|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
import gradio as gr |
|
|
import torch |
|
|
from transformers import ViTForImageClassification, ViTImageProcessor |
|
|
from PIL import Image |
|
|
import numpy as np |
|
|
import os |
|
|
|
|
|
print("="*70) |
|
|
print("🎭 AI EMOTION DETECTOR - INITIALIZING") |
|
|
print("="*70) |
|
|
|
|
|
|
|
|
MODEL_ID = "koyelog/face" |
|
|
DEVICE = "cuda" if torch.cuda.is_available() else "cpu" |
|
|
|
|
|
print(f"\n📦 Model ID: {MODEL_ID}") |
|
|
print(f"🖥️ Device: {DEVICE}") |
|
|
print(f"💾 PyTorch Version: {torch.__version__}") |
|
|
|
|
|
|
|
|
print("\n⏳ Loading model from HuggingFace...") |
|
|
|
|
|
try: |
|
|
model = ViTForImageClassification.from_pretrained( |
|
|
MODEL_ID, |
|
|
cache_dir="./model_cache" |
|
|
) |
|
|
processor = ViTImageProcessor.from_pretrained( |
|
|
MODEL_ID, |
|
|
cache_dir="./model_cache" |
|
|
) |
|
|
model.to(DEVICE) |
|
|
model.eval() |
|
|
print("✅ Model loaded successfully!") |
|
|
print(f"📊 Model Parameters: {sum(p.numel() for p in model.parameters()):,}") |
|
|
|
|
|
except Exception as e: |
|
|
print(f"❌ ERROR loading model: {e}") |
|
|
raise |
|
|
|
|
|
|
|
|
EMOTIONS = { |
|
|
0: {'name': 'Angry', 'emoji': '😠', 'color': '#ff4444', 'description': 'Showing anger or frustration'}, |
|
|
1: {'name': 'Disgust', 'emoji': '🤢', 'color': '#44ff44', 'description': 'Expressing disgust or dislike'}, |
|
|
2: {'name': 'Fear', 'emoji': '😨', 'color': '#9944ff', 'description': 'Showing fear or anxiety'}, |
|
|
3: {'name': 'Happy', 'emoji': '😊', 'color': '#ffdd44', 'description': 'Expressing happiness or joy'}, |
|
|
4: {'name': 'Sad', 'emoji': '😢', 'color': '#4444ff', 'description': 'Showing sadness or sorrow'}, |
|
|
5: {'name': 'Surprise', 'emoji': '😲', 'color': '#ff44ff', 'description': 'Expressing surprise or shock'}, |
|
|
6: {'name': 'Neutral', 'emoji': '😐', 'color': '#888888', 'description': 'No strong emotion detected'} |
|
|
} |
|
|
|
|
|
print(f"\n🎭 Loaded {len(EMOTIONS)} emotion classes:") |
|
|
for idx, emo in EMOTIONS.items(): |
|
|
print(f" {idx}: {emo['emoji']} {emo['name']}") |
|
|
|
|
|
|
|
|
@torch.no_grad() |
|
|
def predict_emotion(image): |
|
|
""" |
|
|
Predict emotion from image |
|
|
Args: |
|
|
image: PIL Image or numpy array |
|
|
Returns: |
|
|
results_dict: Dictionary for Gradio Label |
|
|
html_output: Formatted HTML result |
|
|
""" |
|
|
|
|
|
if image is None: |
|
|
return None, """ |
|
|
<div style='text-align: center; padding: 40px; color: #ff4444;'> |
|
|
<h2>⚠️ No Image Provided</h2> |
|
|
<p>Please upload an image or use webcam to capture!</p> |
|
|
</div> |
|
|
""" |
|
|
|
|
|
try: |
|
|
|
|
|
if isinstance(image, np.ndarray): |
|
|
image = Image.fromarray(image) |
|
|
|
|
|
|
|
|
if image.mode != 'RGB': |
|
|
image = image.convert('RGB') |
|
|
|
|
|
original_size = image.size |
|
|
print(f"\n📸 Processing image: {original_size[0]}x{original_size[1]}") |
|
|
|
|
|
|
|
|
inputs = processor(images=image, return_tensors="pt") |
|
|
