taolei87/icml17_knn

Deriving Neural Architectures from Sequence and Graph Kernels

icml17_knn's Issues

missing functions

it seems that there are some scripts missing in utils.
When trying to execute nntest.py I receive the following:

File "nntest.py", line 2, in
from utils.nn import linearND, linear
ImportError: No module named utils.nn

ValueError: Tried to convert 'indices' to a tensor and failed. Error: Argument must be a dense tensor: range(0, 3) - got shape [3], but wanted [].

def linearND(input_, output_size, scope, init_bias=0.0):
shape = input_.get_shape().as_list()
ndim = len(shape)
#print(ndim)
stddev = min(1.0 / math.sqrt(shape[-1]), 0.1)
with tf.variable_scope(scope):
W = tf.get_variable("Matrix", [shape[-1], output_size], tf.float32, tf.random_normal_initializer(stddev=stddev))
X_shape = tf.gather(tf.shape(input_), range(ndim-1))
target_shape = tf.concat(0, [X_shape, [output_size]])
exp_input = tf.reshape(input_, [-1, shape[-1]])
if init_bias is None:
res = tf.matmul(exp_input, W)
else:
with tf.variable_scope(scope):
b = tf.get_variable("bias", [output_size], initializer=tf.constant_initializer(init_bias))
res = tf.matmul(exp_input, W) + b
res = tf.reshape(res, target_shape)
res.set_shape(shape[:-1] + [output_size])
return res

It seems that the line "X_shape = tf.gather(tf.shape(input_), range(ndim-1))" can't work. Could you help me figure it out?