A problem in the layers.index_matrix_to_pairs function

[Chen-Wang-CUHK]

Hi,
Thanks for your code sharing.
But I found there are some problems in layers.index_matrix_to_pairs function:
By using the original code, I can't get
[[[0, 3], [1, 1], [2, 2]],
[[0, 2], [1, 3], [2, 1]]]
while inputing [[3,1,2], [2,3,1]].

It works, after I change the code to:

def index_matrix_to_pairs(index_matrix):
# [[3,1,2], [2,3,1]] -> [[[0, 3], [1, 1], [2, 2]],
# [[0, 2], [1, 3], [2, 1]]]
replicated_first_indices = tf.range(tf.shape(index_matrix)[1])
rank = len(index_matrix.get_shape())
if rank == 2:
replicated_first_indices = tf.tile(
tf.expand_dims(replicated_first_indices, dim=0),
[tf.shape(index_matrix)[0], 1]
)
return tf.stack([replicated_first_indices, index_matrix], axis=rank)

I don't know either the given example or the code is wrong.

[SHUht]

Could you tell me which version of tensorflow you use? I just learn tensorflow.

[Chen-Wang-CUHK]

I use tf 1.3. Actually, I am also a green hand in tensorflow. 2017-09-05 11:01 GMT+08:00 SHUht <[email protected]>:

…

Could you tell me which version of tensorflow you use? I just learn tensorflow. — You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub <#10 (comment)>, or mute the thread <https://github.com/notifications/unsubscribe-auth/AUMLs09qumPe0Y0YdkdfRQ9Aa8J-iVq1ks5sfLltgaJpZM4PBPdc> .

[SHUht]

"dynamic_rnn_decoder = tf.contrib.seq2seq.dynamic_rnn_decoder " Attributerror: 'module' object has no attribute 'dynamic_rnn_decoder'?
who can tell me which tensorflow can solve it?
thank you