inputs = {k: v.to(DEVICE) for k, v in inputs.items()} |
|
|
|
|
|
|
|
|
outputs = model(**inputs) |
|
|
logits = outputs.logits |
|
|
probs = torch.nn.functional.softmax(logits, dim=-1)[0].cpu() |
|
|
|
|
|
|
|
|
predicted_id = torch.argmax(probs).item() |
|
|
confidence = probs[predicted_id].item() |
|
|
|
|
|
|
|
|
emotion = EMOTIONS[predicted_id] |
|
|
|
|
|
print(f"🎯 Prediction: {emotion['emoji']} {emotion['name']}") |
|
|
print(f"📊 Confidence: {confidence*100:.2f}%") |
|
|
print(f"📈 Top 3 emotions:") |
|
|
top3_indices = torch.topk(probs, 3).indices |
|
|
for idx in top3_indices: |
|
|
print(f" {EMOTIONS[idx.item()]['emoji']} {EMOTIONS[idx.item()]['name']}: {probs[idx]*100:.2f}%") |
|
|
|
|
|
|
|
|
results = { |
|
|
f"{EMOTIONS[i]['emoji']} {EMOTIONS[i]['name']}": float(probs[i]) |
|
|
for i in range(len(EMOTIONS)) |
|
|
} |
|
|
|
|
|
|
|
|
html = generate_result_html( |
|
|
emotion['name'], |
|
|
emotion['emoji'], |
|
|
emotion['color'], |
|
|
emotion['description'], |
|
|
confidence, |
|
|
probs |
|
|
) |
|
|
|
|
|
return results, html |
|
|
|
|
|
except Exception as e: |
|
|
print(f"❌ ERROR during prediction: {e}") |
|
|
import traceback |
|
|
traceback.print_exc() |
|
|
|
|
|
error_html = f""" |
|
|
<div style='text-align: center; padding: 40px; background: #ffe6e6; border-radius: 15px;'> |
|
|
<h2 style='color: #ff4444;'>❌ Prediction Error</h2> |
|
|
<p style='color: #666;'>{str(e)}</p> |
|
|
<p style='color: #999; font-size: 0.9em;'>Please try a different image</p> |
|
|
</div> |
|
|
""" |
|
|
return None, error_html |
|
|
|
|
|
|
|
|
def generate_result_html(name, emoji, color, description, confidence, probs): |
|
|
"""Generate beautiful HTML result display""" |
|
|
|
|
|
|
|
|
bars_html = "" |
|
|
for idx in sorted(range(len(EMOTIONS)), key=lambda i: probs[i], reverse=True): |
|
|
emo = EMOTIONS[idx] |
|
|
prob = probs[idx].item() |
|
|
percentage = prob * 100 |
|
|
bar_width = min(percentage, 100) |
|
|
|
|
|
bars_html += f""" |
|
|
<div style='margin: 12px 0;'> |
|
|
<div style='display: flex; justify-content: space-between; align-items: center; margin-bottom: 6px;'> |
|
|
<div style='display: flex; align-items: center; gap: 10px;'> |
|
|
<span style='font-size: 1.8em;'>{emo['emoji']}</span> |
|
|
<span style='font-weight: 600; color: #333;'>{emo['name']}</span> |
|
|
</div> |
|
|
<span style='font-weight: 700; color: {emo['color']}; font-size: 1.1em;'>{percentage:.1f}%</span> |
|
|
</div> |
|
|
<div style='width: 100%; background: #e9ecef; border-radius: 10px; height: 12px; overflow: hidden; box-shadow: inset 0 2px 4px rgba(0,0,0,0.06);'> |
|
|
<div style='width: {bar_width}%; background: linear-gradient(90deg, {emo['color']}, {emo['color']}dd); height: 100%; transition: width 0.8s cubic-bezier(0.4, 0, 0.2, 1); border-radius: 10px;'></div> |
|
|
</div> |
|
|
</div> |
|
|
""" |
|
|
|
|
|
|
|
|
html = f""" |
|
|
<div style='font-family: "Segoe UI", -apple-system, BlinkMacSystemFont, sans-serif; max-width: 100%;'> |
|
|
|
|
|
<!-- Main Result Card --> |
