CODEWITHSUNDEEP
pythontensorflow
user3285099
user3285099

Reputation: 527

Sampling in tensorflow

I am sampling points in each image using the following function. tf.range gives an error if batch_size is None. How do I sample in tensorflow 

def sampling(binary_selection,num_points, points):
  """
      binary_selection: tensor of size (batch_size, points) 
          with values 1.0 or 0.0. Indicating positive and negative points. 
          We want to sample num_points from positive points of each image
      points: tensor of size (batch_size, num_points_in_image)
      num_points: number of points to sample for each image
  """
  batch_size = points.get_shape()[0]
  indices = tf.multinomial((tf.log(binary_selection)), num_points)
  indices = tf.cast(tf.expand_dims(indices, axis=2), tf.int32)
  batch_seq = tf.expand_dims(tf.range(batch_size), axis=1) 
  im_indices = tf.expand_dims(tf.tile(batch_seq, [1, num_points]), axis=2) 
  indices = tf.concat([im_indices, indices], axis=2)
  return tf.gather_nd(points, indices)

I get the following error

_dimension_tensor_conversion_function raise ValueError("Cannot convert an unknown Dimension to a Tensor: %s" % d) ValueError: Cannot convert an unknown Dimension to a Tensor: ?

During the test and training time I will have batch_size an integer but when I initialize I want to give None as input so that batch size can be varied during test and training time.

Upvotes: 1

Views: 799

Answers (1)

a3.14_Infinity
a3.14_Infinity

Reputation: 5843

You need to provide a value to batch_size.

It needs to be initialized.

Currently, it is not given any value.

Upvotes: 1

Related Questions