Swin-Transformer-Object-Detection环境搭建训练流程及问题

一、背景

Swin-Transformer（Swin代表移位窗口shifted window）可以作为计算机视觉的通用backbone。它的github网址是Swin-Transformer，然后它有好几种应用：

Getting Started
For Image Classification, please see get_started.md for detailed instructions.
For Object Detection and Instance Segmentation, please see *Swin Transformer for Object Detection*.
For Semantic Segmentation, please see Swin Transformer for Semantic Segmentation.
For Self-Supervised Learning, please see Transformer-SSL.
For Video Recognition, please see Video Swin Transformer.

因为这里我们主要是图像实例分割，所以用第二个Swin-Transformer-Object-Detection模型，进入网址Swin-Transformer-Object-Detection

二、流程

1.搭建环境

此次安装版本

Python 3.7
pytorch       1.10.2       py3.7_cuda11.3_cudnn8.2.0_0    pytorch

这个也是基于mm