minor prompt change

app.py

@@ -1,10 +1,13 @@
 import gradio as gr
-from transformers import AutoFeatureExtractor, AutoModelForImageClassification  #for classifer model
-
 import torch
-from transformers import T5Tokenizer, T5ForConditionalGeneration  #for chat model
+from transformers import (
+    AutoFeatureExtractor,
+    AutoModelForImageClassification,
+    T5Tokenizer,
+    T5ForConditionalGeneration
+)
 
-# ------------------ Load classifier model + extractor ------------------
+# ------------------ LOAD CLASSIFIER ------------------
 cls_model_name = "Aalaa/Fine_tuned_Vit_trash_classification"
 feature_extractor = AutoFeatureExtractor.from_pretrained(cls_model_name)
 cls_model = AutoModelForImageClassification.from_pretrained(cls_model_name)
@@ -13,7 +16,6 @@ id2label = cls_model.config.id2label
 
 
 def classify_image(image):
-    """Run ViT classifier and return top 3 predictions."""
     inputs = feature_extractor(images=image, return_tensors="pt")
 
     with torch.no_grad():
@@ -22,28 +24,32 @@ def classify_image(image):
     logits = outputs.logits
     probs = torch.nn.functional.softmax(logits, dim=-1)[0]
 
-    top3_indices = probs.topk(3).indices.tolist()
-
-    result = {id2label[i]: float(probs[i]) for i in top3_indices}
-    return result
+    top3 = probs.topk(3).indices.tolist()
+    return {id2label[i]: float(probs[i]) for i in top3}
 
 
-#------------------ Load flan-t5 chat model------------------
+# ------------------ LOAD FLAN-T5 ------------------
 tokenizer = T5Tokenizer.from_pretrained("google/flan-t5-base")
 chat_model = T5ForConditionalGeneration.from_pretrained("google/flan-t5-base")
 
+
 def explain_recycling(class_label):
     prompt = f"""
-        Waste category: {class_label}
+You are a waste management expert.
+
+The waste item is classified as: {class_label}
+
+Provide a detailed explanation including:
 
-        Explain the followings:
-        1. What recycling type this is (e.g., plastic, organic, glass, paper, metal).
-        2. How to properly dispose of or recycle it correctly.
-        3. Environmental impact if disposed improperly
-        4. Optional tips for reducing waste or reusing the item
+1. Recycling type
+2. Why it belongs to this category
+3. Correct disposal method
+4. How it's recycled or processed
+5. Environmental impact if handled incorrectly
+6. Tips for reducing or reusing this item
 
-        Write 3–6 paragraphs, friendly and clear.
-        """
+Write 3–6 paragraphs, friendly and clear.
+"""
 
     inputs = tokenizer(prompt, return_tensors="pt").input_ids
 
@@ -57,45 +63,43 @@ def explain_recycling(class_label):
 
     return tokenizer.decode(outputs[0], skip_special_tokens=True)
 
-# ------------------ GRADIO APP ------------------
 
+# ------------------ PIPELINE ------------------
 def full_pipeline(image):
-    "Classification → get top label → explanation"
     predictions = classify_image(image)
-
-    top_label = max(predictions, key=predictions.get) # Get the top class name
+    top_label = max(predictions, key=predictions.get)
     explanation = explain_recycling(top_label)
     return predictions, explanation
 
+
+# ------------------ CUSTOM THEME ------------------
 custom_theme = gr.themes.Base(
     primary_hue="green",
     secondary_hue="blue",
-    neutral_hue="slate",
+    neutral_hue="slate"
 ).set(
     body_background_fill="#F8FFF4",
     block_background_fill="#FFFFFF",
-    button_primary_background_fill="#3BAF4A",   # Green Analyze button
+    button_primary_background_fill="#3BAF4A",
     button_primary_background_fill_hover="#2F8C3A",
     button_primary_text_color="white",
 )
 
+
+# ------------------ GRADIO UI ------------------
 with gr.Blocks() as demo:
-    gr.Markdown(
-        "<h1 style='text-align:center;'>AI Waste Classifier</h1>"
-    )
+    gr.Markdown("<h1 style='text-align:center;'>♻️ AI Waste Classifier + Eco Advisor</h1>")
 
     with gr.Row():
         img_input = gr.Image(type="pil", label="Upload waste image")
 
-    with gr.Column():
-        cls_output = gr.Label(num_top_classes=3, label="Classifier Prediction")
+    cls_output = gr.Label(num_top_classes=3, label="Classifier Prediction")
 
-        gr.Markdown("<h1 style='text-align:center;'>Disposal Advisor</h1>")
-        explain_output = gr.Textbox(
-            label="Detailed suggestions",
-            elem_id="explainbox",
-            lines=16
-        )
+    explain_output = gr.Textbox(
+        label="Detailed Recycling & Disposal Advice",
+        elem_id="explainbox",
+        lines=16
+    )
 
     analyze_btn = gr.Button("Analyze", variant="primary")
 
@@ -105,4 +109,5 @@ with gr.Blocks() as demo:
         outputs=[cls_output, explain_output]
     )
 
+
 demo.launch(theme=custom_theme, css="#explainbox {height: 350px;}")