Update app.py

app.py

@@ -1,85 +1 @@
-import os
-import zipfile
-from pathlib import Path
-from io import BytesIO
-
-import torch
-import uvicorn
-from fastapi import FastAPI, UploadFile, File
-from fastapi.responses import JSONResponse
-from transformers import AutoConfig, AutoModelForImageClassification, AutoImageProcessor
-from PIL import Image
-
-# ================== Config ==================
-MODEL_ZIP = "cattle_model.zip"
-MODEL_DIR = Path(__file__).parent / "cattle_model"
-
-# ================== Unzip if needed ==================
-if not MODEL_DIR.exists():
-    print(f"📦 Extracting {MODEL_ZIP}...")
-    with zipfile.ZipFile(MODEL_ZIP, 'r') as zip_ref:
-        zip_ref.extractall(MODEL_DIR.parent)
-    print("✅ Extraction complete")
-else:
-    print("📂 Model folder already exists, skipping extraction")
-
-# ================== Load Model ==================
-print("📦 Loading model...")
-
-# Load config first to avoid HF hub errors
-config = AutoConfig.from_pretrained(str(MODEL_DIR), local_files_only=True)
-
-# Load model with local config
-model = AutoModelForImageClassification.from_pretrained(
-    str(MODEL_DIR),
-    config=config,
-    local_files_only=True
-)
-
-# Load image processor
-processor = AutoImageProcessor.from_pretrained(
-    str(MODEL_DIR),
-    local_files_only=True
-)
-
-model.eval()
-print("✅ Model loaded successfully")
-
-# ================== FastAPI App ==================
-app = FastAPI(title="Cattle/Buffalo Classifier API")
-
-@app.get("/")
-def home():
-    return {"message": "🚀 Cattle/Buffalo Model API is running!"}
-
-@app.get("/labels")
-def get_labels():
-    """Return all possible class labels."""
-    return {"labels": list(model.config.id2label.values())}
-
-@app.post("/predict")
-async def predict(file: UploadFile = File(...)):
-    try:
-        # Read uploaded image
-        image = Image.open(BytesIO(await file.read())).convert("RGB")
-
-        # Preprocess
-        inputs = processor(images=image, return_tensors="pt")
-
-        # Forward pass
-        with torch.no_grad():
-            outputs = model(**inputs)
-            logits = outputs.logits
-            predicted_class_idx = logits.argmax(-1).item()
-
-        # Map to label
-        label = model.config.id2label[predicted_class_idx]
-
-        return JSONResponse(content={"prediction": label})
-
-    except Exception as e:
-        return JSONResponse(content={"error": str(e)}, status_code=500)
-
-# ================== Run Locally ==================
-if __name__ == "__main__":
-    uvicorn.run(app, host="0.0.0.0", port=7860)
+ls /home/user/app/cattle_model