|
|
<div style=' |
|
|
text-align: center; |
|
|
padding: 50px 30px; |
|
|
background: linear-gradient(135deg, {color}18 0%, {color}30 100%); |
|
|
border-radius: 25px; |
|
|
box-shadow: 0 10px 40px rgba(0,0,0,0.12); |
|
|
margin-bottom: 30px; |
|
|
border: 2px solid {color}40; |
|
|
'> |
|
|
<div style=' |
|
|
font-size: 120px; |
|
|
margin: 0 0 20px 0; |
|
|
animation: bounceIn 0.8s cubic-bezier(0.68, -0.55, 0.265, 1.55); |
|
|
display: inline-block; |
|
|
'> |
|
|
{emoji} |
|
|
</div> |
|
|
|
|
|
<h1 style=' |
|
|
color: {color}; |
|
|
font-size: 3.5em; |
|
|
margin: 20px 0 10px 0; |
|
|
font-weight: 800; |
|
|
text-shadow: 2px 2px 8px rgba(0,0,0,0.1); |
|
|
letter-spacing: -1px; |
|
|
'> |
|
|
{name} |
|
|
</h1> |
|
|
|
|
|
<p style=' |
|
|
font-size: 1.3em; |
|
|
color: #555; |
|
|
margin: 15px 0; |
|
|
font-weight: 500; |
|
|
'> |
|
|
{description} |
|
|
</p> |
|
|
|
|
|
<div style=' |
|
|
display: inline-flex; |
|
|
align-items: center; |
|
|
gap: 15px; |
|
|
margin: 25px 0; |
|
|
padding: 15px 35px; |
|
|
background: white; |
|
|
border-radius: 50px; |
|
|
box-shadow: 0 4px 20px rgba(0,0,0,0.1); |
|
|
'> |
|
|
<span style='font-size: 1.2em; color: #666;'>Confidence:</span> |
|
|
<span style='font-size: 2em; font-weight: 800; color: {color};'>{confidence*100:.1f}%</span> |
|
|
</div> |
|
|
|
|
|
<!-- Animated Confidence Bar --> |
|
|
<div style=' |
|
|
width: 100%; |
|
|
max-width: 500px; |
|
|
height: 50px; |
|
|
background: #e9ecef; |
|
|
border-radius: 25px; |
|
|
overflow: hidden; |
|
|
margin: 30px auto 0; |
|
|
box-shadow: inset 0 4px 8px rgba(0,0,0,0.1); |
|
|
position: relative; |
|
|
'> |
|
|
<div style=' |
|
|
width: {confidence*100}%; |
|
|
height: 100%; |
|
|
background: linear-gradient(90deg, {color}, {color}cc); |
|
|
border-radius: 25px; |
|
|
transition: width 1.5s cubic-bezier(0.4, 0, 0.2, 1); |
|
|
display: flex; |
|
|
align-items: center; |
|
|
justify-content: center; |
|
|
box-shadow: 0 0 20px {color}80; |
|
|
'> |
|
|
<span style=' |
|
|
color: white; |
|
|
font-weight: 800; |
|
|
font-size: 1.3em; |
|
|
text-shadow: 0 2px 4px rgba(0,0,0,0.3); |
|
|
'> |
|
|
{confidence*100:.1f}% |
|
|
</span> |
|
|
</div> |
|
|
</div> |
|
|
</div> |
|
|
|
|
|
<!-- Detailed Breakdown --> |
|
|
<div style=' |
|
|
background: white; |
|
|
padding: 35px; |
|
|
border-radius: 20px; |
|
|
box-shadow: 0 8px 32px rgba(0,0,0,0.08); |
|
|
border: 1px solid #e9ecef; |
|
|
'> |
|
|
<h2 style=' |
|
|
margin: 0 0 25px 0; |
|
|
color: #333; |
|
|
font-size: 1.8em; |
|
|
font-weight: 700; |
|
|
display: flex; |
|
|
align-items: center; |
|
|
gap: 10px; |
|
|
'> |
|
|
📊 Detailed Emotion Analysis |
|
|
</h2> |
|
|
|
|
|
{bars_html} |
|
|
</div> |
|
|
|
|
|
<!-- Model Info Footer --> |
|
|
<div style=' |
|
|
margin-top: 25px; |
|
|
padding: 20px; |
|
|
background: linear-gradient(135deg, #f8f9fa, #e9ecef); |
|
|
border-radius: 15px; |
|
|
text-align: center; |
|
|
font-size: 0.9em; |
|
|
color: #666; |
|
|
'> |
|
|
<p style='margin: 5px 0;'> |
|
|
