trigger_gpu_training.py

#!/usr/bin/env python3
"""
Trigger GPU training through Gradio interface
Uses HTTP POST to call the Gradio API endpoint
"""
import requests
import json
import time
from datetime import datetime

print("="*70)
print("🚀 IPAD VAD GPU Training Trigger via Gradio API")
print("="*70)
print(f"Time: {datetime.now().strftime('%Y-%m-%d %H:%M:%S')}")
print()

# Gradio API endpoint (local)
GRADIO_URL = "http://localhost:7860"

# Check if Gradio is running
print("[Step 1] Checking Gradio interface...")
try:
    response = requests.get(GRADIO_URL, timeout=5)
    if response.status_code == 200:
        print(f"✅ Gradio interface is running at {GRADIO_URL}")
    else:
        print(f"⚠️  Gradio returned status {response.status_code}")
except Exception as e:
    print(f"❌ Cannot connect to Gradio: {e}")
    print("   Make sure app.py is running")
    exit(1)

print()

# Get API info
print("[Step 2] Getting API endpoints...")
try:
    api_response = requests.get(f"{GRADIO_URL}/info", timeout=10)
    if api_response.status_code == 200:
        api_info = api_response.json()
        print(f"✅ API info retrieved")
        print(f"   Named endpoints: {len(api_info.get('named_endpoints', {}))}")
    else:
        print(f"⚠️  Could not get API info: {api_response.status_code}")
except Exception as e:
    print(f"⚠️  Could not get API info: {e}")

print()

# Method 1: Try gradio_client (if available)
print("[Step 3] Attempting to trigger training via gradio_client...")
try:
    from gradio_client import Client

    client = Client(GRADIO_URL)
    print(f"✅ Connected to Gradio client")
    print()

    # Configuration
    device_name = "S01"
    epochs = 10
    batch_size = 4
    lr = 1e-4

    print("📋 Training Configuration:")
    print(f"   Device: {device_name}")
    print(f"   Epochs: {epochs}")
    print(f"   Batch Size: {batch_size}")
    print(f"   Learning Rate: {lr}")
    print()

    print("🚀 Triggering GPU training...")
    print("   This will request ZeroGPU allocation (H200, 80GB)")
    print("   Expected time: ~10-15 minutes")
    print()

    # Call the quick training endpoint
    start_time = time.time()
    result = client.predict(
        device_name=device_name,
        epochs=epochs,
        batch_size=batch_size,
        lr=lr,
        api_name="/train_quick_baseline"
    )
    end_time = time.time()

    print()
    print("="*70)
    print(f"✅ Training request completed in {(end_time - start_time) / 60:.1f} minutes!")
    print("="*70)
    print()
    print("📊 Result:")
    print(result)
    print()

except ImportError:
    print("⚠️  gradio_client not available, trying HTTP POST...")
    print()

    # Method 2: HTTP POST (fallback)
    print("[Step 3b] Attempting to trigger training via HTTP POST...")
    try:
        endpoint = f"{GRADIO_URL}/api/predict"

        payload = {
            "fn_index": 2,  # Index of train_quick_baseline function
            "data": [
                "S01",  # device_name
                10,     # epochs
                4,      # batch_size
                0.0001  # lr
            ]
        }

        print("📋 Sending training request...")
        print(f"   Endpoint: {endpoint}")
        print(f"   Payload: {json.dumps(payload, indent=2)}")
        print()

        response = requests.post(
            endpoint,
            json=payload,
            headers={"Content-Type": "application/json"},
            timeout=3600  # 1 hour timeout
        )

        if response.status_code == 200:
            result = response.json()
            print("✅ Training completed!")
            print()
            print("📊 Result:")
            print(json.dumps(result, indent=2))
        else:
            print(f"❌ Training request failed: {response.status_code}")
            print(response.text)

    except Exception as e:
        print(f"❌ HTTP POST failed: {e}")
        import traceback
        traceback.print_exc()

print()
print("="*70)
print("💡 Alternative: Manual Trigger")
print("="*70)
print()
print("If automatic trigger doesn't work, manually trigger via web interface:")
print(f"1. Open: https://huggingface.co/spaces/MSherbinii/ipad-vad-training")
print(f"2. Go to '⚡ Quick Test (10 epochs)' tab")
print(f"3. Click '🚀 Start Quick Training'")
print(f"4. Wait ~10-15 minutes for completion")
print()
print("Or trigger via Python code:")
print("""
from gradio_client import Client

client = Client("https://huggingface.co/spaces/MSherbinii/ipad-vad-training")
result = client.predict(
    quick_device="S01",
    quick_epochs=10,
    quick_batch=4,
    quick_lr=1e-4,
    api_name="/train_quick_baseline"
)
print(result)
""")
print()
print("="*70)