Update app.py

app.py

@@ -1,41 +1,44 @@
 import gradio as gr
-import spaces
-from transformers import AutoImageProcessor
-from transformers import SiglipForImageClassification
-from transformers.image_utils import load_image
-from PIL import Image
-import torch
+from gender_classification import gender_classification
+from emotion_classification import emotion_classification
 
-# Load model and processor
-model_name = "prithivMLmods/Gender-Classifier-Mini"
-model = SiglipForImageClassification.from_pretrained(model_name)
-processor = AutoImageProcessor.from_pretrained(model_name)
+# Function to update the selected model state when a button is clicked.
+def select_model(model_name):
+    return model_name
 
-@spaces.GPU
-def gender_classification(image):
-    """Predicts gender category for an image."""
-    image = Image.fromarray(image).convert("RGB")
-    inputs = processor(images=image, return_tensors="pt")
-    
-    with torch.no_grad():
-        outputs = model(**inputs)
-        logits = outputs.logits
-        probs = torch.nn.functional.softmax(logits, dim=1).squeeze().tolist()
-    
-    labels = {"0": "Female ♀", "1": "Male ♂"}
-    predictions = {labels[str(i)]: round(probs[i], 3) for i in range(len(probs))}
-    
-    return predictions
+# Main classification function that calls the appropriate model based on selection.
+def classify(image, model_name):
+    if model_name == "gender":
+        return gender_classification(image)
+    elif model_name == "emotion":
+        return emotion_classification(image)
+    else:
+        return {"Error": "No model selected"}
 
-# Create Gradio interface
-iface = gr.Interface(
-    fn=gender_classification,
-    inputs=gr.Image(type="numpy"),
-    outputs=gr.Label(label="Prediction Scores"),
-    title="Gender Classification",
-    description="Upload an image to classify its gender."
-)
+with gr.Blocks() as demo:
+    # Sidebar with title and model selection buttons
+    with gr.Sidebar():
+        gr.Markdown("# SigLIP2 Classification")
+        with gr.Row():
+            gender_btn = gr.Button("Gender Classification")
+            emotion_btn = gr.Button("Emotion Classification")
+        # State to hold the current model choice
+        selected_model = gr.State("gender")
+        # Set model state when buttons are clicked
+        gender_btn.click(fn=select_model, inputs=[], outputs=selected_model, _js="() => 'gender'")
+        emotion_btn.click(fn=select_model, inputs=[], outputs=selected_model, _js="() => 'emotion'")
+        gr.Markdown("### Current Model:")
+        model_display = gr.Textbox(value="gender", interactive=False)
+        # Update display when state changes
+        selected_model.change(lambda m: m, selected_model, model_display)
 
-# Launch the app
-if __name__ == "__main__":
-    iface.launch()
+    # Main interface: image input, analyze button, and prediction output.
+    with gr.Column():
+        image_input = gr.Image(type="numpy", label="Upload Image")
+        analyze_btn = gr.Button("Analyze")
+        output_label = gr.Label(label="Prediction Scores")
+
+        # When the "Analyze" button is clicked, use the selected model to classify the image.
+        analyze_btn.click(fn=classify, inputs=[image_input, selected_model], outputs=output_label)
+
+demo.launch()