<strong>Model:</strong> koyelog/face (Vision Transformer) | |
|
|
<strong>Accuracy:</strong> 98.80% | |
|
|
<strong>Parameters:</strong> 85.8M |
|
|
</p> |
|
|
</div> |
|
|
</div> |
|
|
|
|
|
<style> |
|
|
@keyframes bounceIn {{ |
|
|
0% {{ |
|
|
opacity: 0; |
|
|
transform: scale(0.3) translateY(-50px); |
|
|
}} |
|
|
50% {{ |
|
|
opacity: 1; |
|
|
transform: scale(1.05); |
|
|
}} |
|
|
70% {{ |
|
|
transform: scale(0.9); |
|
|
}} |
|
|
100% {{ |
|
|
transform: scale(1); |
|
|
}} |
|
|
}} |
|
|
</style> |
|
|
""" |
|
|
|
|
|
return html |
|
|
|
|
|
|
|
|
print("\n🎨 Building Gradio interface...") |
|
|
|
|
|
|
|
|
custom_css = """ |
|
|
.gradio-container { |
|
|
font-family: 'Segoe UI', -apple-system, BlinkMacSystemFont, sans-serif !important; |
|
|
max-width: 1400px !important; |
|
|
} |
|
|
|
|
|
.main-header { |
|
|
text-align: center; |
|
|
background: linear-gradient(135deg, #667eea 0%, #764ba2 100%); |
|
|
color: white; |
|
|
padding: 60px 30px; |
|
|
border-radius: 25px; |
|
|
margin-bottom: 40px; |
|
|
box-shadow: 0 15px 50px rgba(102, 126, 234, 0.3); |
|
|
} |
|
|
|
|
|
.tab-nav button { |
|
|
font-size: 18px !important; |
|
|
font-weight: 600 !important; |
|
|
padding: 18px 30px !important; |
|
|
} |
|
|
|
|
|
.gr-button-primary { |
|
|
background: linear-gradient(135deg, #667eea, #764ba2) !important; |
|
|
border: none !important; |
|
|
font-size: 18px !important; |
|
|
font-weight: 600 !important; |
|
|
padding: 16px 40px !important; |
|
|
border-radius: 12px !important; |
|
|
transition: all 0.3s ease !important; |
|
|
} |
|
|
|
|
|
.gr-button-primary:hover { |
|
|
transform: translateY(-2px) !important; |
|
|
box-shadow: 0 8px 25px rgba(102, 126, 234, 0.4) !important; |
|
|
} |
|
|
|
|
|
footer { |
|
|
visibility: hidden !important; |
|
|
} |
|
|
""" |
|
|
|
|
|
|
|
|
with gr.Blocks( |
|
|
theme=gr.themes.Soft( |
|
|
primary_hue="purple", |
|
|
secondary_hue="pink", |
|
|
font=gr.themes.GoogleFont("Inter") |
|
|
), |
|
|
css=custom_css, |
|
|
title="🎭 AI Emotion Detector | koyelog", |
|
|
analytics_enabled=False |
|
|
) as demo: |
|
|
|
|
|
|
|
|
gr.HTML(""" |
|
|
<div class="main-header"> |
|
|
<h1 style='font-size: 4em; margin: 0; font-weight: 900; text-shadow: 3px 3px 6px rgba(0,0,0,0.2);'> |
|
|
🎭 AI Emotion Detector |
|
|
</h1> |
|
|
<p style='font-size: 1.5em; margin: 20px 0 10px; opacity: 0.95; font-weight: 500;'> |
|
|
Powered by Vision Transformer | 98.80% Validation Accuracy |
|
|
</p> |
|
|
<p style='font-size: 1.1em; opacity: 0.85;'> |
|
|
Model: <strong>koyelog/face</strong> | 85.8M Parameters | Real-time Detection |
|
|
</p> |
|
|
<div style='margin-top: 20px; display: flex; gap: 15px; justify-content: center; flex-wrap: wrap;'> |
|
|
<span style='background: rgba(255,255,255,0.25); padding: 10px 25px; border-radius: 25px; backdrop-filter: blur(10px);'> |
|
|
😠 Angry |
|
|
</span> |
|
|
<span style='background: rgba(255,255,255,0.25); padding: 10px 25px; border-radius: 25px; backdrop-filter: blur(10px);'> |
|
|
🤢 Disgust |
|
|
