My approach to Intel Scene Classification (Analytics Vidhya)
-
Updated
Oct 27, 2019 - Jupyter Notebook
My approach to Intel Scene Classification (Analytics Vidhya)
PyTorch 实现自然场景图像分类的模块化改进:BN、残差连接、SE 注意力、RandAugment 及模型集成,最终准确率 92.1%。附消融实验、训练曲线与交互式 Demo
Add a description, image, and links to the intel-scene-classification topic page so that developers can more easily learn about it.
To associate your repository with the intel-scene-classification topic, visit your repo's landing page and select "manage topics."