40%

Complete your profile to find better job opportunities

CNN-vs-Vision-Transformer-Benchmark
GitHubRepository

CNN-vs-Vision-Transformer-Benchmark

A performance comparison of CNN and Vision Transformer architectures on CIFAR-10 image classification.

  • 1 stars
  • 0 forks
  • HTML language
View on GitHub
Published
8 Oct 2025
Updated
17 Oct 2025
AI summary

This repository benchmarks CNN and Vision Transformer architectures on CIFAR-10, comparing performance metrics like accuracy, speed, memory usage, and throughput. It uses PyTorch DDP with NCCL backend for distributed multi-GPU training on Kaggle Notebooks.

From the README

CNN vs Vision Transformer Benchmark This project implements both CNN and Vision Transformer (ViT) models from scratch and benchmarks their performance across multiple metrics: accuracy, training speed, memory usage, and throughput. ๐Ÿ“Œ Implemented on: Kaggle Notebook with 2x GPU execution ๐Ÿš€ Distributed Training Results: 11.7x ViT Speedup via NCCL Backend Optimization Implemented distributed multi-GPU benchmark using PyTorch DDP (torch.distributed) with NCCL backend, achieving 1.87x wall-clock speedup and 87% parallel efficiency by training CNN and ViT models concurrently on separate GPUs ๐Ÿš€ DDP Multi-GPU Performance Results Benchmark Configuration โ€ข Hardware: 2x Tesla T4 GPUs...

Skills

  • HTML
  • Python

More work by Laharsh Moturi