</span> |
|
|
<span style='background: rgba(255,255,255,0.25); padding: 10px 25px; border-radius: 25px; backdrop-filter: blur(10px);'> |
|
|
😨 Fear |
|
|
</span> |
|
|
<span style='background: rgba(255,255,255,0.25); padding: 10px 25px; border-radius: 25px; backdrop-filter: blur(10px);'> |
|
|
😊 Happy |
|
|
</span> |
|
|
<span style='background: rgba(255,255,255,0.25); padding: 10px 25px; border-radius: 25px; backdrop-filter: blur(10px);'> |
|
|
😢 Sad |
|
|
</span> |
|
|
<span style='background: rgba(255,255,255,0.25); padding: 10px 25px; border-radius: 25px; backdrop-filter: blur(10px);'> |
|
|
😲 Surprise |
|
|
</span> |
|
|
<span style='background: rgba(255,255,255,0.25); padding: 10px 25px; border-radius: 25px; backdrop-filter: blur(10px);'> |
|
|
😐 Neutral |
|
|
</span> |
|
|
</div> |
|
|
</div> |
|
|
""") |
|
|
|
|
|
with gr.Tabs(): |
|
|
|
|
|
|
|
|
with gr.Tab("📹 Live Webcam Detection"): |
|
|
gr.Markdown(""" |
|
|
### 🎥 Capture Your Emotion in Real-Time |
|
|
Click the camera button to capture your face and instantly detect your emotion! |
|
|
""") |
|
|
|
|
|
with gr.Row(): |
|
|
with gr.Column(scale=1): |
|
|
webcam_input = gr.Image( |
|
|
sources=["webcam"], |
|
|
type="pil", |
|
|
label="📸 Your Face", |
|
|
streaming=False, |
|
|
mirror_webcam=True |
|
|
) |
|
|
webcam_button = gr.Button( |
|
|
"🔍 Detect My Emotion", |
|
|
variant="primary", |
|
|
size="lg", |
|
|
scale=1 |
|
|
) |
|
|
|
|
|
with gr.Column(scale=1): |
|
|
webcam_html = gr.HTML(label="🎯 Emotion Result") |
|
|
webcam_label = gr.Label( |
|
|
label="📊 Emotion Probabilities", |
|
|
num_top_classes=7 |
|
|
) |
|
|
|
|
|
webcam_button.click( |
|
|
fn=predict_emotion, |
|
|
inputs=webcam_input, |
|
|
outputs=[webcam_label, webcam_html] |
|
|
) |
|
|
|
|
|
|
|
|
with gr.Tab("🖼️ Upload Image"): |
|
|
gr.Markdown(""" |
|
|
### 📤 Upload or Drag & Drop Face Image |
|
|
Supports JPG, PNG, JPEG formats. Best results with front-facing, well-lit photos! |
|
|
""") |
|
|
|
|
|
with gr.Row(): |
|
|
with gr.Column(scale=1): |
|
|
image_input = gr.Image( |
|
|
type="pil", |
|
|
label="🖼️ Upload Face Image", |
|
|
sources=["upload", "clipboard"] |
|
|
) |
|
|
image_button = gr.Button( |
|
|
"🔍 Detect Emotion", |
|
|
variant="primary", |
|
|
size="lg" |
|
|
) |
|
|
|
|
|
with gr.Column(scale=1): |
|
|
image_html = gr.HTML(label="🎯 Emotion Result") |
|
|
image_label = gr.Label( |
|
|
label="📊 Emotion Probabilities", |
|
|
num_top_classes=7 |
|
|
) |
|
|
|
|
|
image_button.click( |
|
|
fn=predict_emotion, |
|
|
inputs=image_input, |
|
|
outputs=[image_label, image_html] |
|
|
) |
|
|
|
|
|
|
|
|
gr.HTML(""" |
|
|
<div style=' |
|
|
text-align: center; |
|
|
margin-top: 60px; |
|
|
padding: 50px 30px; |
|
|
background: linear-gradient(135deg, #f5f7fa 0%, #c3cfe2 100%); |
|
|
border-radius: 25px; |
|
|
box-shadow: 0 8px 32px rgba(0,0,0,0.08); |
|
|
'> |
|
|
<h2 style='color: #333; margin-bottom: 30px; font-size: 2em;'> |
|
|
📊 Model Information |
|
|
</h2> |
|
|
|
|
|
<div style=' |
|
|
display: grid; |
