Reformat a bunch of files.

Author: fchollet

examples/audio/speaker_recognition_using_cnn.py

@@ -7,6 +7,7 @@
 Accelerator: GPU
 Converted to Keras 3 by: [Fadi Badine](https://twitter.com/fadibadine)
 """
+
 """
 ## Introduction
 

examples/audio/transformer_asr.py

@@ -6,6 +6,7 @@
 Description: Training a sequence-to-sequence Transformer for automatic speech recognition.
 Accelerator: GPU
 """
+
 """
 ## Introduction
 

examples/generative/adain.py

@@ -6,6 +6,7 @@
 Description: Neural Style Transfer with Adaptive Instance Normalization.
 Accelerator: GPU
 """
+
 """
 # Introduction
 

examples/generative/conditional_gan.py

@@ -6,6 +6,7 @@
 Description: Training a GAN conditioned on class labels to generate handwritten digits.
 Accelerator: GPU
 """
+
 """
 Generative Adversarial Networks (GANs) let us generate novel image data, video data,
 or audio data from a random input. Typically, the random input is sampled

examples/generative/dcgan_overriding_train_step.py

@@ -6,6 +6,7 @@
 Description: A simple DCGAN trained using `fit()` by overriding `train_step` on CelebA images.
 Accelerator: GPU
 """
+
 """
 ## Setup
 """

examples/generative/deep_dream.py

@@ -6,6 +6,7 @@
 Description: Generating Deep Dreams with Keras.
 Accelerator: GPU
 """
+
 """
 ## Introduction
 

examples/generative/dreambooth.py

@@ -6,6 +6,7 @@
 Description: Implementing DreamBooth.
 Accelerator: GPU
 """
+
 """
 ## Introduction
 

examples/generative/finetune_stable_diffusion.py

@@ -6,6 +6,7 @@
 Description: Fine-tuning Stable Diffusion using a custom image-caption dataset.
 Accelerator: GPU
 """
+
 """
 ## Introduction
 

examples/generative/gan_ada.py

@@ -6,6 +6,7 @@
 Description: Generating images from limited data using the Caltech Birds dataset.
 Accelerator: GPU
 """
+
 """
 ## Introduction
 

examples/generative/gaugan.py

@@ -6,6 +6,7 @@
 Description: Implementing a GauGAN for conditional image generation.
 Accelerator: GPU
 """
+
 """
 ## Introduction
 

examples/generative/lstm_character_level_text_generation.py

@@ -6,6 +6,7 @@
 Description: Generate text from Nietzsche's writings with a character-level LSTM.
 Accelerator: GPU
 """
+
 """
 ## Introduction
 

examples/generative/molecule_generation.py

@@ -6,6 +6,7 @@
 Description: Implementing a Convolutional Variational AutoEncoder (VAE) for Drug Discovery.
 Accelerator: GPU
 """
+
 """
 ## Introduction
 

examples/generative/stylegan.py

@@ -6,6 +6,7 @@
 Description: Implementation of StyleGAN for image generation.
 Accelerator: GPU
 """
+
 """
 ## Introduction
 

examples/generative/text_generation_fnet.py

@@ -6,6 +6,7 @@
 Description: FNet transformer for text generation in Keras.
 Accelerator: GPU
 """
+
 """
 ## Introduction
 

examples/generative/text_generation_with_miniature_gpt.py

@@ -6,6 +6,7 @@
 Description: Implement a miniature version of GPT and train it to generate text.
 Accelerator: GPU
 """
+
 """
 ## Introduction
 

examples/generative/vq_vae.py

@@ -6,6 +6,7 @@
 Description: Training a VQ-VAE for image reconstruction and codebook sampling for generation.
 Accelerator: GPU
 """
+
 """
 In this example, we develop a Vector Quantized Variational Autoencoder (VQ-VAE).
 VQ-VAE was proposed in

examples/graph/gat_node_classification.py

@@ -6,6 +6,7 @@
 Description: An implementation of a Graph Attention Network (GAT) for node classification.
 Accelerator: GPU
 """
+
 """
 ## Introduction
 

