损失:执行回归时，Keras中的NaN [英] Loss: NaN in Keras while performing regression

问题描述

我正在尝试预测连续值(首次使用神经网络).我已经规范化了输入数据.我不知道为什么从第一个纪元开始就得到了loss: nan输出.

I am trying to predict a continuous value (using a Neural Network for the first time). I have normalized the input data. I can't figure out why I am getting a loss: nan output starting with the first epoch.

我阅读并尝试了以前对同一问题的回答中的许多建议，但没有一个对我有帮助.我的训练数据形状为:(201917, 64).

I read and tried many suggestions from previous answers to the same question but that none of them helped me. My training data shape is: (201917, 64).

这是我的代码:

model = Sequential()
model.add(Dense(100, input_dim=X.shape[1], activation='relu'))
model.add(Dense(100, activation='relu'))
model.add(Dense(100, activation='relu'))

# Output layer
model.add(Dense(1, activation='linear'))

# Construct the neural network inside of TensorFlow
model.compile(loss='mean_squared_error', optimizer='Adam')

# train the model
model.fit(X_train, y_train, epochs=10, batch_size=32,
shuffle=True, verbose=2)

推荐答案

简而言之，您可以按照以下步骤查找问题的原因:

In short, these are the steps that you can take to find the cause of your problem:

1. 确保您的数据集应该是应该的:

1. Make sure that your dataset is what it should be:

• 在数据集中查找任何 nan / inf 并对其进行修复.
• 编码错误(将其转换为 UTF-8 ).
• 列或行中的值无效.

• Look for any nan/inf in your dataset and fix it.
• Incorrect encoding (convert it to UTF-8).
• Invalid values in your column or rows.

使用 Dropout ， BatchNormalization ， L1 / L2 正则化，更改您的 batch_size ，或将数据缩放到其他范围(例如 [-1，1] ).

Normalize your model using Dropout, BatchNormalization, L1/L2 regularization, change your batch_size, or scale your data to other ranges (e.g. [-1, 1]).

您可以检查此和

You can check this and this link to get extra help.

这篇关于损失:执行回归时，Keras中的NaN的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！