtype=intemediate_dtype,
+        dtype=intermediate_dtype,
         seed=seed,
     )
     return tf.cast(output, dtype)
@@ -109,14 +109,14 @@ def gamma(shape, alpha, dtype=None, seed=None):
     dtype = dtype or floatx()
     seed = _cast_seed(draw_seed(seed))
     # TODO: `tf.random.stateless_gamma` doesn't support bfloat16
-    intemediate_dtype = dtype
+    intermediate_dtype = dtype
     if standardize_dtype(dtype) == "bfloat16":
-        intemediate_dtype = "float32"
+        intermediate_dtype = "float32"
     return tf.cast(
         tf.random.stateless_gamma(
             shape,
             alpha=alpha,
-            dtype=intemediate_dtype,
+            dtype=intermediate_dtype,
             seed=seed,
         ),
         dtype,
@@ -127,16 +127,16 @@ def binomial(shape, counts, probabilities, dtype=None, seed=None):
     dtype = dtype or floatx()
     seed = _cast_seed(draw_seed(seed))
     # TODO: `tf.random.stateless_binomial` doesn't support bfloat16
-    intemediate_dtype = dtype
+    intermediate_dtype = dtype
     if standardize_dtype(dtype) == "bfloat16":
-        intemediate_dtype = "float32"
+        intermediate_dtype = "float32"
     return tf.cast(
         tf.random.stateless_binomial(
             shape=shape,
             seed=seed,
             counts=counts,
             probs=probabilities,
-            output_dtype=intemediate_dtype,
+            output_dtype=intermediate_dtype,
         ),
         dtype,
     )
@@ -161,11 +161,11 @@ def beta(shape, alpha, beta, dtype=None, seed=None):
     seed_2 = seed_1 + 12
 
     # TODO: `tf.random.stateless_gamma` doesn't support bfloat16
-    intemediate_dtype = dtype
+    intermediate_dtype = dtype
     if standardize_dtype(dtype) == "bfloat16":
-        intemediate_dtype = "float32"
-    alpha = tf.convert_to_tensor(alpha, dtype=intemediate_dtype)
-    beta = tf.convert_to_tensor(beta, dtype=intemediate_dtype)
+        intermediate_dtype = "float32"
+    alpha = tf.convert_to_tensor(alpha, dtype=intermediate_dtype)
+    beta = tf.convert_to_tensor(beta, dtype=intermediate_dtype)
 
     # tensorflow's tf.random.stateless_gamma has a bit of unconventional
     # implementation of the stateless_gamma function where it checks the
@@ -180,13 +180,13 @@ def beta(shape, alpha, beta, dtype=None, seed=None):
 
     gamma_a = tf.cast(
         tf.random.stateless_gamma(
-            shape=shape, seed=seed_1, alpha=alpha, dtype=intemediate_dtype
+            shape=shape, seed=seed_1, alpha=alpha, dtype=intermediate_dtype
         ),
         dtype,
     )
     gamma_b = tf.cast(
         tf.random.stateless_gamma(
-            shape=shape, seed=seed_2, alpha=beta, dtype=intemediate_dtype
+            shape=shape, seed=seed_2, alpha=beta, dtype=intermediate_dtype
         ),
         dtype,
     )

keras/src/backend/torch/linalg.py

@@ -29,7 +29,7 @@ def inv(x):
 
 def lu_factor(x):
     LU, pivots = torch.linalg.lu_factor(x)
-    # torch retuns pivots with 1-based indexing
+    # torch returns pivots with 1-based indexing
     return LU, pivots - 1
 
 

keras/src/callbacks/model_checkpoint.py

@@ -341,7 +341,7 @@ def _get_most_recently_modified_file_matching_pattern(self, pattern):
         later time of modification (for instance, when epoch/batch is used as
         formatting option), but not necessarily (when accuracy or loss is used).
         The tie-breaker is put in the logic as best effort to return the most
-        recent, and to avoid undeterministic result.
+        recent, and to avoid nondeterministic result.
 
         Modified time of a file is obtained with `os.path.getmtime()`.
 

keras/src/distribution/distribution_lib.py

@@ -694,7 +694,7 @@ class LayoutMap(collections.abc.MutableMapping):
     `TensorLayout` instance.
 
     In the normal case, the key to query is usually the `variable.path`, which
-    is the idenifier of the variable.
+    is the identifier of the variable.
 
     As shortcut, tuple or list of axis names are also allowed when inserting
     as value, and will be converted to `TensorLayout`.

keras/src/export/export_lib.py

@@ -617,7 +617,7 @@ def _check_device_compatible(self):
                 "the TF runtime in the same environment will not work. "
                 "To use JAX-native serialization for high-performance export "
                 "and serving, please install `tensorflow-gpu` and ensure "
-                "CUDA version compatiblity between your JAX and TF "
+                "CUDA version compatibility between your JAX and TF "
                 "installations."
             )
             return False

keras/src/layers/attention/grouped_query_attention_test.py

@@ -124,7 +124,7 @@ def test_initializer(self):
         backend.backend() == "numpy",
         reason="Numpy backend does not support masking.",
     )
-    def test_query_mask_progagation(self):
+    def test_query_mask_propagation(self):
         """Test automatic propagation of the query's mask."""
         layer = layers.GroupedQueryAttention(
             num_query_heads=2, num_key_value_heads=2, head_dim=2

keras/src/layers/attention/multi_head_attention_test.py

@@ -94,7 +94,7 @@ def test_high_dim_attention(
     @parameterized.named_parameters(
         ("without_key_same_proj", (4, 8), (2, 8), None, None),
         ("with_key_same_proj", (4, 8), (2, 8), (2, 3), None),
-        ("wihtout_key_different_proj", (4, 8), (2, 8), None, (3, 4)),
+        ("without_key_different_proj", (4, 8), (2, 8), None, (3, 4)),
         ("with_key_different_proj", (4, 8), (2, 8), (2, 3), (1, 5)),
         ("high_dim_same_proj", (4, 2, 3, 8), (1, 1, 5, 8), (1, 1, 5, 2), None),
         (