Update app.py

app.py

@@ -2,82 +2,73 @@ import re
 import gradio as gr
 import torch
 from PIL import Image
-from transformers import pipeline, AutoProcessor, AutoModelForVision2Seq, AutoTokenizer, AutoModelForSeq2SeqLM
+from transformers import (
+    pipeline,
+    AutoProcessor,
+    AutoModelForVision2Seq,
+    AutoTokenizer,
+    AutoModelForSeq2SeqLM,
+)
 
 # Auto-detect CPU/GPU
-device = 0 if torch.cuda.is_available() else -1
-
-# 1) BLIP captioner - Fixed tokenizer usage
-try:
-    processor = AutoProcessor.from_pretrained("Salesforce/blip-image-captioning-large")
-    model = AutoModelForVision2Seq.from_pretrained("Salesforce/blip-image-captioning-large")
-    
-    caption_pipe = pipeline(
-        "image-to-text",
-        model=model,
-        tokenizer=processor.tokenizer,
-        image_processor=processor.image_processor,
-        device=device
-    )
-    print("✅ BLIP model loaded successfully")
-except Exception as e:
-    print(f"❌ Error loading BLIP model: {e}")
-    raise
-
-# 2) Flan-T5 for text-to-text - Fixed tokenizer initialization
+DEVICE = 0 if torch.cuda.is_available() else -1
+
+# 1) BLIP captioner
+processor = AutoProcessor.from_pretrained("Salesforce/blip-image-captioning-large")
+blip_model = AutoModelForVision2Seq.from_pretrained("Salesforce/blip-image-captioning-large")
+caption_pipe = pipeline(
+    task="image-to-text",
+    model=blip_model,
+    tokenizer=processor.tokenizer,
+    image_processor=processor.image_processor,
+    device=DEVICE,
+)
+
+# 2) FLAN-T5 for text-to-text
 FLAN_MODEL = "google/flan-t5-large"
-try:
-    # Load tokenizer and model separately for better control
-    flan_tokenizer = AutoTokenizer.from_pretrained(FLAN_MODEL)
-    flan_model = AutoModelForSeq2SeqLM.from_pretrained(FLAN_MODEL)
-    
-    # Create pipelines with explicit tokenizer
-    category_pipe = pipeline(
-        "text2text-generation",
-        model=flan_model,
-        tokenizer=flan_tokenizer,
-        device=device,
-        max_new_tokens=32,
-        do_sample=True,
-        temperature=1.0,
-    )
-    
-    analysis_pipe = pipeline(
-        "text2text-generation",
-        model=flan_model,
-        tokenizer=flan_tokenizer,
-        device=device,
-        max_new_tokens=256,
-        do_sample=True,
-        temperature=1.0,
-    )
-    
-    suggestion_pipe = pipeline(
-        "text2text-generation",
-        model=flan_model,
-        tokenizer=flan_tokenizer,
-        device=device,
-        max_new_tokens=256,
-        do_sample=True,
-        temperature=1.0,
-    )
-    
-    # Expander when BLIP caption is too short
-    expansion_pipe = pipeline(
-        "text2text-generation",
-        model=flan_model,
-        tokenizer=flan_tokenizer,
-        device=device,
-        max_new_tokens=128,
-        do_sample=False,
-    )
-    
-    print("✅ Flan-T5 model loaded successfully")
-except Exception as e:
-    print(f"❌ Error loading Flan-T5 model: {e}")
-    raise
-
-# Example gallery helper returns 10 example ad URLs
+flan_tokenizer = AutoTokenizer.from_pretrained(FLAN_MODEL)
+flan_model = AutoModelForSeq2SeqLM.from_pretrained(FLAN_MODEL)
+
+category_pipe = pipeline(
+    "text2text-generation",
+    model=flan_model,
+    tokenizer=flan_tokenizer,
+    device=DEVICE,
+    max_new_tokens=32,
+    do_sample=True,
+    temperature=1.0,
+)
+
+analysis_pipe = pipeline(
+    "text2text-generation",
+    model=flan_model,
+    tokenizer=flan_tokenizer,
+    device=DEVICE,
+    max_new_tokens=256,
+    do_sample=True,
+    temperature=1.0,
+)
+
+suggestion_pipe = pipeline(
+    "text2text-generation",
+    model=flan_model,
+    tokenizer=flan_tokenizer,
+    device=DEVICE,
+    max_new_tokens=256,
+    do_sample=True,
+    temperature=1.0,
+)
+
+expansion_pipe = pipeline(
+    "text2text-generation",
+    model=flan_model,
+    tokenizer=flan_tokenizer,
+    device=DEVICE,
+    max_new_tokens=128,
+    do_sample=False,
+)
+
+# Example gallery helper
 def get_recommendations():
     return [
         "https://i.imgur.com/InC88PP.jpeg",
@@ -92,110 +83,87 @@ def get_recommendations():
         "https://i.imgur.com/Xj92Cjv.jpeg",
     ]
 
