added api setup

Dockerfile

@@ -0,0 +1,20 @@
+FROM python:3.10-slim
+
+# Set up a new user named "user" with user ID 1000
+RUN useradd -m -u 1000 user
+
+# Switch to the new user
+USER user
+
+# Set environment variables
+ENV HOME=/home/user \
+    PATH=/home/user/.local/bin:$PATH
+
+WORKDIR $HOME/app
+
+COPY --chown=user requirements.txt .
+RUN pip install --no-cache-dir --upgrade -r requirements.txt
+
+COPY --chown=user . .
+
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]

app.py

@@ -0,0 +1,73 @@
+import os
+import io
+import numpy as np
+import tensorflow as tf
+from fastapi import FastAPI, File, UploadFile
+from PIL import Image
+from huggingface_hub import hf_hub_download, login
+
+# Import Mask RCNN modules
+from mrcnn.config import Config
+import mrcnn.model as modellib
+
+app = FastAPI()
+
+# CORS Configuration
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],  
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+class PredictionConfig(Config):
+    NAME = "petrol_station"
+    IMAGES_PER_GPU = 1
+    NUM_CLASSES = 1 + 1     
+    DETECTION_MIN_CONFIDENCE = 0.9
+
+# Configuration constants
+REPO_ID = "SaniaE/MRCNN_Petrol_Pump_Segmentation"
+FILENAME = "mask_rcnn_petrol station_0080.h5"
+config = PredictionConfig()
+graph = tf.get_default_graph()
+model_eval = None
+
+@app.on_event("startup")
+def load_model():
+    global model_eval
+    token = os.getenv("HF_Token")          
+    
+    if token: 
+        login(token=token)
+    else: 
+        print("No HF_Token found - attempting public download")
+
+    print(f"Downloading weights from {REPO_ID}")
+    
+    weights_path = hf_hub_download(repo_id=REPO_ID, filename=FILENAME, token=token)
+    
+    model_eval = modellib.MaskRCNN(mode="inference", model_dir=".", config=config)
+    model_eval.load_weights(weights_path, by_name=True)
+    
+    model_eval.keras_model._make_predict_function()
+    print("Model loaded successfully.")
+
+
+@app.post("/predict")
+async def predict(file: UploadFile = File(...)):
+    contents = await file.read()
+    image = Image.open(io.BytesIO(contents)).convert("RGB")
+    image_np = np.array(image)
+
+    global graph
+    with graph.as_default():
+        results = model_eval.detect([image_np], verbose=0)
+    
+    r = results[0]
+    return {
+        "rois": r['rois'].tolist(),
+        "class_ids": r['class_ids'].tolist(),
+        "scores": r['scores'].tolist(),
+        "num_detections": len(r['class_ids'])
+    }

requirements.txt

@@ -0,0 +1,15 @@
+fastapi
+uvicorn
+python-multipart
+huggingface-hub
+pandas==1.3.5
+numpy==1.24.3
+matplotlib==3.5.3
+scikit-image==0.19.3
+opencv-python-headless==4.10.0.84
+h5py==2.10.0
+keras==2.2.0
+tensorflow-gpu==1.15.0
+Keras-applications==1.0.7
+protobuf==3.20.3
+Pillow==9.5.0