Create Testapp.txt

Testapp.txt

@@ -0,0 +1,385 @@
+import gradio as gr
+import torch
+import clip
+import numpy as np
+import random
+import os
+from PIL import Image
+from ultralytics import YOLO # Still needed for person detection
+from gtts import gTTS
+import uuid
+import time
+import tempfile
+
+# --- Configuration ---
+DEVICE = "cuda" if torch.cuda.is_available() else "cpu"
+YOLO_PERSON_MODEL_PATH = 'yolov8n.pt'  # Standard YOLOv8 for person detection
+# YOLO_FASHION_MODEL_PATH = 'best.pt' # REMOVED - Not using fashion model anymore
+CLIP_MODEL_NAME = "ViT-B/32"
+
+# --- Load Models ---
+print(f"Using device: {DEVICE}")
+try:
+    clip_model, clip_preprocess = clip.load(CLIP_MODEL_NAME, device=DEVICE)
+    print(f"CLIP model ({CLIP_MODEL_NAME}) loaded successfully.")
+except Exception as e:
+    print(f"Error loading CLIP model: {e}")
+    # Handle error
+try:
+    yolo_person_model = YOLO(YOLO_PERSON_MODEL_PATH).to(DEVICE)
+    print(f"YOLO person detection model ({YOLO_PERSON_MODEL_PATH}) loaded successfully.")
+except Exception as e:
+    print(f"Error loading YOLO person model: {e}")
+    # Handle error
+
+# REMOVED Fashion Model Loading
+
+# --- Prompts and Responses ---
+style_prompts = {
+    'drippy': [
+        "avant-garde streetwear", "high-fashion designer outfit", "trendsetting urban attire",
+        "luxury sneakers and chic accessories", "cutting-edge, bold style"
+    ],
+    'mid': [
+        "casual everyday outfit", "modern minimalistic attire", "comfortable yet stylish look",
+        "simple, relaxed streetwear", "balanced, practical fashion"
+    ],
+    'not_drippy': [
+        "disheveled outfit", "poorly coordinated fashion", "unfashionable, outdated attire",
+        "tacky, mismatched ensemble", "sloppy, uninspired look"
+    ]
+}
+
+# --- REINSTATED: Clothing prompts for CLIP ---
+clothing_prompts = [
+    "t-shirt", "dress shirt", "blouse", "hoodie", "jacket", "sweater", "coat",
+    "dress", "skirt", "pants", "jeans", "trousers", "shorts",
+    "sneakers", "boots", "heels", "sandals",
+    "cap", "hat", "scarf", "gloves", "bag", "accessory", "tank-top", "haircut"
+]
+
+# --- REINSTATED: Combine all prompts for CLIP ---
+all_prompts = []
+for cat_prompts in style_prompts.values():
+    all_prompts.extend(cat_prompts)
+
+# Record end of style prompts before adding clothing prompts
+style_prompts_end_index = len(all_prompts)
+all_prompts.extend(clothing_prompts)
+print(f"Total prompts for CLIP: {len(all_prompts)}")
+
+response_templates = {
+    'drippy': [
+        "You're Drippy, bruh – fire {item}!", "{item} goes crazy, on god!", "Certified drippy with that {item}."
+    ],
+    'mid': [
+        "Drop the {item} and you might get a text back.", "It's alright, but I'd upgrade the {item}.",
+        "Mid fit alert. That {item} is holding you back."
+    ],
+    'not_drippy': [
+        "Bro thought that {item} was tuff!", "Oh hell nah! Burn that {item}!",
+        "Crimes against fashion, especially that {item}! Also… maybe get a haircut.",
+        "Never walk out the house again with that {item}."
+    ]
+}
+CATEGORY_LABEL_MAP = { "drippy": "drippy", "mid": "mid", "not_drippy": "trash" }
+
+# --- REINSTATED: Function to get top clothing items based on CLIP probabilities ---
+def get_top_clothing(probs, n=3):
+    """Gets the top N clothing items based on CLIP probabilities."""
