Upload 6 files

DEPLOYMENT_STEPS.txt

@@ -0,0 +1,169 @@
+================================================================================
+HUGGING FACE SPACES DEPLOYMENT - ADIM ADIM
+================================================================================
+
+📁 HAZIR DOSYALAR:
+   ✓ Dockerfile
+   ✓ app.py
+   ✓ requirements.txt
+   ✓ README.md
+   ✓ test_deployed_api.py
+
+================================================================================
+ADIMLAR:
+================================================================================
+
+1️⃣  HUGGING FACE'E GİT
+   URL: https://huggingface.co/new-space
+   
+   Hesabın yoksa önce kayıt ol:
+   https://huggingface.co/join
+
+--------------------------------------------------------------------------------
+
+2️⃣  YENİ SPACE OLUŞTUR
+   
+   ⚙️ AYARLAR:
+   
+   Space name: dog-breed-api
+              (veya istediğin isim)
+   
+   Space SDK: 🐳 Docker  ⚠️ ÇOK ÖNEMLİ!
+             (Gradio veya Streamlit DEĞİL - sadece Docker!)
+   
+   Space hardware: CPU basic - Free
+   
+   Visibility: Public
+   
+   ➤ "Create Space" tıkla
+
+--------------------------------------------------------------------------------
+
+3️⃣  DOSYALARI YÜKLE
+   
+   Space açıldıktan sonra:
+   
+   a) Üstteki "+ Add file" → "Upload files" tıkla
+      
+   b) Şu SIRAYA GÖRE dosyaları yükle:
+      
+      1. Dockerfile
+      2. requirements.txt  
+      3. app.py
+      4. README.md (opsiyonel)
+      
+   c) Her dosyadan sonra "Commit changes to main" tıkla
+
+--------------------------------------------------------------------------------
+
+4️⃣  BUILD İZLE
+   
+   Dosyalar yüklendikten sonra:
+   
+   - "App" sekmesine geç
+   - "Building..." yazısını göreceksin
+   - Logs açılacak
+   
+   ⏱️ Bekleme: 5-10 dakika
+   
+   Loglar:
+   ┌─────────────────────────────────────┐
+   │ Building Docker image...            │
+   │ Installing dependencies...          │
+   │ Downloading model (200+ MB)...      │
+   │ Starting application...             │
+   │ ✓ Running on port 7860              │
+   └─────────────────────────────────────┘
+   
+   Başarılı olunca: ✓ Running
+
+--------------------------------------------------------------------------------
+
+5️⃣  TEST ET!
+   
+   Space URL'in:
+   https://KULLANICI-ADIN-dog-breed-api.hf.space
+   
+   API Endpoint:
+   https://KULLANICI-ADIN-dog-breed-api.hf.space/predict_pet
+   
+   
+   📝 Test scripti ile:
+   
+   a) test_deployed_api.py dosyasını aç
+   
+   b) İlk satırı düzenle:
+      SPACE_URL = "https://SENIN-KULLANICI-ADIN-dog-breed-api.hf.space"
+   
+   c) Çalıştır:
+      python test_deployed_api.py
+   
+   
+   🌐 Browser'da test:
+   
+   a) https://KULLANICI-ADIN-dog-breed-api.hf.space/ aç
+      → Sağlık kontrolü göreceksin (JSON)
+   
+   b) Postman/Insomnia kullan:
+      - URL: .../predict_pet
+      - Method: POST
+      - Body: form-data
+      - Key: image (file type)
+      - Value: Bir köpek fotoğrafı seç
+
+================================================================================
+BAŞARILI OLDUKTAN SONRA:
+================================================================================
+
+✅ API'n hazır!
+
+📡 Endpoint:
+   https://KULLANICI-ADIN-dog-breed-api.hf.space/predict_pet
+
+📊 Kullanım örnekleri:
+   - README.md dosyasına bak
+   - Python, JavaScript, cURL örnekleri var
+
+⚡ Performans:
+   - İlk istek: 10-15s (model yükleme)
+   - Sonraki: 2-4s (hızlı!)
+
+💰 Maliyet:
+   - TAMAMEN ÜCRETSİZ! (Public Space)
+
+================================================================================
+SORUN GİDERME
+================================================================================
+
+❌ "Building failed"
+   → Logs'a bak, hata mesajını gör
+   → Dockerfile'ı kontrol et
+   → requirements.txt'yi kontrol et
+
+❌ "503 Service Unavailable"
+   → Space henüz başlamadı, 1-2 dakika bekle
+
+❌ "Out of memory"
+   → Model çok büyük, ücretli tier gerek
+   → Ya da daha küçük model kullan
+
+❌ Fotoğraf yüklenmiyor
+   → Dosya boyutu max 10MB olmalı
+   → Format: JPEG, PNG, WebP
+
+================================================================================
+İPUCU: Space'i aktif tut
+================================================================================
+
+Hugging Face Spaces'te free tier'da Space'ler inaktifse uyku moduna girer.
+
+İlk istekte tekrar uyanır (10-15 saniye sürer).
+
+Sürekli aktif tutmak için:
+- Her gün 1 istek at
+- Ya da ücretli tier'a geç (always-on)
+
+================================================================================
+BAŞARILAR! 🚀
+================================================================================
+