-# Main processing function with error handling
+# Main processing function
+
 def process(image: Image):
-    try:
-        if image is None:
-            return "", "", "", get_recommendations()
-        
-        # 1) BLIP caption
-        caption_result = caption_pipe(image, max_new_tokens=64)
-        caption = caption_result[0]['generated_text'].strip()
-
-        # 1a) Expand caption if too short
-        if len(caption.split()) < 3:
-            desc_result = expansion_pipe(f"Expand into a detailed description: {caption}")
-            desc = desc_result[0]['generated_text'].strip()
-        else:
-            desc = caption
-
-        # 2) Ad category
-        cat_prompt = (
-            f"Description: {desc}\n\n"
-            "Provide a concise category label for this ad (e.g. 'Food', 'Fitness'):"
-        )
-        category_result = category_pipe(cat_prompt)
-        category = category_result[0]['generated_text'].splitlines()[0].strip()
+    if image is None:
+        return "", "", "", "", get_recommendations()
+
+    # 1) BLIP caption
+    caption_res = caption_pipe(image, max_new_tokens=64)
+    raw_caption = caption_res[0]["generated_text"].strip()
+
+    # 1a) Expand if too short
+    if len(raw_caption.split()) < 3:
+        exp = expansion_pipe(f"Expand into a detailed description: {raw_caption}")
+        desc = exp[0]["generated_text"].strip()
+    else:
+        desc = raw_caption
+
+    # 2) Category
+    cat_prompt = (
+        f"Description: {desc}\n\n"
+        "Provide a concise category label for this ad (e.g. 'Food', 'Fitness'):"
+    )
+    cat_out = category_pipe(cat_prompt)[0]["generated_text"].splitlines()[0].strip()
 
