3
    model.add(Convolution2D(64, 3, 3, border_mode='same', input_shape=(32, 32, 3)))
    model.add(Activation('relu'))
    model.add(Convolution2D(32, 3, 3))
    model.add(Activation('relu'))
    model.add(MaxPooling2D(pool_size=(2, 2)))
    model.add(Dropout(0.25))

    model.add(Convolution2D(64, 3, 3, border_mode='same'))
    model.add(Activation('relu'))
    model.add(Convolution2D(64, 3, 3))
    model.add(Activation('relu'))
    model.add(MaxPooling2D(pool_size=(2, 2)))
    model.add(Dropout(0.25))

    model.add(Flatten())
    model.add(Dense(512))
    model.add(Activation('relu'))
    model.add(Dropout(0.5))
    model.add(Dense(10))
    model.add(Activation('softmax'))

this is the error

ValueError                                Traceback (most recent call last)
<ipython-input-21-a60216c72b54> in <module>()
----> 1 model.add(Convolution2D(64, 3, 3, border_mode='same', input_shape=(3, 32, 32)))
      2 model.add(Activation('relu'))
      3 model.add(Convolution2D(32, 3, 3))
      4 model.add(Activation('relu'))
      5 model.add(MaxPooling2D(pool_size=(2, 2)))

/home/pranshu_44/anaconda3/lib/python3.5/site-packages/keras/models.py in add(self, layer)
    330                  output_shapes=[self.outputs[0]._keras_shape])
    331         else:
--> 332             output_tensor = layer(self.outputs[0])
    333             if isinstance(output_tensor, list):
    334                 raise TypeError('All layers in a Sequential model '

/home/pranshu_44/anaconda3/lib/python3.5/site-packages/keras/engine/topology.py in __call__(self, x, mask)
    527             # Raise exceptions in case the input is not compatible
    528             # with the input_spec specified in the layer constructor.
--> 529             self.assert_input_compatibility(x)
    530 
    531             # Collect input shapes to build layer.

/home/pranshu_44/anaconda3/lib/python3.5/site-packages/keras/engine/topology.py in assert_input_compatibility(self, input)
    467                                          self.name + ': expected ndim=' +
    468                                          str(spec.ndim) + ', found ndim=' +
--> 469                                          str(K.ndim(x)))
    470             if spec.dtype is not None:
    471                 if K.dtype(x) != spec.dtype:

ValueError: Input 0 is incompatible with layer convolution2d_11: expected ndim=4, found ndim=2

i'm trying to image classification of cifar 10 but i'm getting this error according to do docs [https://keras.io/layers/convolutional/][1] my answer is correct but i don't know why i'm getting this error

  • should i use (None, 32,32,3) dimentions
icedwater
  • 4,701
  • 3
  • 35
  • 50
Pranshu Shah
  • 98
  • 1
  • 7

1 Answers1

1

The Conv2D layer requires an input of 4 dimensions, but, apparently, you only give 2. But I'm sure you've already noticed this.

According to adventuresinmachinelearning :

The format of the data to be supplied is [i, j, k, l] where i is the number of training samples, j is the height of the image, k is the weight and l is the channel number.

I'm unfamiliar with the data you're using, but the value for l (the channel number) should be:

[For a] greyscale image, l will always be equal to 1 (if we had an RGB image, it would be equal to 3)

So basically you just have to:

import tensorflow as tf
tf.reshape(your_image_tensor, [-1, 28, 28, 1]) #For a grayscale image
tf.reshape(your_image_tensor, [-1, 28, 28, 3]) #For a RGB image

Making the appropriate changes for your own code. If you dont want to use tensorflow, I recommend you read this

Update: You can also reshape arrays with numpy.reshape() For more: https://docs.scipy.org/doc/numpy/reference/generated/numpy.reshape.html

John Doe
  • 108
  • 12