ValueError: Shape must be rank 0 but is rank 1 for 'cond_11/Switch' (op: 'Switch')

Question

Actually we cant use tf.var as bool in if statement and instead of use tf.cond. I write this code for normalization input data and get confusing error,where I do wrong?

   def global_contrast_normalize(X, scale=1., subtract_mean=True,use_std=False,
       sqrt_bias=0., min_divisor=1e-8):
       mean=tf.reduce_mean(X,axis=1)
       if subtract_mean:
         X = X - mean[:, numpy.newaxis]  # Makes a copy.
      else:
         X = tf.copy.copy(X)
      if X.get_shape()[1]==1:
        #ddof = 0
        mean, var = tf.nn.moments(X, axes=[1])

        normalizers = tf.sqrt(sqrt_bias + var) / scale

      else:
        normalizers = tf.sqrt(sqrt_bias + tf.reduce_sum((X ** 2),axis=1)) / scale
        Normalizers= tf.Variable(normalizers,'float32')
        M=tf.Variable(min_divisor,'float32')

      tf.cond( tf.less_equal(Normalizers,M),lambda:tf.assign(Normalizers,  [1]),lambda:tf.assign(Normalizers,normalizers))
      X /= Normalizers[:, tf.newaxis]  # Does not make a copy.
      return X

error:

in _call_cpp_shape_fn_impl raise ValueError(err.message)

ValueError: Shape must be rank 0 but is rank 1 for 'cond_11/Switch' (op: 'Switch') with input shapes: [1], [1].

Answer 1

The error is stating that the expected input is a scalar (rank 0), but has a shape of ([1],[1]). Usually you can get around this by reshaping the input to a scalar value (using tf.reshape(Normalizers, [])).

For this case, it looks like you want to conditionally set the values of Normalizers depending on whether they are <= M. tf.where does exactly that.

(note, you don't have to convert normalizers or min_divisor to tf.Variable)

Example usage of tf.where:

def global_contrast_normalize(...):
  ...   
  comparison = tf.less_equal(normalizers,M)
  normalizers = tf.where(comparison, tf.ones_like(normalizers), normalizers
  X /= normalizers[:, tf.newaxis]
  return X