问题描述
我的输入形状应该是100x100.它代表一个句子.每个单词都是100个维度的向量，一个句子中最多可以包含100个单词.
My input shape is supposed to be 100x100. It represents a sentence. Each word is a vector of 100 dimensions and there are 100 words at maximum in a sentence.
我向CNN输入了8个句子.我不确定这是否意味着我的输入形状应为100x100x8.
I feed eight sentences to the CNN.I am not sure whether this means my input shape should be 100x100x8 instead.
接下来的几行
Convolution2D(10, 3, 3, border_mode='same',
input_shape=(100, 100))
抱怨:
输入0与层卷积2d_1不兼容:预期ndim = 4，找到ndim = 3
Input 0 is incompatible with layer convolution2d_1: expected ndim=4, found ndim=3
这对我来说没有意义，因为我的输入尺寸为2.我可以通过将input_shape更改为(100,100,8)来解决它.但是期望的ndim = 4"位对我来说没有任何意义.
This does not make sense to me as my input dimension is 2. I can get through it by changing input_shape to (100,100,8). But the "expected ndim=4" bit just does not make sense to me.
我也看不到为什么带有10个滤镜的3x3卷积层不能接受100x100的输入.
I also cannot see why a convolution layer of 3x3 with 10 filters do not accept input of 100x100.
即使我收到有关期望的ndim = 4"的投诉.我在激活层遇到问题.在那里抱怨:
Even I get thru the complains about the "expected ndim=4". I run into problem in my activation layer. There it complains:
不能将softmax应用于不是2D或3D的张量.在这里ndim = 4
Cannot apply softmax to a tensor that is not 2D or 3D. Here, ndim=4
任何人都可以解释这里发生了什么以及如何解决吗?非常感谢.
Can anyone explain what is going on here and how to fix it? Many thanks.
推荐答案
我遇到了同样的问题，并且解决了这个问题，在input_shape参数中添加了channel的一维.
I had the same problem and I solved it adding one dimension for channel to input_shape argument.
我建议以下解决方案:
Convolution2D(10, 3, 3, border_mode='same', input_shape=(100, 100, 1))
这篇关于当构建CNN时，我收到了Keras的投诉，这些投诉对我来说没有意义.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！