keras-hub-nightly 0.16.0.dev20240915160609__py3-none-any.whl → 0.16.1.dev202409220340__py3-none-any.whl

keras_hub/src/tests/test_case.py

@@ -600,6 +600,7 @@ class TestCase(tf.test.TestCase, parameterized.TestCase):
         expected_output=None,
         expected_output_shape=None,
         expected_partial_output=None,
+        expected_labels=None,
     ):
         """Run instantiation and a forward pass for a preset."""
         with self.assertRaises(Exception):
@@ -637,10 +638,17 @@ class TestCase(tf.test.TestCase, parameterized.TestCase):
 
             tree.map_structure(compare, output, expected_partial_output)
 
+        if expected_labels is not None:
+            output = ops.argmax(output, axis=-1)
+            self.assertAllEqual(output, expected_labels)
+
     def get_test_data_dir(self):
         return str(pathlib.Path(__file__).parent / "test_data")
 
-    def load_test_image(self, size):
-        path = os.path.join(self.get_test_data_dir(), "test_image.png")
-        img = keras.utils.load_img(path, target_size=size)
+    def load_test_image(self, target_size=None):
+        # From https://commons.wikimedia.org/wiki/File:California_quail.jpg
+        path = os.path.join(self.get_test_data_dir(), "test_image.jpg")
+        img = keras.utils.load_img(
+            path, target_size=target_size, keep_aspect_ratio=True
+        )
         return np.array(img)

keras_hub/src/tokenizers/byte_pair_tokenizer.py

@@ -540,6 +540,7 @@ class BytePairTokenizer(tokenizer.Tokenizer):
         if self.add_prefix_space:
             inputs = tf.strings.join([" ", inputs])
 
+        inputs = tf.convert_to_tensor(inputs)
         unbatched = inputs.shape.rank == 0
         if unbatched:
             inputs = tf.expand_dims(inputs, 0)

keras_hub/src/tokenizers/sentence_piece_tokenizer.py

@@ -238,6 +238,7 @@ class SentencePieceTokenizer(tokenizer.Tokenizer):
     @preprocessing_function
     def tokenize(self, inputs):
         self._check_vocabulary()
+        inputs = tf.convert_to_tensor(inputs)
         unbatched = inputs.shape.rank == 0
         if unbatched:
             inputs = tf.expand_dims(inputs, 0)

keras_hub/src/tokenizers/word_piece_tokenizer.py

@@ -473,6 +473,7 @@ class WordPieceTokenizer(tokenizer.Tokenizer):
     @preprocessing_function
     def tokenize(self, inputs):
         self._check_vocabulary()
+        inputs = tf.convert_to_tensor(inputs)
         unbatched = inputs.shape.rank == 0
         pattern = None
         if self.split and self.special_tokens_in_strings:

keras_hub/src/utils/imagenet/__init__.py

@@ -0,0 +1,13 @@
+# Copyright 2024 The KerasNLP Authors
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     https://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.