Improving a DCGAN by giving the generator an edge batch to start with

Question

I'm trying to improve a DCGAN by giving the generator an edge batch to start with. I'm having trouble with the dimensions of the array. I want my image edge array to have the same dimension as np.random.randn(64, 128)

Here is some of my code:

def load_dataset():
  """
  """
  (X, _), (_, _) = cifar10.load_data()
  #X = np.expand_dims(X, axis=-1).astype('float32')
  X = (X - 127.5) / 127.5
  return X.astype('float32')

def rgb2edge(img):
  bw = cv2.Sobel(rgb2gray(img), cv2.CV_64F, 1, 0)
  return bw
c = rgb2edge(X[1000])
for i in range(64):
  x = rgb2edge(X[i])
  np.concatenate((c,x))

def generate_batch_fake(generator, n_latent_dim, n_samples):
  """
  """
  x_input = np.random.randn(n_samples, n_latent_dim) #Here is where I want to put the array "c"
  X = generator.predict(x_input)
  y = np.zeros((n_samples, 1))
  return X, y

As you can see my the size of the array "c" is (64,32,32)

So the error in my trying is the following:

"Input 0 of layer sequential_10 is incompatible with the layer: expected axis -1 of input shape to have value 128 but received input with shape [32, 32]."

Any suggestions on how to change dimensions would be great!