-        # 3) Five-sentence analysis
-        ana_prompt = (
-            f"Based on this advertisement description: {desc}\n\n"
-            "Write exactly 5 detailed sentences analyzing this advertisement. Cover: 1) What product/service is being advertised, 2) The main visual elements and design, 3) The target audience, 4) The marketing message or value proposition, 5) The emotional appeal or persuasion technique used. Make each sentence substantial and informative."
-        )
-        raw_ana_result = analysis_pipe(ana_prompt)
-        raw_ana = raw_ana_result[0]['generated_text'].strip()
-        sentences = re.split(r'(?<=[.!?])\s+', raw_ana)
-        # Take first 5 sentences and ensure they're substantial
-        analysis_sentences = []
-        for i, sentence in enumerate(sentences[:8]):  # Look at more sentences to find 5 good ones
-            if len(sentence.strip()) > 20 and len(analysis_sentences) < 5:  # Filter short sentences
-                analysis_sentences.append(sentence.strip())
-        analysis = " ".join(analysis_sentences[:5])
-
-        # 4) Five bullet-point suggestions
-        sug_prompt = (
-            f"Based on this advertisement: {desc}\n\n"
-            "Provide exactly 5 specific, actionable improvement suggestions for this advertisement. Focus on concrete changes like: visual design improvements, clearer messaging, better call-to-action, enhanced targeting, or stronger emotional appeal. Each suggestion should be one clear sentence starting with '- ' and be practical to implement."
-        )
-        raw_sug_result = suggestion_pipe(sug_prompt)
-        raw_sug = raw_sug_result[0]['generated_text'].strip()
-        
-        # Better parsing of suggestions
-        lines = raw_sug.split('\n')
-        suggestions_list = []
-        for line in lines:
-            line = line.strip()
-            if line.startswith('-'):
-                suggestions_list.append(line)
-            elif line and not line.startswith('-') and len(suggestions_list) < 5:
-                suggestions_list.append(f"- {line}")
-        
-        # Ensure we have exactly 5 suggestions
-        while len(suggestions_list) < 5:
-            suggestions_list.append(f"- Improve visual hierarchy and readability")
-        
-        suggestions = '\n'.join(suggestions_list[:5])
-
-        return category, analysis, suggestions, get_recommendations()
-    
-    except Exception as e:
-        error_msg = f"Error analyzing advertisement: {str(e)}"
-        print(error_msg)
-        return "Analysis failed", error_msg, "", get_recommendations()
-
-# Gradio UI definition
+    # 3) Five-sentence analysis
+    ana_prompt = (
+        f"Description: {desc}\n\n"
+        "Write exactly five sentences explaining what this ad communicates and its emotional impact."
+    )
+    ana_raw = analysis_pipe(ana_prompt)[0]["generated_text"].strip()
+    sentences = re.split(r'(?<=[.!?])\s+', ana_raw)
+    analysis = " ".join(sentences[:5])
+
+    # 4) Five bullet-point suggestions
+    sug_prompt = (
+        f"Description: {desc}\n\n"
+        "Provide five distinct improvement suggestions, each starting with '- '."
+    )
+    sug_raw = suggestion_pipe(sug_prompt)[0]["generated_text"].strip()
+    bullets = [l for l in sug_raw.splitlines() if l.startswith("-")]
+    if len(bullets) < 5:
+        for line in sug_raw.splitlines():
+            if len(bullets) >= 5:
+                break
+            if line and not line.startswith("-"):
+                bullets.append("- " + line)
+    while len(bullets) < 5:
+        bullets.append("- Improve visual appeal and clarity.")
+    suggestions = "\n".join(bullets[:5])
+
+    return raw_caption, cat_out, analysis, suggestions, get_recommendations()
+
+# Gradio UI
 def main():
     with gr.Blocks(title="Smart Ad Analyzer") as demo:
         gr.Markdown("## 📢 Smart Ad Analyzer")
         gr.Markdown(
-            "Transform your advertising with AI-powered insights! Upload any advertisement image to receive:\n\n"
-            "🎯 **Smart Categorization** - Automatically classify your ad type\n\n"
-            "🔍 **Deep Analysis** - Get a comprehensive 5-sentence breakdown of your ad's message, visual elements, and emotional impact\n\n"
-            "💡 **Actionable Improvements** - Receive 5 specific, practical suggestions to enhance your ad's effectiveness\n\n"
-            "📸 **Inspiration Gallery** - Discover example ads after your analysis\n\n"
-            "Perfect for marketers, business owners, and creative professionals looking to optimize their advertising campaigns!"
+            "Upload an ad image to get:\n"
+            "- 🔍 **BLIP Caption**\n"
+            "- 📂 **Ad Category**\n"
+            "- 📊 **Five-sentence Analysis**\n"
+            "- 🚀 **Five Improvement Suggestions**\n"
+            "- 📸 **Example Ads**"
         )
-
         with gr.Row():
             inp = gr.Image(type='pil', label='Upload Ad Image')
             with gr.Column():
+                cap_out = gr.Textbox(label='🔍 BLIP Caption', interactive=False)
                 cat_out = gr.Textbox(label='📂 Ad Category', interactive=False)
-                ana_out = gr.Textbox(label='📊 Ad Analysis', lines=8, interactive=False)
-                sug_out = gr.Textbox(label='🚀 Improvement Suggestions', lines=8, interactive=False)
-                btn = gr.Button('Analyze Ad', size='sm', variant='primary')
-
-        gallery = gr.Gallery(label='Example Ads')  # Empty initially
-
+                ana_out = gr.Textbox(label='📊 Ad Analysis', lines=5, interactive=False)
+                sug_out = gr.Textbox(label='🚀 Improvement Suggestions', lines=5, interactive=False)
+                btn = gr.Button('Analyze Ad', variant='primary')
+        gallery = gr.Gallery(label='Example Ads')
         btn.click(
             fn=process,
             inputs=[inp],
-            outputs=[cat_out, ana_out, sug_out, gallery],
+            outputs=[cap_out, cat_out, ana_out, sug_out, gallery],
         )
-
         gr.Markdown('Made by Simon Thalmay')
-
     return demo
 
-if __name__ == '__main__':
+if __name__ == "__main__":
     demo = main()
-    demo.launch()
+    demo.launch()