examples/graph/mpnn-molecular-graphs.py

@@ -6,6 +6,7 @@
 Description: Implementation of an MPNN to predict blood-brain barrier permeability.
 Accelerator: GPU
 """
+
 """
 ## Introduction
 

examples/keras_recipes/antirectifier.py

@@ -6,6 +6,7 @@
 Description: Demonstration of custom layer creation.
 Accelerator: GPU
 """
+
 """
 ## Introduction
 

examples/keras_recipes/better_knowledge_distillation.py

@@ -6,6 +6,7 @@
 Description: Training better student models via knowledge distillation with function matching.
 Accelerator: GPU
 """
+
 """
 ## Introduction
 

examples/keras_recipes/reproducibility_recipes.py

@@ -6,6 +6,7 @@
 Description: Demonstration of random weight initialization and reproducibility in Keras models.
 Accelerator: GPU
 """
+
 """
 ## Introduction
 

examples/keras_recipes/sklearn_metric_callbacks.py

@@ -6,6 +6,7 @@
 Description: This example shows how to use Keras callbacks to evaluate and export non-TensorFlow based metrics.
 Accelerator: GPU
 """
+
 """
 ## Introduction
 

examples/keras_recipes/subclassing_conv_layers.py

@@ -6,6 +6,7 @@
 Description: This example shows how to implement custom convolution layers using the `Conv.convolution_op()` API.
 Accelerator: GPU
 """
+
 """
 ## Introduction
 

examples/keras_recipes/tensorflow_numpy_models.py

@@ -6,6 +6,7 @@
 Description: Overview of how to use the TensorFlow NumPy API to write Keras models.
 Accelerator: GPU
 """
+
 """
 ## Introduction
 

examples/keras_recipes/tfrecord.py

@@ -6,6 +6,7 @@
 Description: Loading TFRecords for computer vision models.
 Accelerator: TPU
 """
+
 """
 ## Introduction + Set Up
 

examples/keras_recipes/trainer_pattern.py

@@ -6,6 +6,7 @@
 Description: Guide on how to share a custom training step across multiple Keras models.
 Accelerator: GPU
 """
+
 """
 ## Introduction
 

examples/nlp/active_learning_review_classification.py

@@ -6,6 +6,7 @@
 Description: Demonstrating the advantages of active learning through review classification.
 Accelerator: GPU
 """
+
 """
 ## Introduction
 

examples/nlp/bidirectional_lstm_imdb.py

@@ -6,6 +6,7 @@
 Description: Train a 2-layer bidirectional LSTM on the IMDB movie review sentiment classification dataset.
 Accelerator: GPU
 """
+
 """
 ## Setup
 """

examples/nlp/lstm_seq2seq.py

@@ -6,6 +6,7 @@
 Description: Character-level recurrent sequence-to-sequence model.
 Accelerator: GPU
 """
+
 """
 ## Introduction
 

examples/nlp/masked_language_modeling.py

@@ -6,6 +6,7 @@
 Description: Implement a Masked Language Model (MLM) with BERT and fine-tune it on the IMDB Reviews dataset.
 Accelerator: GPU
 """
+
 """
 ## Introduction
 
@@ -196,9 +197,9 @@ def get_masked_input_and_labels(encoded_texts):
     # Set input to [MASK] which is the last token for the 90% of tokens
     # This means leaving 10% unchanged
     inp_mask_2mask = inp_mask & (np.random.rand(*encoded_texts.shape) < 0.90)
-    encoded_texts_masked[
-        inp_mask_2mask
-    ] = mask_token_id  # mask token is the last in the dict
+    encoded_texts_masked[inp_mask_2mask] = (
+        mask_token_id  # mask token is the last in the dict
+    )
 
