Error when checking model input expected convolution2d input 1 to have 4 dimensions but got array with shape 32 32 3

Question

I want to train a deep network starting with the following layer   model   Sequential   model add Conv2D 32  3  3  input shape  32  32  3      using   history   model fit generator get training data                    samples per epoch 1  nb epoch 1 nb val samples 5                  verbose 1 validation data get validation data     with the following generator   def get training data self        while 1          for i in range 1 5               image   self X train i              label   self Y train i              yield  image label     validation generator looks similar    During training  I get the error    Error when checking model input  expected convolution2d input 1 to have 4  dimensions  but got array with shape  32  32  3    How can that be  with a first layer   model add Conv2D 32  3  3  input shape  32  32  3

User · Answer

it depends on how you actually order your data,if its on a channel first basis then you should reshape your data: x_train=x_train.reshape(x_train.shape[0],channel,width,height)

if its channel last: x_train=s_train.reshape(x_train.shape[0],width,height,channel)

User · Answer

The input shape you have defined is the shape of a single sample  The model itself expects some array of samples as input  even if its an array of length 1   Your output really should be 4-d  with the 1st dimension to enumerate the samples  i e  for a single image you should return a shape of  1  32  32  3   You can find more information here under  quot Convolution2D quot   quot Input shape quot  Edit  Based on Danny s comment below  if you want a batch size of 1  you can add the missing dimension using this  image   np expand dims image  axis 0

User · Answer

It is as simple as to Add one dimension  so I was going through the tutorial taught by Siraj Rawal on CNN Code Deployment tutorial  it was working on his terminal  but the same code was not working on my terminal  so I did some research about it and solved  I don t know if that works for you all  Here I have come up with solution   Unsolved code lines which gives you problem   if K image data format       channels first       x train   x train reshape x train shape 0   1  img rows  img cols      x test   x test reshape x test shape 0   1  img rows  img cols      print x train shape      input shape    1  img rows  img cols  else      x train   x train reshape x train shape 0   img rows  img cols      x test   x test reshape x test shape 0   img rows  img cols      input shape    img rows  img cols  1    Solved Code    if K image data format       channels first       x train   x train reshape x train shape 0   1  img rows  img cols      x test   x test reshape x test shape 0   1  img rows  img cols      print x train shape      input shape    1  img rows  img cols  else      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  1    Please share the feedback here if that worked for you

User · Answer

x train   x train reshape -1 28  28  1     Reshape for CNN -  should work   x test   x test reshape -1 28  28  1  history cnn   cnn fit x train  y train  epochs 5  validation data  x test  y test     Output      Train on 60000 samples  validate on 10000 samples   Epoch 1 5   60000 60000                                  - 157s 3ms step - loss  0 0981 - acc  0 9692 - val loss  0 0468 - val acc  0 9861   Epoch 2 5   60000 60000                                  - 157s 3ms step - loss  0 0352 - acc  0 9892 - val loss  0 0408 - val acc  0 9879   Epoch 3 5   60000 60000                                  - 159s 3ms step - loss  0 0242 - acc  0 9924 - val loss  0 0291 - val acc  0 9913   Epoch 4 5   60000 60000                                  - 165s 3ms step - loss  0 0181 - acc  0 9945 - val loss  0 0361 - val acc  0 9888   Epoch 5 5   60000 60000                                  - 168s 3ms step - loss  0 0142 - acc  0 9958 - val loss  0 0354 - val acc  0 9906

User · Answer

yes  it accepts the tuple of four arguments   if you have Number of training Images or whatever  6000  image size 28x28 and a grayscale image you ll have parameters as  6000 28 28 1   the last argument is 1 for greyscale and 3 for color images

User · Answer

Got the same problem  non of the answers worked for me  After a lot of debugging I found out that the size of one image was smaller than 32  This leads to a broken array with wrong dimensions and the above mentioned error  To solve the problem  make sure that all images have the correct dimensions

User · Answer

You should simply apply the following transformation to your input data array   input data   input data reshape  -1  image side1  image side2  channels

User · Answer

I got the same error while working with mnist data set  looks like a problem with the dimensions of X train  I added another dimension and it solved the purpose   X train  X test    y train  y test   train test split X reshaped                                    y labels                                    train size   0 8                                    random state   42   X train   X train reshape -1 28  28  1   X test   X test reshape -1 28  28  1

User · Answer

Probably very trivial  but I solved it by just converting the input to numpy array    For the neural network architecture       model   Sequential       model add Conv2D 32   5  5   activation  relu   input shape  32  32  3      When the input was       n train   len train y raw      train X    train X raw       i  for i in range n train       train y    train y raw i  0  for i in range n train     I got the error   But when I changed it to      n train   len train y raw     train X   np asarray  train X raw       i  for i in range n train       train y   np asarray  train y raw i  0  for i in range n train      It fixed the issue

[deep-learning] Error when checking model input: expected convolution2d_input_1 to have 4 dimensions, but got array with shape (32, 32, 3)

Examples related to deep-learning

Examples related to keras

Examples related to keras-layer