Upload files to ''

docker with FAISS

.dockerignore

@@ -0,0 +1,34 @@
+# Python
+__pycache__
+*.pyc
+*.pyo
+*.pyd
+.Python
+env/
+venv/
+.env
+*.log
+
+# Docker
+Dockerfile
+docker-compose.yml
+.dockerignore
+
+# Git
+.git
+.gitignore
+
+# IDE
+.vscode/
+.idea/
+
+# Face data (will be mounted as volume)
+*.pkl
+*.faiss
+data/
+
+# Others
+README.md
+*.md
+tests/
+.pytest_cache/

Dockerfile

@@ -0,0 +1,34 @@
+# Use Python 3.11 slim as base image
+FROM python:3.11-slim
+
+# Set working directory
+WORKDIR /app
+
+# Install system dependencies
+RUN apt-get update && apt-get install -y \
+    build-essential \
+    cmake \
+    libgl1-mesa-glx \
+    libglib2.0-0 \
+    libsm6 \
+    libxext6 \
+    libxrender-dev \
+    && rm -rf /var/lib/apt/lists/*
+
+# Copy requirements first for better caching
+COPY requirements.txt .
+
+# Install Python dependencies
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Copy application code
+COPY . .
+
+# Create directory for face data persistence
+RUN mkdir -p /app/data
+
+# Expose port
+EXPOSE 8000
+
+# Command to run the application
+CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "8000"]

docker-compose.yml

@@ -0,0 +1,34 @@
+version: '3.8'
+
+services:
+  face-recognition-api:
+    build: .
+    container_name: face-recognition-api
+    ports:
+      - "8000:8000"
+    volumes:
+      - ./data:/app/data  # For persisting face data
+    environment:
+      - PYTHONUNBUFFERED=1
+      - MAX_WORKERS=4
+      - FACE_DETECTION_SIZE=640
+      - SIMILARITY_THRESHOLD=0.6
+    deploy:
+      resources:
+        limits:
+          cpus: '2'
+          memory: 4G
+        reservations:
+          cpus: '1'
+          memory: 2G
+    restart: unless-stopped
+    healthcheck:
+      test: ["CMD", "curl", "-f", "http://localhost:8000/"]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+      start_period: 40s
+
+networks:
+  default:
+    driver: bridge

faissChecking.py

@@ -0,0 +1,32 @@
+
+
+# import faiss
+
+# # Load the FAISS index
+# index = faiss.read_index("face_index.faiss")
+
+# # Print information about the index
+# print(f"Number of vectors in the index: {index.ntotal}")
+# print(index)
+
+import faiss
+import numpy as np
+
+# Load the FAISS index
+index = faiss.read_index("face_index.faiss")
+
+# Check the total number of vectors in the index
+total_vectors = index.ntotal
+print(f"Number of vectors in the index: {total_vectors}")
+
+# Reconstruct vectors one by one
+vectors = []
+for i in range(total_vectors):
+    vectors.append(index.reconstruct(i))
+
+# Convert the list of vectors to a NumPy array
+vectors_array = np.array(vectors)
+
+# Save the array to a text file for inspection
+np.savetxt("faiss_vectors.txt", vectors_array, fmt="%.6f")
+print("Vectors saved to faiss_vectors.txt")

pickleChecking.py

@@ -0,0 +1,70 @@
+# import pickle
+
+# # Load the pickle file
+# with open("face_store.pkl", "rb") as f:
+#     data = pickle.load(f)
+
+# # Print the data for inspection
+# print(data)
+
+
+# import json
+# import numpy as np
+
+# def convert_ndarray(obj):
+#     """Recursively convert numpy.ndarray to list in a data structure."""
+#     if isinstance(obj, np.ndarray):
+#         return obj.tolist()
+#     elif isinstance(obj, list):
+#         return [convert_ndarray(item) for item in obj]
+#     elif isinstance(obj, dict):
+#         return {key: convert_ndarray(value) for key, value in obj.items()}
+#     else:
+#         return obj
+
+# # Assuming `data` contains numpy arrays
+# # data = {
+# #     "name": "example",
+# #     "embedding": np.array([1.0, 2.0, 3.0]),
+# #     "nested": {
+# #         "another_array": np.array([4.0, 5.0])
+# #     }
+# # }
+
+# # Convert `data` to JSON-serializable format
+# data_serializable = convert_ndarray(data)
+
+# # Save as JSON
+# with open("data.json", "w") as json_file:
+#     json.dump(data_serializable, json_file, indent=4)
+
+# print("JSON file saved successfully!")
+
+
+import pickle
+import json
+import numpy as np
+
+# Function to convert non-serializable objects (like numpy arrays) to a serializable format
+def convert_to_serializable(data):
+    if isinstance(data, np.ndarray):
+        return data.tolist()  # Convert ndarray to list
+    elif isinstance(data, dict):  # If data is a dictionary, recursively convert values
+        return {key: convert_to_serializable(value) for key, value in data.items()}
+    elif isinstance(data, list):  # If data is a list, recursively convert items
+        return [convert_to_serializable(item) for item in data]
+    else:
+        return data  # For other types, return as is
+
+# Load the pickle file
+with open("face_store.pkl", "rb") as f:
+    data = pickle.load(f)
+
+# Convert the data to a JSON-serializable format
+data_serializable = convert_to_serializable(data)
+
+# Save to a JSON file
+with open("face_store.json", "w") as json_file:
+    json.dump(data_serializable, json_file, indent=4)
+
+print("Data has been saved to face_store.json")