+    clothing_probs_start_index = style_prompts_end_index
+    clothing_probs = probs[clothing_probs_start_index:]
+    actual_n = min(n, len(clothing_prompts))
+    if actual_n <= 0:
+        return ["item"]
+    top_indices_in_slice = np.argsort(clothing_probs)[-actual_n:]
+    return [clothing_prompts[i] for i in reversed(top_indices_in_slice)]
+
+# --- Core Logic ---
+def analyze_outfit(input_img: Image.Image):
+    if input_img is None:
+        return ("<p style='color: #FF5555; text-align: center;'>Please upload an image.</p>",
+                None, "Error: No image provided.")
+
+    img = input_img.copy()
+    # 1) YOLO Person Detection
+    person_results = yolo_person_model(img, verbose=False)
+    boxes = person_results[0].boxes.xyxy.cpu().numpy()
+    classes = person_results[0].boxes.cls.cpu().numpy()
+    confidences = person_results[0].boxes.conf.cpu().numpy()
+    person_indices = np.where(classes == 0)[0]
+    cropped_img = img
+    if len(person_indices) > 0:
+        max_conf_person_idx = person_indices[np.argmax(confidences[person_indices])]
+        x1, y1, x2, y2 = map(int, boxes[max_conf_person_idx])
+        x1, y1 = max(0, x1), max(0, y1)
+        x2, y2 = min(img.width, x2), min(img.height, y2)
+        if x1 < x2 and y1 < y2:
+             cropped_img = img.crop((x1, y1, x2, y2))
+             print(f"Person detected and cropped: Box {x1, y1, x2, y2}")
+        else:
+            print("Warning: Invalid person bounding box after clipping. Using full image.")
+            cropped_img = img
+    else:
+        print("No person detected by yolo_person_model. Analyzing full image.")
+
+    # 2) CLIP Analysis
+    detected_clothing_item = "look"
+    try:
+        image_tensor = clip_preprocess(cropped_img).unsqueeze(0).to(DEVICE)
+        text_tokens = clip.tokenize(all_prompts).to(DEVICE)
+
+        with torch.no_grad():
+            logits, _ = clip_model(image_tensor, text_tokens)
+            all_probs = logits.softmax(dim=-1).cpu().numpy()[0]
+
+        drip_len = len(style_prompts['drippy'])
+        mid_len = len(style_prompts['mid'])
+        drip_score = np.mean(all_probs[0 : drip_len])
+        mid_score = np.mean(all_probs[drip_len : drip_len + mid_len])
+        not_score = np.mean(all_probs[drip_len + mid_len : style_prompts_end_index])
+
+        if drip_score > mid_score and drip_score > not_score:
+            category_key = 'drippy'
+            final_score = drip_score
+        elif mid_score > not_score:
+            category_key = 'mid'
+            final_score = mid_score
+        else:
+            category_key = 'not_drippy'
+            final_score = not_score
+
+        category_label = CATEGORY_LABEL_MAP[category_key]
+        final_score_str = f"{final_score:.2f}"
+        print(f"Style analysis: Category={category_label}, Score={final_score_str}")
+
+        clothing_items_detected_by_clip = get_top_clothing(all_probs, n=1)
+        if clothing_items_detected_by_clip:
+             detected_clothing_item = clothing_items_detected_by_clip[0]
+             print(f"Top clothing item identified by CLIP: {detected_clothing_item}")
+        else:
+             print("Warning: CLIP did not identify a top clothing item.")
+             detected_clothing_item = "fit"
+
+    except Exception as e:
+        print(f"Error during CLIP analysis or clothing selection: {e}")
+        return ("<p style='color: #FF5555;'>Error during analysis.</p>",
+                None, f"Analysis Error: {e}")
+
+    # 3) Generate Response and TTS
+    try:
+        response_text = random.choice(response_templates[category_key]).format(item=detected_clothing_item)
+        tts_path = os.path.join(tempfile.gettempdir(), f"drip_{uuid.uuid4().hex}.mp3")
+        tts = gTTS(text=response_text, lang='en', tld='com', slow=False)
+        tts.save(tts_path)
+        print(f"Generated TTS response: '{response_text}' saved to {tts_path}")
+
+        # --- Updated HTML Output ---
+        # Simpler structure, relies more on CSS for styling defined below
+        category_html = f"""
+            <div class='results-container'>
+                <h2 class='result-category'>RATING: {category_label.upper()}</h2>
+                <p class='result-score'>Style Score: {final_score_str}</p>
+            </div>
+        """
+        return category_html, tts_path, response_text
+
+    except Exception as e:
+        print(f"Error during response/TTS generation: {e}")
+        category_html = f"""
+            <div class='results-container'>
+                <h2 class='result-category'>Result: {category_label.upper()} (Score: {final_score_str})</h2>
+                <p class='result-score' style='color: #FFAAAA;'>Error generating audio/full response.</p>
+            </div>
+        """
+        return category_html, None, f"Analysis complete ({category_label}), but error generating audio/response."
