Complete System Setup for GPU Accelerated AI Projects | CUDA 12.5 + cuDNN + RTX 3050
In this video, I explain my full system configuration and step-by-step setup for running GPU accelerated AI projects in Python using InsightFace, ONNXRuntime-GPU, and OpenCV. This guide covers hardware specs, software versions, download links, and environment variables so you can replicate the same setup on your own machine.
💻 System Specifications:
GPU: NVIDIA GeForce RTX 3050 (Driver 555.99, CUDA 12.5)
CPU: AMD Ryzen 7 5800H (3.20 GHz)
RAM: 8 GB
OS: Windows 11 Home Single Language (Version 25H2)
Python: 3.12
Libraries: onnx 1.20.0, onnxruntime-gpu 1.23.2, OpenCV, InsightFace
⚙️ Software & Downloads:
CUDA Toolkit 12.5: https://developer.nvidia.com/cuda-too...
cuDNN for CUDA 12.x: https://developer.nvidia.com/rdp/cudn...
🔧 Environment Variables (Windows):
Add to PATH:
C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.5\bin
C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.5\libnvvp
C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.5\extras\CUPTI\lib64
✨ Key Highlights:
How to install CUDA Toolkit and cuDNN correctly
Copying cuDNN files into CUDA bin, lib, and include folders
Setting environment variables for Windows 11
Verifying GPU execution with ONNXRuntime (`CUDAExecutionProvider`)
Running Python AI projects with GPU acceleration
This video is perfect for anyone setting up their Windows machine for AI, machine learning, or computer vision projects with GPU acceleration.
#SystemConfiguration #CUDA #cuDNN #RTX3050 #Python #ONNXRuntime #AIProjects