Dockerfile

@@ -0,0 +1,21 @@
+FROM python:3.11-slim
+
+WORKDIR /app
+
+# Install dependencies
+COPY requirements_deployment.txt requirements.txt
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Copy app
+COPY app_deployment.py app.py
+
+# Expose port
+EXPOSE 7860
+
+# Set environment
+ENV PORT=7860
+ENV PYTHONUNBUFFERED=1
+
+# Run app
+CMD ["python", "app.py"]
+

README.md

@@ -1,11 +1,95 @@
----
-title: Petbackend
-emoji: 🦀
-colorFrom: red
-colorTo: yellow
-sdk: docker
-pinned: false
-license: apache-2.0
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# 🐕 Dog Breed Classification API
+
+ConvNextV2-large-DogBreed model ile köpek ırkı tahmini yapan API.
+
+## 🚀 Kullanım
+
+### Endpoint
+
+```
+POST /predict_pet
+```
+
+### Request
+
+**Content-Type:** `multipart/form-data`
+
+**Body:**
+- `image` (file): Köpek fotoğrafı (JPEG, PNG, WebP)
+
+### Response
+
+```json
+{
+  "breed": "Doberman_pinscher",
+  "confidence": 0.533,
+  "top_5": [
+    {"breed": "Doberman_pinscher", "confidence": 0.533},
+    {"breed": "Beauceron", "confidence": 0.065},
+    {"breed": "German_pinscher", "confidence": 0.041},
+    {"breed": "Black_and_tan_coonhound", "confidence": 0.023},
+    {"breed": "Greater_swiss_mountain_dog", "confidence": 0.011}
+  ],
+  "model": "ConvNextV2-large-DogBreed",
+  "accuracy": "91.39%"
+}
+```
+
+## 📝 Örnekler
+
+### Python
+
+```python
+import requests
+
+url = "https://YOUR-SPACE-URL.hf.space/predict_pet"
+
+with open("dog.jpg", "rb") as f:
+    files = {"image": f}
+    response = requests.post(url, files=files)
+    
+result = response.json()
+print(f"Breed: {result['breed']}")
+print(f"Confidence: {result['confidence']:.2%}")
+```
+
+### cURL
+
+```bash
+curl -X POST https://YOUR-SPACE-URL.hf.space/predict_pet \
+  -F "image=@dog.jpg"
+```
+
+### JavaScript (Fetch)
+
+```javascript
+const formData = new FormData();
+formData.append('image', fileInput.files[0]);
+
+const response = await fetch('https://YOUR-SPACE-URL.hf.space/predict_pet', {
+  method: 'POST',
+  body: formData
+});
+
+const result = await response.json();
+console.log(result.breed, result.confidence);
+```
+
+## ℹ️ Model Bilgisi
+
+- **Model:** [Pavarissy/ConvNextV2-large-DogBreed](https://huggingface.co/Pavarissy/ConvNextV2-large-DogBreed)
+- **Accuracy:** 91.39% (validation set)
+- **Architecture:** ConvNextV2-large-22k-224
+- **Training:** 50 epochs, Stanford Dogs Dataset
+- **Classes:** 120 dog breeds
+
+## 🔧 Performans
+
+- **İlk istek:** 10-15 saniye (model yükleme)
+- **Sonraki istekler:** 2-4 saniye
+- **Hardware:** CPU basic (HF Spaces free tier)
+
+## 📄 License
+
+MIT
+

