[英]Creating 3D Convolutional Layer
ValueError: One of the dimensions in the output is <= 0 due to downsampling in conv3d_15. ValueError:由于 conv3d_15 中的下采样,output 中的一个维度 <= 0。 Consider increasing the input size.
考虑增加输入大小。 Received input shape [None, 1, 1, 1, 1904211] which would produce output shape with a zero or negative value in a dimension.
接收到的输入形状 [None, 1, 1, 1, 1904211] 将产生 output 形状,维度中的值为零或负值。
Can anyone explain me what is the meaning of this error谁能解释一下这个错误是什么意思
While i am trying to build my 3d convolutional neural.network.当我尝试构建我的 3d 卷积神经网络时。 I got this erro
我得到了这个错误
A 3D convolution layer expect the input to be in a shape similar to (4, 28, 28, 28, 1). 3D 卷积层期望输入的形状类似于 (4, 28, 28, 28, 1)。 For 28x28x28 volumes with a single channel.
适用于具有单通道的 28x28x28 体积。 More info here - https://www.tensorflow.org/api_docs/python/tf/keras/layers/Conv3D
更多信息在这里 - https://www.tensorflow.org/api_docs/python/tf/keras/layers/Conv3D
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.