ValueError:检查目标时出错:预期dense_2具有3维，但得到形状为(10000, 1)的数组 [英] ValueError: Error when checking target: expected dense_2 to have 3 dimensions, but got array with shape (10000, 1)

问题描述

我正在使用 keras MLP 网络对 3-D 词向量进行二元分类 input_shape=(None,24,73).我使用了两个密集层 dense_1 和 dense_2.在 dense_2 处，我收到一个我无法解决的错误.

这是我的模型摘要.

层(类型)输出形状参数#==================================================================密集_1(密集)(无、8、90)6660_________________________________________________________________密集_2(密集)(无，8，1)91==================================================================总参数:6,751可训练参数:6,751不可训练的参数:0

<块引用>

ValueError: 检查目标时出错:预期密集_2 有 3维度，但得到了形状为 (22, 1) 的数组

解决方案

既然你有一个 binary_classification 任务，你的最后一层应该看起来像这样

model.add(Dense(1, activation='sigmoid'))

现在您的模型正在放置与形状不匹配的 3D 阵列你的目标(二维)

I am using keras MLP network for binary classification of 3-D word vector input_shape=(None,24,73). I have used two dense layers dense_1 and dense_2. At dense_2 I'm getting an error which I've not been able to solve.

This is my model summary.

Layer (type)                 Output Shape              Param #   
=================================================================
dense_1 (Dense)              (None, 8, 90)             6660      
_________________________________________________________________
dense_2 (Dense)              (None, 8, 1)              91        
=================================================================
Total params: 6,751
Trainable params: 6,751
Non-trainable params: 0

ValueError: Error when checking target: expected dense_2 to have 3 dimensions, but got array with shape (22, 1)

解决方案

Since you have a binary_classification task your last layer should look something like this

model.add(Dense(1, activation='sigmoid'))

Right now you model is out puting 3D array which don't match the shape of your target (2D)

这篇关于ValueError:检查目标时出错:预期dense_2具有3维，但得到形状为(10000, 1)的数组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！