Initial commit

.gitattributes

@@ -0,0 +1,36 @@
+*.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
+*.ckpt 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
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz 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
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl 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
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* 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
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+*.keras filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,2 @@
+seasme
+data

README.md

@@ -0,0 +1,13 @@
+---
+title: Questions Similarity
+emoji: 🐠
+colorFrom: gray
+colorTo: gray
+sdk: gradio
+sdk_version: 4.44.1
+app_file: app.py
+pinned: false
+short_description: Checks similarity among two questions using Seasme network.
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,20 @@
+from inference import predict
+import gradio as gr
+
+# Function to call the FastAPI backend
+def predict(question1, question2, threshold):
+
+    similarity, is_same = predict(question1, question2, threshold, verbose=True)
+    
+    return similarity, is_same
+    
+
+# Launch the Gradio interface
+if __name__ == "__main__":
+    gr.Interface(predict,
+                 inputs=[gr.Textbox(placeholder="Is Leonel Messi the Goat ?"),
+                         gr.Textbox(placeholder="Is Leonel Messi the best player ever?"), 
+                         gr.Slider(minimum=0.0, maximum=1.0)],
+                 outputs=["number", "textbox"],
+                 description="This app tells us whether the two questions are similar or not"
+                 )

inference.py

@@ -0,0 +1,45 @@
+import tensorflow as tf
+import numpy
+model = tf.keras.models.load_model('./model/trained_model.keras', safe_mode=False, compile=False)
+
+# Show the model architecture
+model.summary()
+
+# GRADED FUNCTION: predict
+def predict(question1, question2, threshold, verbose=False):
+    """Function for predicting if two questions are duplicates.
+
+    Args:
+        question1 (str): First question.
+        question2 (str): Second question.
+        threshold (float): Desired threshold.
+        verbose (bool, optional): If the results should be printed out. Defaults to False.
+
+    Returns:
+        bool: True if the questions are duplicates, False otherwise.
+    """
+    generator = tf.data.Dataset.from_tensor_slices((([question1], [question2]),None)).batch(batch_size=1)
+    
+    ### START CODE HERE ###
+    
+    # Call the predict method of your model and save the output into v1v2
+    v1v2 = model.predict(generator)
+    out_size = v1v2.shape[1]
+    # Extract v1 and v2 from the model output
+    v1 = v1v2[:,:int(out_size/2)]
+    v2 = v1v2[:,int(out_size/2):]
+    print(v1.shape)
+    # Take the dot product to compute cos similarity of each pair of entries, v1, v2
+    # Since v1 and v2 are both vectors, use the function tf.math.reduce_sum instead of tf.linalg.matmul
+    d = tf.reduce_sum(v1 * v2)
+    # Is d greater than the threshold?
+    res = d > threshold
+
+    ### END CODE HERE ###
+    
+    if(verbose):
+        print("Q1  = ", question1, "\nQ2  = ", question2)
+        print("d   = ", d.numpy())
+        print("res = ", res.numpy())
+
+    return d.numpy(), res.numpy()

model/trained_model.keras

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:882a852a01cf4bfc3c029089855f1082df1944b7ef2b32a142db341fd668fb9b
+size 57860766

requirements.txt

@@ -0,0 +1,5 @@
+gradio
+tensorflow==2.13.0
+keras==2.13.1
+numpy
+pandas