PyTorch 实现与追问
- 题目来源
- Devinterview 其中第 85—146 题的题目索引来自 Devinterview，答案由 AIMLInterviews 重新撰写；原文的 50 题补充部分在此收录为 62 道，含拆分追问。
Add gradient clipping.
原题Add gradient accumulation.
原题Add automatic mixed precision.
原题Save and resume a checkpoint exactly.
原题When should a learning-rate scheduler step?
原题Freeze and later unfreeze a backbone.
原题Why does validation differ between train() and eval()?
原题Prevent gradients during validation.
原题Calculate epoch loss with a smaller final batch.
原题Handle a non-finite loss.
原题
暂无题目