+
+
+# --- Elite Fashion / Techno CSS ---
+custom_css = """
+:root {
+    --primary-bg-color: #000000;
+    --secondary-bg-color: #1A1A1A;
+    --text-color: #FFFFFF;
+    --accent-color: #1F04FF;
+    --border-color: #333333; /* Slightly lighter than secondary bg for subtle definition */
+    --input-bg-color: #1A1A1A;
+    --button-text-color: #FFFFFF;
+    --body-text-size: 16px; /* Base text size */
+}
+/* --- Global Styles --- */
+body, .gradio-container {
+    background-color: var(--primary-bg-color) !important;
+    color: var(--text-color) !important;
+    font-family: 'Inter', -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, Oxygen, Ubuntu, Cantarell, 'Open Sans', 'Helvetica Neue', sans-serif; /* Modern font stack */
+    font-size: var(--body-text-size);
+}
+/* Hide default Gradio footer */
+footer { display: none !important; }
+/* --- Component Styling --- */
+.gr-block { /* General block container */
+    background-color: var(--secondary-bg-color) !important;
+    border: 1px solid var(--border-color) !important;
+    border-radius: 8px !important; /* Slightly rounded corners */
+    padding: 15px !important;
+    box-shadow: none !important; /* Remove default shadows */
+}
+/* Input/Output Text Areas & General inputs */
+.gr-input, .gr-output, .gr-textbox textarea, .gr-dropdown select, .gr-checkboxgroup input {
+    background-color: var(--input-bg-color) !important;
+    color: var(--text-color) !important;
+    border: 1px solid var(--border-color) !important;
+    border-radius: 5px !important;
+}
+.gr-textbox textarea::placeholder { /* Style placeholder text if needed */
+    color: #888888 !important;
+}
+/* Component Labels */
+.gr-label span, .gr-label .label-text {
+    color: var(--text-color) !important;
+    font-weight: 500 !important; /* Slightly bolder labels */
+    font-size: 0.95em !important;
+    margin-bottom: 8px !important; /* Space below label */
+}
+/* Image Input/Output */
+.gr-image {
+   background-color: var(--primary-bg-color) !important; /* Match main background */
+   border: 1px dashed var(--border-color) !important; /* Dashed border for drop zone */
+   border-radius: 8px !important;
+   overflow: hidden; /* Ensure image stays within bounds */
+}
+.gr-image img {
+    border-radius: 6px !important; /* Slightly round image corners */
+    object-fit: contain; /* Ensure image fits well */
+}
+.gr-image .no-image, .gr-image .upload-button { /* Placeholder text/button inside image component */
+     color: #AAAAAA !important;
+}
+/* Audio Component */
+.gr-audio > div:first-of-type { /* Target the container around the audio player */
+    border: 1px solid var(--border-color) !important;
+    background-color: var(--secondary-bg-color) !important;
+    border-radius: 5px !important;
+    padding: 10px !important;
+}
+.gr-audio audio { /* Style the audio player itself */
+    width: 100%; /* Make player responsive */
+    filter: invert(1) hue-rotate(180deg); /* Basic dark theme for player controls */
+}
+/* --- Button Styling --- */
+.gr-button { /* General button style reset */
+    border: none !important;
+    border-radius: 5px !important;
+    transition: background-color 0.2s ease, transform 0.1s ease;
+    font-weight: 600 !important;
+}
+.gr-button-primary { /* Specific styling for the primary Analyze button */
+    background-color: var(--accent-color) !important;
+    color: var(--button-text-color) !important;
+    font-size: 1.1em !important; /* Make primary button slightly larger */
+    padding: 12px 20px !important; /* Adjust padding */
+}
+.gr-button-primary:hover {
+    background-color: #482FFF !important; /* Slightly lighter blue on hover */
