在训练的时候出现了这个错误，Found Inf or NaN global norm，哪个大牛帮忙看一下怎么破？ · wb14123/seq2seq-couplet#25

(1 评论) (0 反应) (0 负责人)Python (5,477 star) (1,072 fork)batch import

help wantedquestion

描述

InvalidArgumentError (see above for traceback): Found Inf or NaN global norm. : Tensor had Inf values [[node VerifyFinite/CheckNumerics (defined at C:\Users\xxx\seq2seq-couplet-master1\model.py:79) = CheckNumericsT=DT_FLOAT, message="Found Inf or NaN global norm.", _device="/job:localhost/replica:0/task:0/device:GPU:0"]]

技术栈: python
领域: machine learning
议题类型: bug
难度: 3
预计时间: half day
活动状态: stale
清晰度: mostly clear
前置要求: basic TensorFlow knowledgeunderstanding of gradient issues
新手友好度: 30
研究方向: The issue reports 'Found Inf or NaN global norm' during training of a seq2seq couplet model. The error originates at model.py line 79 in the global norm calculation. Investigate potential causes such as unstable gradients, learning rate too high, or issues in the loss function. Consider adding gradient clipping or adjusting optimizer parameters. The only comment is from the author asking for help; no maintainer response has been provided. Check the repository's training scripts for hyperparameters and data preprocessing steps that might lead to numerical instability.