conversation-tensorflow

conversation-tensorflow copied to clipboard

在model.py文件中，对targets的处理你的代码是这样的： self.decoder_inputs = labels decoder_input_shift_1 = tf.slice(self.decoder_inputs, [0, 1], [batch_size, Config.data.max_seq_length-1]) pad_tokens = tf.zeros([batch_size, 1], dtype=tf.int32) # make target (right shift 1 from decoder_inputs) self.targets = tf.concat([decoder_input_shift_1, pad_tokens], axis=1) 我看了一些其他人的代码，有些对self.targets直接用label，有些用以下代码，即左边增加标识符号，右边去掉最后一个字符，这个有啥讲究吗？...

zcqiand

Error when run in tensorflow 1.6+

2

When I run your project in tf 1.6 or tf 1.7, I got an error: TypeError: The two structures don't have the same sequence type. First structure has type ,...

nguyenvulebinh

New error on train, possibly caused by beam-search-decoder bugfix

4

when running python main.py --config cornell-movie-dialogs --mode train_and_evaluate I get the error message > load vocab ... > vocab size: 41676 > make Training data and Test data Start.... >...

lk251

Significant overfit on default hyperparameters on cornell-movie-dialogs config

2

Running: python main.py --config cornell-movie-dialogs --mode train to the end (100000 steps) will result in a training loss of about 2.6, test loss of 8.4. Which hyperparameters did you use?...

lk251

hierarchical encoder decoder

1

구현은 했는데 if문이 너무 많아져서 LSTM인경우와 bi인경우 계속 tf.stack이 다르게 작동하네요 ㅠㅠ 왜그럴까요? 특히 LSTM, GRU(RNN)인 경우에 output의 모양과 타입이 달라서 tf.stack([output])해줘야하는경우도 있고 tf.stack(output)해줘야 되는경우도 있고 그러네요 ㅠㅠ 흠..

junbeomlee

Is it possible to use customer service conversation as data set with this model ?

7

Hi, Is it possible to use customer service conversation as data set with this model ? such as ``` Hello May I help you ? I want to ask something...

genz10