     # Set 10% to a random token
     inp_mask_2random = inp_mask_2mask & (np.random.rand(*encoded_texts.shape) < 1 / 9)
@@ -293,9 +294,11 @@ def bert_module(query, key, value, i):
 def get_pos_encoding_matrix(max_len, d_emb):
     pos_enc = np.array(
         [
-            [pos / np.power(10000, 2 * (j // 2) / d_emb) for j in range(d_emb)]
-            if pos != 0
-            else np.zeros(d_emb)
+            (
+                [pos / np.power(10000, 2 * (j // 2) / d_emb) for j in range(d_emb)]
+                if pos != 0
+                else np.zeros(d_emb)
+            )
             for pos in range(max_len)
         ]
     )

examples/nlp/mlm_training_tpus.py

@@ -6,6 +6,7 @@
 Description: Train a masked language model on TPUs using 🤗 Transformers.
 Accelerator: TPU
 """
+
 """
 ## Introduction
 

examples/nlp/multi_label_classification.py

@@ -6,6 +6,7 @@
 Description: Implementing a large-scale multi-label text classification model.
 Accelerator: GPU
 """
+
 """
 ## Introduction
 

examples/nlp/multimodal_entailment.py

@@ -6,6 +6,7 @@
 Description: Training a multimodal model for predicting entailment.
 Accelerator: GPU
 """
+
 """
 ## Introduction
 

examples/nlp/ner_transformers.py

@@ -6,6 +6,7 @@
 Description: NER using the Transformers and data from CoNLL 2003 shared task.
 Accelerator: GPU
 """
+
 """
 ## Introduction
 

examples/nlp/neural_machine_translation_with_transformer.py

@@ -6,6 +6,7 @@
 Description: Implementing a sequence-to-sequence Transformer and training it on a machine translation task.
 Accelerator: GPU
 """
+
 """
 ## Introduction
 

examples/nlp/question_answering.py

@@ -6,6 +6,7 @@
 Description: Question answering implementation using Keras and Hugging Face Transformers.
 Accelerator: GPU
 """
+
 """
 ## Introduction to Question Answering
 

examples/nlp/semantic_similarity_with_bert.py

@@ -6,6 +6,7 @@
 Description: Natural Language Inference by fine-tuning BERT model on SNLI Corpus.
 Accelerator: GPU
 """
+
 """
 ## Introduction
 

examples/nlp/text_classification_from_scratch.py

@@ -6,6 +6,7 @@
 Description: Text sentiment classification starting from raw text files.
 Accelerator: GPU
 """
+
 """
 ## Introduction
 

examples/nlp/text_classification_with_transformer.py

@@ -7,6 +7,7 @@
 Accelerator: GPU
 Converted to Keras 3 by: [Sitam Meur](https://github.com/sitamgithub-MSIT)
 """
+
 """
 ## Setup
 """

examples/nlp/text_extraction_with_bert.py

@@ -6,6 +6,7 @@
 Description: Fine tune pretrained BERT from HuggingFace Transformers on SQuAD.
 Accelerator: TPU
 """
+
 """
 ## Introduction
 

examples/rl/actor_critic_cartpole.py

@@ -6,6 +6,7 @@
 Description: Implement Actor Critic Method in CartPole environment.
 Accelerator: NONE
 """
+
 """
 ## Introduction
 

examples/rl/ddpg_pendulum.py

@@ -6,6 +6,7 @@
 Description: Implementing DDPG algorithm on the Inverted Pendulum Problem.
 Accelerator: NONE
 """
+
 """
 ## Introduction
 

examples/rl/deep_q_network_breakout.py

@@ -6,6 +6,7 @@
 Description: Play Atari Breakout with a Deep Q-Network.
 Accelerator: NONE
 """
+
 """
 ## Introduction
 

examples/structured_data/classification_with_grn_and_vsn.py

@@ -194,9 +194,12 @@
 )
 # Feature default values.
 COLUMN_DEFAULTS = [
-    [0.0]
-    if feature_name in NUMERIC_FEATURE_NAMES + [TARGET_FEATURE_NAME, WEIGHT_COLUMN_NAME]
-    else ["NA"]
+    (
+        [0.0]
+        if feature_name
+        in NUMERIC_FEATURE_NAMES + [TARGET_FEATURE_NAME, WEIGHT_COLUMN_NAME]
+        else ["NA"]
+    )
     for feature_name in CSV_HEADER
 ]
 

examples/structured_data/collaborative_filtering_movielens.py

@@ -6,6 +6,7 @@
 Description: Recommending movies using a model trained on Movielens dataset.
 Accelerator: GPU
 """
+
 """
 ## Introduction