Tensorflow delete element from each row based on index (negation of gather_nd)

You can use tf.boolean_mask and tf.scatter_nd to create a boolean vector for your (repeated)data. First, you create an indices tensor to indicate the value to mask :

row = tf.constant([0,1,2,3,4,5,6,7,8] ,dtype = tf.int64)
mask_for_each_row = tf.stack([row ,presentIndices[: , 1]],axis = 1 )

and then you use mask_for_each_row as indices in tf.scatter_nd method :

samples =tf.boolean_mask(data ,~tf.scatter_nd(mask_for_each_row , 
            tf.ones((9,),dtype = tf.bool),(9,5)))
samples = tf.reshape(samples ,(9,4))

the samples tensor :

      <tf.Tensor: shape=(9, 4), dtype=int32, numpy=
      array([[ 1, 10, 10,  2],
             [ 4, 10, 10,  2],
             [ 4,  1, 10, 10],
             [10,  9, 10, 10],
             [10,  7, 10, 10],
             [ 8, 10,  3,  5],
             [ 6, 10,  3,  5],
             [ 6,  8, 10,  5],
             [ 6,  8, 10,  3]])>