pytorch/examples

example time_sequence_prediction does not produce expected output

Open

#247 创建于 2017年10月27日

在 GitHub 查看
 (5 评论) (1 反应) (0 负责人)Python (21,634 star) (9,429 fork)batch import
good first issue

描述

https://github.com/pytorch/examples/tree/master/time_sequence_prediction

After a few steps, the loss suddenly jumps up and stays high: loss: 0.00101216329969 loss: 0.195070432582

the pdf0 is OK, pdf1 is OK but from pdf2 the graph becomes an "L "

贡献者指南

技术栈
pytorchpython
领域
machine learningai
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。
4
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。
half day
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。
mostly clear
前置要求
PythonPyTorchRNN/LSTMTime series prediction
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。
30
研究方向
Investigate the training loop in the time sequence prediction example (https://github.com/pytorch/examples/tree/master/time sequence prediction). The issue describes a sudden loss increase after a few steps and an 'L' shaped graph from pdf2 onward. Check for exploding gradients, learning rate issues, or incorrect sequence batching. Compare with well known implementations of LSTM for time series to identify potential bugs.
example time_sequence_prediction does not produce expected output · pytorch/examples#247 | Good First Issue