如何在多个图像输入中使用Conv2D？

如何解决如何在多个图像输入中使用Conv2D？

我想使用多个图像作为网络的输入。我想添加Conv2D层，像这样：

from tensorflow.keras.layers import *
from tensorflow.keras.models import Sequential

model = Sequential([
    Input(shape=(1,128,1)),Conv2D(32,3),Flatten(),])

但是此代码引发错误：Input 0 of layer conv2d_40 is incompatible with the layer: expected ndim=4,found ndim=5. Full shape received: [None,1,1]

但是下面的代码运行正常：

model = Sequential([
    Input(shape=(1,512,Dense(32),])

我知道，我可以添加多个Input层，但是我想知道有没有办法做到这一点？

我的意思是我想使用输入形状为[NUMBER_OF_IMAGES,WIDTH,HEIGHT,N_CHANNELS]的数据

NUMBER_OF_IMAGES并不代表全部图像。这是当前输入的金额

解决方法

Conv2D需要4D输入，您无法更改。我不确定您要完成什么，但可以改用Conv3D：

from tensorflow.keras.layers import *
from tensorflow.keras.models import Sequential
import tensorflow as tf

model = Sequential([
    Input(shape=(None,128,1)),Conv3D(32,kernel_size=(1,3,3)),Flatten()
])

multiple_images = tf.random.uniform((10,10,1),dtype=tf.float32)

model(multiple_images)

<tf.Tensor: shape=(10,5080320),dtype=float32,numpy=
array([[-0.26742983,-0.09689523,-0.12120364,...,-0.02987139,0.05515741,0.12026916],[-0.18898709,0.12448274,-0.17439063,0.23424357,-0.06001307,-0.13852882],[-0.14464797,0.26356792,-0.34748033,0.07819699,-0.11639086,0.10701762],[-0.1536693,0.13642962,-0.18564,0.07165999,-0.0173855,-0.04348694],[-0.32320747,0.09207243,-0.22274591,0.11940736,-0.02635285,-0.1140241 ],[-0.21126074,-0.00094431,-0.10933039,0.06002581,-0.09649743,0.09335127]],dtype=float32)>