app.py

@@ -0,0 +1,129 @@
+"""
+Production-ready Flask backend for deployment
+Optimized for Hugging Face Spaces / Railway / Render
+"""
+
+from flask import Flask, request, jsonify
+import io
+from PIL import Image
+from flask_cors import CORS
+import logging
+import os
+
+app = Flask(__name__)
+CORS(app, resources={r"/predict_pet": {"origins": "*"}})
+
+# Logging configuration
+logging.basicConfig(
+    level=logging.INFO,
+    format='%(asctime)s - %(name)s - %(levelname)s - %(message)s'
+)
+logger = logging.getLogger(__name__)
+
+# Model global variables
+model = None
+image_processor = None
+
+def load_model():
+    """Load model on first request"""
+    global model, image_processor
+    
+    if model is not None:
+        return
+    
+    try:
+        import torch
+        from transformers import AutoImageProcessor, AutoModelForImageClassification
+        
+        logger.info("Loading ConvNextV2-large-DogBreed model...")
+        
+        model_name = "Pavarissy/ConvNextV2-large-DogBreed"
+        
+        # Detect device
+        device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+        logger.info(f"Using device: {device}")
+        
+        # Load model
+        image_processor = AutoImageProcessor.from_pretrained(model_name)
+        model = AutoModelForImageClassification.from_pretrained(model_name)
+        model = model.to(device)
+        model.eval()
+        
+        logger.info(f"✓ Model loaded successfully on {device}")
+        
+    except Exception as e:
+        logger.error(f"Failed to load model: {e}")
+        raise
+
+@app.route('/', methods=['GET'])
+def health_check():
+    """Health check endpoint"""
+    return jsonify({
+        'status': 'healthy',
+        'service': 'Dog Breed Prediction API',
+        'model': 'ConvNextV2-large-DogBreed',
+        'accuracy': '91.39%',
+        'version': '1.0.0'
+    })
+
+@app.route('/predict_pet', methods=['POST'])
+def predict_pet():
+    """Predict dog breed from uploaded image"""
+    
+    try:
+        # Load model if not loaded
+        load_model()
+        
+        # Validate request
+        if 'image' not in request.files:
+            return jsonify({'error': 'No image file provided'}), 400
+            
+        file = request.files['image']
+        
+        # Read and validate image
+        image_bytes = file.read()
+        pil_image = Image.open(io.BytesIO(image_bytes))
+        
+        if pil_image.mode != 'RGB':
+            pil_image = pil_image.convert('RGB')
+        
+        # Make prediction
+        import torch
+        inputs = image_processor(pil_image, return_tensors="pt")
+        
+        device = next(model.parameters()).device
+        inputs = {k: v.to(device) for k, v in inputs.items()}
+        
+        with torch.no_grad():
+            outputs = model(**inputs)
+            logits = outputs.logits
+            
+        probs = torch.nn.functional.softmax(logits, dim=-1)[0].cpu()
+        top_5_probs, top_5_indices = torch.topk(probs, 5)
+        
+        # Format results
+        top_5_breeds = []
+        for prob, idx in zip(top_5_probs, top_5_indices):
+            top_5_breeds.append({
+                'breed': model.config.id2label[idx.item()],
+                'confidence': float(prob.item())
+            })
+        
+        logger.info(f"Prediction: {top_5_breeds[0]['breed']} ({top_5_breeds[0]['confidence']:.2%})")
+        
+        return jsonify({
+            'breed': top_5_breeds[0]['breed'],
+            'confidence': top_5_breeds[0]['confidence'],
+            'top_5': top_5_breeds,
+            'model': 'ConvNextV2-large-DogBreed',
+            'accuracy': '91.39%'
+        })
+        
+    except Exception as e:
+        logger.error(f"Error: {str(e)}", exc_info=True)
+        return jsonify({'error': str(e)}), 500
+
+if __name__ == '__main__':
+    port = int(os.environ.get('PORT', 7860))
+    app.run(host='0.0.0.0', port=port, debug=False)
+

