对比三类GPU训练遥感分类模型，发现消费级显卡提速一倍
Practical GPU Choices for Earth Observation: ResNet-50 Training Throughput on Integrated, Laptop, and Cloud Accelerators
- 用ResNet-50处理哨兵2影像，全流程自动化并容器化
- RTX 3060和T4比M3 Pro快一倍，精度仍达EuroSAT标准
- 适合想低成本部署遥感深度学习的开发者和研究者
本项目基于ResNet构建土地利用与土地覆盖（LULC）分类流水线，针对哨兵2影像在三种异构GPU上进行基准测试。工作流实现数据获取、地理空间预处理、切片、模型训练及可视化全流程自动化，并采用容器化保证可复现性。性能评估显示，在NVIDIA RTX 3060和Tesla T4上训练速度相较Apple M3 Pro基线最高提升2倍，同时在EuroSAT数据集上保持高分类准确率。结果表明，可在消费级及免费云GPU上可行部署深度学习LULC模型，支持可扩展的地理空间分析。
原文摘要 · Abstract (English)
This project implements a ResNet-based pipeline for land use and land cover (LULC) classification on Sentinel-2 imagery, benchmarked across three heterogeneous GPUs. The workflow automates data acquisition, geospatial preprocessing, tiling, model training, and visualization, and is fully containerized for reproducibility. Performance evaluation reveals up to a 2x training speed-up on an NVIDIA RTX 3060 and a Tesla T4 compared to the Apple M3 Pro baseline, while maintaining high classification accuracy on the EuroSAT dataset. These results demonstrate the feasibility of deploying deep learning LULC models on consumer and free cloud GPUs for scalable geospatial analytics.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。