ESPCN use 3 conv layers, but I found you use 4 conv layer. can you tell me why, it has better psnr result?
贡献者指南
技术栈
python
领域
machine learning
议题类型
research
难度面向新贡献者的预计实现难度,1 表示很小改动,5 表示专家级工作。
3
预计时间有经验贡献者完成调查、实现、测试并准备 pull request 的粗略时间范围。
under 1 hour
活动状态议题当前的可参与程度:新鲜、活跃、陈旧、阻塞或等待维护者输入。
stale
清晰度议题是否清楚说明期望改动、验收标准和下一步。
clear
前置要求
无
新手友好度1-100 的估计分数,表示该议题对首次贡献者的友好程度。
70
研究方向
Review the super resolution example in the pytorch/examples repository, specifically the ESPCN implementation with 4 conv layers. Compare with the original ESPCN paper which uses 3 layers. Check if the 4 layer variant has been discussed in the issue comments or linked resources. Provide explanation based on evidence.
Super resolution · pytorch/examples#217 | Good First Issue