|
|
grid-template-columns: repeat(auto-fit, minmax(250px, 1fr)); |
|
|
gap: 25px; |
|
|
margin: 30px 0; |
|
|
'> |
|
|
<div style='background: white; padding: 25px; border-radius: 15px; box-shadow: 0 4px 16px rgba(0,0,0,0.06);'> |
|
|
<p style='font-weight: 700; color: #667eea; font-size: 1.1em; margin-bottom: 10px;'>Model ID</p> |
|
|
<p style='font-size: 1.2em; color: #333; font-weight: 600;'>koyelog/face</p> |
|
|
</div> |
|
|
<div style='background: white; padding: 25px; border-radius: 15px; box-shadow: 0 4px 16px rgba(0,0,0,0.06);'> |
|
|
<p style='font-weight: 700; color: #667eea; font-size: 1.1em; margin-bottom: 10px;'>Architecture</p> |
|
|
<p style='font-size: 1.2em; color: #333; font-weight: 600;'>Vision Transformer (ViT)</p> |
|
|
</div> |
|
|
<div style='background: white; padding: 25px; border-radius: 15px; box-shadow: 0 4px 16px rgba(0,0,0,0.06);'> |
|
|
<p style='font-weight: 700; color: #667eea; font-size: 1.1em; margin-bottom: 10px;'>Parameters</p> |
|
|
<p style='font-size: 1.2em; color: #333; font-weight: 600;'>85.8 Million</p> |
|
|
</div> |
|
|
<div style='background: white; padding: 25px; border-radius: 15px; box-shadow: 0 4px 16px rgba(0,0,0,0.06);'> |
|
|
<p style='font-weight: 700; color: #667eea; font-size: 1.1em; margin-bottom: 10px;'>Accuracy</p> |
|
|
<p style='font-size: 1.2em; color: #333; font-weight: 600;'>Train: 99.29% | Val: 98.80%</p> |
|
|
</div> |
|
|
</div> |
|
|
|
|
|
<div style='margin: 30px 0; padding: 25px; background: white; border-radius: 15px; box-shadow: 0 4px 16px rgba(0,0,0,0.06);'> |
|
|
<p style='font-weight: 700; color: #333; font-size: 1.3em; margin-bottom: 15px;'> |
|
|
Training Details |
|
|
</p> |
|
|
<p style='color: #666; font-size: 1.05em; line-height: 1.6;'> |
|
|
<strong>Dataset:</strong> 181,230 images across 7 emotion categories<br> |
|
|
<strong>Training Epochs:</strong> 20 epochs with dual T4 GPUs<br> |
|
|
<strong>Best Epoch:</strong> Epoch 20/20 (Val Acc: 98.80%)<br> |
|
|
<strong>License:</strong> MIT License |
|
|
</p> |
|
|
</div> |
|
|
|
|
|
<p style='color: #666; font-size: 1.05em; margin-top: 30px; line-height: 1.6;'> |
|
|
⚠️ <strong>Best Results:</strong> Front-facing photos | Good lighting | Single face | Clear expressions |
|
|
</p> |
|
|
|
|
|
<p style='color: #999; font-size: 0.95em; margin-top: 30px;'> |
|
|
Created by <strong style='color: #667eea;'>Koyeliya Ghosh</strong><br> |
|
|
<a href='https://huggingface.co/koyelog/face' target='_blank' style='color: #667eea; font-weight: 600;'> |
|
|
View Model on HuggingFace → |
|
|
</a> |
|
|
</p> |
|
|
</div> |
|
|
""") |
|
|
|
|
|
|
|
|
if __name__ == "__main__": |
|
|
print("\n" + "="*70) |
|
|
print("🚀 LAUNCHING EMOTION DETECTION APP") |
|
|
print("="*70) |
|
|
print("✅ Model loaded and ready") |
|
|
print("✅ Gradio interface built") |
|
|
print("✅ Starting server...\n") |
|
|
|
|
|
demo.launch( |
|
|
server_name="0.0.0.0", |
|
|
server_port=7860, |
|
|
share=False, |
|
|
show_error=True, |
|
|
show_api=True |
|
|
) |
|
|
|