+    transform: scale(1.02); /* Subtle scale effect */
+    box-shadow: 0 0 10px var(--accent-color); /* Add a glow effect */
+}
+.gr-button-primary:active {
+    transform: scale(0.98); /* Press down effect */
+}
+/* --- Typography & Content --- */
+h1, h2, h3 {
+    color: var(--text-color) !important;
+    font-weight: 600; /* Bold headings */
+    letter-spacing: 0.5px; /* Add slight letter spacing */
+}
+.prose h1 { /* Target Markdown H1 specifically if needed */
+    text-align: center;
+    margin-bottom: 25px !important;
+    font-size: 2em !important; /* Larger title */
+    text-transform: uppercase; /* Uppercase for impact */
+    letter-spacing: 1.5px;
+}
+.prose p { /* Target Markdown Paragraph */
+     color: #CCCCCC !important; /* Slightly dimmer text for descriptions */
+     font-size: 0.95em;
+     text-align: center;
+}
+/* Custom styling for the results HTML block */
+.results-container {
+    text-align: center;
+    padding: 20px;
+    border: 1px solid var(--accent-color); /* Use accent color for border */
+    border-radius: 8px;
+    background: linear-gradient(145deg, var(--secondary-bg-color), #2a2a2a); /* Subtle gradient */
+}
+.result-category {
+    color: var(--accent-color) !important; /* Use accent color for category */
+    font-size: 1.5em;
+    margin-bottom: 5px;
+    font-weight: 700;
+    text-transform: uppercase;
+}
+.result-score {
+    color: var(--text-color) !important;
+    font-size: 1.1em;
+    margin-top: 0;
+}
+/* --- Layout Adjustments --- */
+.gradio-container {
+    max-width: 850px !important; /* Slightly wider max-width */
+    margin: auto !important;
+    padding-top: 30px; /* Add some space at the top */
+}
+.gr-row {
+    gap: 25px !important; /* Increase gap between columns */
+}
+"""
+
+
+# --- Gradio Interface (Now using the custom CSS) ---
+with gr.Blocks(css=custom_css, theme=gr.themes.Base(primary_hue="neutral", secondary_hue="neutral", text_size=gr.themes.sizes.text_lg)) as demo: # Use Base theme to minimize default styles
+    # Title using Markdown (styled by CSS)
+    gr.Markdown("<h1>💧 DripAI: Rate Your Fit 💧</h1>")
+
+    with gr.Row():
+        with gr.Column(scale=1, min_width=350): # Assign min width for better responsiveness
+            input_image = gr.Image(
+                type='pil',
+                label="Upload Your Outfit", # Simpler label
+                sources=['upload', 'webcam', 'clipboard'],
+                height=450 # Slightly taller image area
+            )
+            analyze_button = gr.Button(
+                "Analyze Outfit",
+                variant="primary",
+                # size="lg" removed, controlled by CSS
+            )
+
+        with gr.Column(scale=1, min_width=350): # Assign min width
+            gr.Markdown("### ANALYSIS RESULTS") # Simple heading
+            category_html = gr.HTML(label="Rating & Score") # Label for screen readers/context
+            response_box = gr.Textbox(
+                lines=3,
+                label="Verbal Feedback", # Updated label
+                interactive=False
+            )
+            audio_output = gr.Audio(
+                autoplay=True, # Changed default to false, user can click play
+                label="Audio Feedback",
+                streaming=False
+            )
+
+    # Bind the analysis function to the button click
+    analyze_button.click(
+        fn=analyze_outfit,
+        inputs=[input_image],
+        outputs=[category_html, audio_output, response_box]
+    )
+
+    # Footer description text
+    gr.Markdown("<p>Upload, paste, or use your webcam to capture your outfit. DripAI evaluates your style.</p>")
+
+# --- Launch App ---
+if __name__ == "__main__":
+    demo.launch(debug=True)