Duplicate from keras-io/bert-semantic-similarity

Co-authored-by: vumichien <vumichien@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,27 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,14 @@
+---
+title: Semantic Similarity with BERT
+emoji: 🌇🌆
+colorFrom: red
+colorTo: blue
+sdk: gradio
+sdk_version: 3.0.24
+app_file: app.py
+pinned: false
+license: apache-2.0
+duplicated_from: keras-io/bert-semantic-similarity
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,100 @@
+from huggingface_hub import from_pretrained_keras
+import numpy as np
+import gradio as gr
+import transformers
+import tensorflow as tf
+
+class BertSemanticDataGenerator(tf.keras.utils.Sequence):
+    """Generates batches of data."""
+    def __init__(
+        self,
+        sentence_pairs,
+        labels,
+        batch_size=32,
+        shuffle=True,
+        include_targets=True,
+    ):
+        self.sentence_pairs = sentence_pairs
+        self.labels = labels
+        self.shuffle = shuffle
+        self.batch_size = batch_size
+        self.include_targets = include_targets
+        # Load our BERT Tokenizer to encode the text.
+        # We will use base-base-uncased pretrained model.
+        self.tokenizer = transformers.BertTokenizer.from_pretrained(
+            "bert-base-uncased", do_lower_case=True
+        )
+        self.indexes = np.arange(len(self.sentence_pairs))
+        self.on_epoch_end()
+
+    def __len__(self):
+        # Denotes the number of batches per epoch.
+        return len(self.sentence_pairs) // self.batch_size
+
+    def __getitem__(self, idx):
+        # Retrieves the batch of index.
+        indexes = self.indexes[idx * self.batch_size : (idx + 1) * self.batch_size]
+        sentence_pairs = self.sentence_pairs[indexes]
+
+        # With BERT tokenizer's batch_encode_plus batch of both the sentences are
+        # encoded together and separated by [SEP] token.
+        encoded = self.tokenizer.batch_encode_plus(
+            sentence_pairs.tolist(),
+            add_special_tokens=True,
+            max_length=128,
+            return_attention_mask=True,
+            return_token_type_ids=True,
+            pad_to_max_length=True,
+            return_tensors="tf",
+        )
+
+        # Convert batch of encoded features to numpy array.
+        input_ids = np.array(encoded["input_ids"], dtype="int32")
+        attention_masks = np.array(encoded["attention_mask"], dtype="int32")
+        token_type_ids = np.array(encoded["token_type_ids"], dtype="int32")
+
+        # Set to true if data generator is used for training/validation.
+        if self.include_targets:
+            labels = np.array(self.labels[indexes], dtype="int32")
+            return [input_ids, attention_masks, token_type_ids], labels
+        else:
+            return [input_ids, attention_masks, token_type_ids]
+
+model = from_pretrained_keras("keras-io/bert-semantic-similarity")
+labels = ["contradiction", "entailment", "neutral"]
+
+def predict(sentence1, sentence2):
+    sentence_pairs = np.array([[str(sentence1), str(sentence2)]])
+    test_data = BertSemanticDataGenerator(
+        sentence_pairs, labels=None, batch_size=1, shuffle=False, include_targets=False,
+    )
+    probs = model.predict(test_data[0])[0]
+    
+    labels_probs = {labels[i]: float(probs[i]) for i, _ in enumerate(labels)}
+    return labels_probs
+    
+    #idx = np.argmax(proba)
+    #proba = f"{proba[idx]*100:.2f}%"
+    #pred = labels[idx]
+    #return f'The semantic similarity of two input sentences is {pred} with {proba} of probability'
+
+inputs = [
+         gr.Audio(source = "upload", label='Upload audio file', type="filepath"),
+]
+
+examples = [["Two women are observing something together.", "Two women are standing with their eyes closed."],
+            ["A smiling costumed woman is holding an umbrella", "A happy woman in a fairy costume holds an umbrella"],
+            ["A soccer game with multiple males playing", "Some men are playing a sport"],            
+]
+
+gr.Interface(
+    fn=predict,
+    title="Semantic Similarity with BERT",
+    description = "Natural Language Inference by fine-tuning BERT model on SNLI Corpus 📰",
+    inputs=["text", "text"],
+    examples=examples,
+    #outputs=gr.Textbox(label='Prediction'),
+    outputs=gr.outputs.Label(num_top_classes=3, label='Semantic similarity'),
+    cache_examples=True,
+    article = "Author: <a href=\"https://huggingface.co/vumichien\">Vu Minh Chien</a>. Based on the keras example from <a href=\"https://keras.io/examples/nlp/semantic_similarity_with_bert/\">Mohamad Merchant</a>",
+).launch(debug=True, enable_queue=True)

requirements.txt

@@ -0,0 +1,6 @@
+tensorflow
+keras
+gradio
+tensorflow_addons
+tensorflow-io
+transformers