Update app.py

app.py

@@ -1,39 +1,34 @@
-import tensorflow as tf
 import gradio as gr
-import numpy as np
+import torch
+from transformers import AutoTokenizer
+from model import SentimentClassifier
 
-# Load the saved model
-model = load_model('sentimentality.h5')
+model_state_dict = torch.load('sentimentality.h5')
+model = SentimentClassifier(2)
+model.load_state_dict(model_state_dict)
+model.eval()
 
-# Define the function to preprocess the text
-def preprocess(text):
-    # Tokenize the text
-    tokenizer = tf.keras.preprocessing.text.Tokenizer(num_words=10000)
-    tokenizer.fit_on_texts(text)
-    sequences = tokenizer.texts_to_sequences(text)
-
-    # Pad the sequences to a fixed length of 30
-    padded_sequences = tf.keras.preprocessing.sequence.pad_sequences(sequences, maxlen=30, padding='post')
+tokenizer = AutoTokenizer.from_pretrained('bert-base-uncased')
 
-    return np.array(padded_sequences)
 
-# Define the function to make predictions on the text
-def sentiment_analysis(text):
-    preprocessed_text = preprocess([text])
-    prediction = model.predict(preprocessed_text)[0][0]
-    
-    if prediction >= 0.5:
-        return "positive"
-    else:
-        return "negative"
+def preprocess(text):
+    inputs = tokenizer(text, padding='max_length',
+                       truncation=True, max_length=512, return_tensors='pt')
+    return inputs
+# Define a function to use the model to make predictions
+def predict(review):
+    inputs = preprocess(review)
+    with torch.no_grad():
+        outputs = model(inputs['input_ids'], inputs['attention_mask'])
+        predicted_class = torch.argmax(outputs[0]).item()
+    if(predicted_class==0):
+        return "It was a negative review"
+    return "It was a positive review"
 
-# Define the Gradio interface
-interface = gr.Interface(
-    fn=get_sentiment_scores,
-    inputs=gr.inputs.Textbox(placeholder="Enter a positive or negative sentence here..."),
-    outputs=gr.outputs.Textbox(label="Sentiment Label"),
-    examples=[["This is wonderful!"], ["I hate this product."]]
-)
+# Create a Gradio interface
+input_text = gr.inputs.Textbox(label="Input Text")
+output_text = gr.outputs.Textbox(label="Output Text")
+interface = gr.Interface(fn=predict, inputs=input_text, outputs=output_text)
 
-# Launch the interface
-interface.launch()
+# Run the interface
+interface.launch()