ValueError:数据基数不明确.请提供具有相同第一维度的数据 [英] ValueError: Data cardinality is ambiguous. Please provide data which shares the same first dimension

问题描述

我正在尝试创建具有多个输入分支的keras模型，但是keras不喜欢输入具有不同的大小.

I'm trying to create a keras model with multiple input branches, but keras doesn't like that the inputs have different sizes.

这是一个最小的示例:

import numpy as np

from tensorflow import keras
from tensorflow.keras import layers


inputA = layers.Input(shape=(2,))
xA = layers.Dense(8, activation='relu')(inputA)

inputB = layers.Input(shape=(3,))
xB = layers.Dense(8, activation='relu')(inputB)

merged = layers.Concatenate()([xA, xB])

output = layers.Dense(8, activation='linear')(merged)    

model = keras.Model(inputs=[inputA, inputB], outputs=output)


a = np.array([1, 2])
b = np.array([3, 4, 5])    

model.predict([a, b])

哪个会导致错误:

ValueError: Data cardinality is ambiguous:
  x sizes: 2, 3
Please provide data which shares the same first dimension.

在喀拉拉邦有更好的方法吗?我已经阅读了其他参考相同错误的问题，但我不太了解需要更改的内容.

Is there a better way to do this in keras? I've read the other questions referencing the same error, but I'm not really understanding what I need to change.

推荐答案

您需要以正确的格式传递数组...(n_batch，n_feat).一个简单的重塑就足以创建批处理尺寸

you need to pass array in the correct format... (n_batch, n_feat). A simple reshape is sufficient to create the batch dimensionality

import numpy as np
from tensorflow import keras
from tensorflow.keras import layers


inputA = layers.Input(shape=(2,))
xA = layers.Dense(8, activation='relu')(inputA)

inputB = layers.Input(shape=(3,))
xB = layers.Dense(8, activation='relu')(inputB)

merged = layers.Concatenate()([xA, xB])

output = layers.Dense(8, activation='linear')(merged)    

model = keras.Model(inputs=[inputA, inputB], outputs=output)


a = np.array([1, 2]).reshape(1,-1)
b = np.array([3, 4, 5]).reshape(1,-1)

model.predict([a, b])

这篇关于ValueError:数据基数不明确.请提供具有相同第一维度的数据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！