Python Keras ValueError：输入 0 与层 conv2d_1 不兼容：预期 ndim=4，发现 ndim=5
声明：本页面是StackOverFlow热门问题的中英对照翻译，遵循CC BY-SA 4.0协议，如果您需要使用它，必须同样遵循CC BY-SA许可，注明原文地址和作者信息，同时你必须将它归于原作者（不是我）：StackOverFlow
原文地址: http://stackoverflow.com/questions/47665391/
Warning: these are provided under cc-by-sa 4.0 license. You are free to use/share it, But you must attribute it to the original authors (not me):
StackOverFlow
Keras ValueError: Input 0 is incompatible with layer conv2d_1: expected ndim=4, found ndim=5
提问by Lucky
I have checked all the solutions, but still, I am facing the same error. My training images shape is (26721, 32, 32, 1), which I believe it is 4 dimension, but I don't know why error shows it is 5 dimension.
我已经检查了所有解决方案，但仍然面临同样的错误。我的训练图像形状是(26721, 32, 32, 1)，我相信它是 4 维，但我不知道为什么错误显示它是 5 维。
model = Sequential()
model.add(Convolution2D(16, 5, 5, border_mode='same', input_shape= input_shape ))
So this is how I am defining model.fit_generator
所以这就是我的定义 model.fit_generator
model.fit_generator(train_dataset, train_labels, nb_epoch=epochs, verbose=1,validation_data=(valid_dataset, valid_labels), nb_val_samples=valid_dataset.shape[0],callbacks=model_callbacks)
回答by Daniel M?ller
The problem is input_shape.
问题是input_shape。
It should actually contain 3 dimensions only. And internally keras will add the batch dimension making it 4.
它实际上应该只包含 3 个维度。并且在内部 keras 将添加批处理维度使其成为 4。
Since you probably used input_shapewith 4 dimensions (batch included), keras is adding the 5th.
由于您可能使用input_shape了 4 个维度（包括批次），因此 keras 将添加第 5 个维度。
You should use input_shape=(32,32,1).
你应该使用input_shape=(32,32,1).
回答by SANDEEP KUMAR H
The problem is with input_shape. Try adding an extra dimension/channel for letting keras know that you are working on a grayscale image ie -->1
问题在于input_shape. 尝试添加额外的维度/通道，让 keras 知道您正在处理灰度图像，即 -->1
input_shape= (56,56,1).
Probably if you are using a normal Deep learning model then it won't raise an issue but for Convnet it does.
input_shape= (56,56,1). 可能如果您使用的是普通的深度学习模型，那么它不会引发问题，但对于 Convnet 来说却是。
回答by Akash Desai
For reshape the data we need to add fourth dimensions i.e changing from (6000,28,28)to (6000,28,28,1)
为了重塑数据，我们需要添加第四维，即从(6000,28,28)到(6000,28,28,1)
My code is:
我的代码是：
img_rows=x_train[0].shape[0]
img_cols=x_test[0].shape[1]
X_train=x_train.reshape(x_train.shape[0],img_rows,img_cols,1)
X_test=x_test.reshape(x_test.shape[0],img_rows,img_cols,1)
Input_shape=(img_rows,img_cols,**). *-> I forgot to put 1 here.
I have face the same problem
我遇到了同样的问题
Input 0 is incompatible with layer conv2d_4 : except ndim=4 ,found ndim=3
Input 0 is incompatible with layer conv2d_4 : except ndim=4 ,found ndim=3
I solved this problem by simply putting value in the input shape
我通过简单地在输入形状中放置值来解决这个问题
Input_shape=(img_rows,img_cols,1)#store the shape of single image.
With this problem is solved
有了这个问题就解决了
回答by dgamer
Here you need to check the "channels_first"whenever CNN is used as 2d,Also reshape your train_data and test data as:
在这里，无论何时将 CNN 用作 2d，您都需要检查“channels_first”，还将您的 train_data 和测试数据重塑为：
if K.image_data_format() == 'channels_first': #check for channels_first
train_img.reshape(train_img.shape[0],1,x,x)
Input_shape=(1,x,x) #In your case x is 32
else:
train_img.reshape(train_img.shape[0],x,x,1)
Input_shape=(x,x,1)
回答by Akash Desai
I have faced the same problem
我遇到了同样的问题
Input 0 is incompatible with layer conv2d_4 : except ndim=4 ,found ndim=3
输入 0 与层 conv2d_4 不兼容：ndim=4 除外，发现 ndim=3
I solved this problem by simply putting value in the input shape
我通过简单地在输入形状中放置值来解决这个问题
Input_shape=(img_rows,img_cols,1)#store the shape of single image. .. & the problem is solved