requirements.txt

@@ -0,0 +1,7 @@
+flask==3.0.0
+flask-cors==4.0.0
+transformers==4.35.0
+torch==2.1.0
+pillow==10.1.0
+accelerate==0.24.0
+

test_deployed_api.py

@@ -0,0 +1,82 @@
+"""
+Deployed HF Space API Test Scripti
+"""
+
+import requests
+
+# ⚠️ BURAYA KENDI SPACE URL'INI YAZ!
+# Ornek: https://alpip-dog-breed-api.hf.space
+SPACE_URL = "https://KULLANICI-ADIN-dog-breed-api.hf.space"
+
+API_ENDPOINT = f"{SPACE_URL}/predict_pet"
+
+# Test fotografi
+image_path = r"C:\Users\alpip\OneDrive - Istanbul Bilgi Universitesi\Masaüstü\WhatsApp Image 2025-10-24 at 17.57.47.jpeg"
+
+print("=" * 80)
+print("DEPLOYED API TEST")
+print("=" * 80)
+print()
+print(f"API Endpoint: {API_ENDPOINT}")
+print(f"Test Image: {image_path}")
+print()
+
+try:
+    # Health check once
+    print("1. Health check yapiliyor...")
+    response = requests.get(SPACE_URL)
+    if response.status_code == 200:
+        print("   ✓ Backend calisiyor!")
+    else:
+        print(f"   ✗ Backend cevap vermiyor: {response.status_code}")
+        exit(1)
+    
+    print()
+    print("2. Fotograf gonderiliyor...")
+    
+    # Fotografi gonder
+    with open(image_path, 'rb') as f:
+        files = {'image': ('dog.jpg', f, 'image/jpeg')}
+        response = requests.post(API_ENDPOINT, files=files)
+    
+    print(f"   HTTP Status: {response.status_code}")
+    print()
+    
+    if response.status_code == 200:
+        result = response.json()
+        
+        print("=" * 80)
+        print("BASARILI! TAHMINLER:")
+        print("=" * 80)
+        
+        for i, pred in enumerate(result['top_5'], 1):
+            breed = pred['breed']
+            confidence = pred['confidence'] * 100
+            bar = '#' * int(confidence / 2)
+            print(f"{i}. {breed:40s} {confidence:6.2f}% {bar}")
+        
+        print("=" * 80)
+        print(f"EN IYI TAHMIN: {result['breed']} ({result['confidence']*100:.2f}%)")
+        print(f"Model: {result['model']}")
+        print(f"Accuracy: {result['accuracy']}")
+        print("=" * 80)
+        print()
+        print("API HAZIR! Kullanmaya baslayabilirsin!")
+        print()
+        print("Frontend'den kullanim:")
+        print(f"  POST {API_ENDPOINT}")
+        print("  Body: form-data")
+        print("  Key: 'image' (file)")
+        
+    else:
+        print(f"HATA: {response.status_code}")
+        print(response.text)
+        
+except FileNotFoundError:
+    print(f"Fotograf bulunamadi: {image_path}")
+except requests.exceptions.ConnectionError:
+    print("Backend'e baglanilamadi!")
+    print("Space'in 'Running' durumunda oldugundan emin ol")
+except Exception as e:
+    print(f"Hata: {str(e)}")
+