Create app.py

app.py

@@ -0,0 +1,67 @@
+import gradio as gr
+import torch
+from transformers import ViTFeatureExtractor, ViTForImageClassification, pipeline
+from PIL import Image
+import easyocr
+from aesthetic_score import AestheticScorer
+
+# Initialize models
+# Vision Transformer for Emotion Detection
+feature_extractor = ViTFeatureExtractor.from_pretrained("nateraw/vit-base-beauty")
+model = ViTForImageClassification.from_pretrained("nateraw/vit-base-beauty")
+emotion_detector = pipeline("image-classification", model=model, feature_extractor=feature_extractor)
+
+# OCR for Text Detection
+reader = easyocr.Reader(['en'])
+
+# Aesthetic Scoring Model (Placeholder)
+aesthetic_scorer = AestheticScorer()
+
+# Function to analyze a single thumbnail
+def analyze_single_thumbnail(image):
+    # Text detection using OCR
+    ocr_result = reader.readtext(image)
+    text_detected = " ".join([item[1] for item in ocr_result]) if ocr_result else "No text found"
+
+    # Emotion detection for overall appeal
+    emotions = emotion_detector(image)
+    main_emotion = max(emotions, key=lambda x: x['score'])['label'] if emotions else "Unknown"
+
+    # Aesthetic scoring
+    aesthetic_score = aesthetic_scorer.score(image)
+
+    return {
+        "Detected Text": text_detected,
+        "Emotion Detected": main_emotion,
+        "Aesthetic Score": aesthetic_score,
+    }
+
+# Function to compare two thumbnails
+def compare_thumbnails(image1, image2):
+    result1 = analyze_single_thumbnail(image1)
+    result2 = analyze_single_thumbnail(image2)
+
+    # Determine which thumbnail might perform better based on scores
+    if result1["Aesthetic Score"] > result2["Aesthetic Score"]:
+        better_thumbnail = "Thumbnail 1 is likely better."
+    elif result2["Aesthetic Score"] > result1["Aesthetic Score"]:
+        better_thumbnail = "Thumbnail 2 is likely better."
+    else:
+        better_thumbnail = "Both thumbnails have similar appeal."
+
+    return result1, result2, better_thumbnail
+
+# Gradio Interface
+iface = gr.Interface(
+    fn=compare_thumbnails,
+    inputs=[gr.Image(type="pil"), gr.Image(type="pil")],
+    outputs=[
+        gr.JSON(label="Thumbnail 1 Analysis"),
+        gr.JSON(label="Thumbnail 2 Analysis"),
+        gr.Textbox(label="Comparison Result"),
+    ],
+    title="YouTube Thumbnail Comparator",
+    description="Upload two thumbnails to compare their effectiveness based on detected text, emotions, and aesthetic score.",
+)
+
+iface.launch()