问题描述
我正在尝试使用学习的.h5文件进行预测.学习模型如下.
I am trying to predict using the learned .h5 file.The learning model is as follows.
model =Sequential()
model.add(Dense(12, input_dim=3, activation='relu'))
model.add(Dense(8, activation='relu'))
model.add(Dense(4, activation='relu'))
model.add(Dense(1, activation='sigmoid'))
model.compile(loss='binary_crossentropy', optimizer = 'adam', metrics = ['accuracy'])
然后，我将输入的形式编写如下.
And I wrote the form of the input as follows.
x = np.array([[band1_input[input_cols_loop][input_rows_loop]],[band2_input[input_cols_loop][input_rows_loop]],[band3_input[input_cols_loop][input_rows_loop]]])
prediction_prob = model.predict(x)
我认为形状正确，但是发生了以下错误.
I thought the shape was correct, but the following error occurred.
x的形状显然是(3,1)，但是上述错误并没有消失(数据来自形式的csv文件).
The shape of x is obviously (3,1), but the above error doesn't disappear (the data is from a csv file in the form of (value 1, value 2, value 3, class)).
我该如何解决这个问题?
How can I solve this problem?
推荐答案
您是对的，但这不是keras期望的.预期为(1, 3)形状:按照惯例，轴0表示批次大小，轴1表示特征.第一个Dense层接受3个功能，这就是为什么它仅看到一个功能时就会抱怨的原因.
You are right, but that's not what keras expects. It expects (1, 3) shape: by convention, axis 0 denotes the batch size and axis 1 denotes the features. The first Dense layer accepts 3 features, that's why it complains when it sees just one.
解决方案就是简单地转置x.
The solution is simply to transpose x.
这篇关于ValueError:检查时出错:预期density_1_input的形状为(3，)，但数组的形状为(1，)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！