dropout is missing from Linear function in LSTM model.
贡献者指南
技术栈
pythonpytorch
领域
machine learning
议题类型
bug
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。
2
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
PyTorch basicsLSTM knowledge
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。
80
研究方向
The issue is in fairseq/models/lstm.py at line 496. The Linear function call currently lacks a dropout argument. The fix involves adding dropout parameter from the configuration to this Linear layer. The repository has recent updates, but the bug remains. No linked PRs or comments exist. A newcomer should examine the model's init to see how dropout is defined and apply it consistently.