practical_seq2seq

practical_seq2seq copied to clipboard

basic_cell = tf.contrib.rnn.core_rnn_cell.DropoutWrapper( AttributeError: module 'tensorflow.contrib.rnn' has no attribute 'core_rnn_cell'

11

I am on python 3 and tensorflow version 0.12.0 i am getting this error while calling 03-twitter-chatbot.py can someone help me solve this

karanpande

@suriyadeepan i trained the model on the PC without GPU, i spend five days,but it seems need more days, i am at epoch 62400 , the loss i get is...

pzhao16me

mini-batch loss, how low is low enough?

2

Hi all, I have been trying to duplicate the level of quality seen on the example page for the Cornell Movie dialogue and I am wondering how low have you...

kuhanw

Error in restoring session weights - read less byte

1

Hi, I am getting this weird error while running the chatbot code. I am using tensorflow 0.12.1 and python 3.5 using anaconda. [[Node: save/RestoreV2_49 = RestoreV2[dtypes=[DT_FLOAT], _device="/job:localhost/replica:0/task:0/cpu:0"](_recv_save/Const_0, save/RestoreV2_49/tensor_names, save/RestoreV2_49/shape_and_slices)]] Caused...

GKarmakar

'NoneType' object has no attribute 'update'

4

When I run the code self.decode_outputs, self.decode_states = tf.contrib.legacy_seq2seq.embedding_rnn_seq2seq(self.enc_ip,self.dec_ip, stacked_lstm, xvocab_size, yvocab_size, emb_dim) it occurs 'NoneType' object has no attribute 'update'. Thanks for help!

tangyudi

Previous batch_gen will generate the same batch all the time.Now it can generate batches in order and you will get a new batch when you run batch_gen.__next__()

PedroPei

I unable to test the model

1

I used this code. import tensorflow as tf import numpy as np # preprocessed data from datasets.twitter import data import data_utils # load data from pickle and npy files metadata,...

bandarikanth

ImportError: No module named datasets.twitter

3

Hello, getting below error on running "03-Twitter-chatbot.ipynb" in notebook, the file is exists (data.py) ImportError Traceback (most recent call last) in () 3 4 # preprocessed data ----> 5 from...

SamirMatkar

cannot serialize '_io.TextIOWrapper' object

7

Hi! I m trying to run the code, but when i try execute: ``` model = seq2seq_wrapper.Seq2Seq(xseq_len=xseq_len, yseq_len=yseq_len, xvocab_size=xvocab_size, yvocab_size=yvocab_size, ckpt_path='ckpt/twitter/', emb_dim=emb_dim, num_layers=3) ``` I got the following error: ```...

jdebec

Too many UNK in the output

2

I trained the network for 5000 iterations; see the loss below Building Graph Training started Model saved to disk at iteration #1000 val loss : 3.290424 Model saved to disk...

LeenaShekhar