Spaces:
Sleeping
Sleeping
File size: 4,871 Bytes
d14d520 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 |
#!/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)
|