-
I am trying to run the query `chat_web_best_weights_training.bat` and I am getting the displayed in the screenshot. I have tried all the possible solutions available regarding this but then also it is…
-
Nowadays I was training the nmt as a chatbot, with more than 4 million query-answer pairs as training corpus. However, I found that answer generated by nmt often is just a duplicate from its query.
…
-
I'm currently using python3 with https://github.com/llSourcell/tensorflow_chatbot/issues/46
`Reading model parameters from working_dir/seq2seq.ckpt-42500
> hello
> how are you?
I ' m not .
> …
-
Hello, thanks for sharing this awesome project at first :)
I have fine-tuned the supNMT pre-trained model and save the checkpoint out there. Now I want to build a model out of MASS directory and impl…
-
I'm trying to train a chatbot on google colab, and I've trained around 16k steps successfully before encountering this error:
Exception in thread Thread-1:
Traceback (most recent call last):
Fi…
-
hi Abraham! i ran your algorithm with some series subtitles (in italian), but the result is quite akward... surely due to the small dimension of my dataset (60k lines)... i was wondering, maybe i coul…
-
现在tensorflow1.0已经发布了，API有变动，我把代码里API变动的地方都改了，但是测试训练时仍显示softmax loss function的matmul矩阵shape不对，不知道是哪里出了问题，先问问，回头有时间我自己再读读源码找一下~
log：
```bash
dim: 6865
准备数据
bucket 0 中有数据 164276 条
bucket 1 中有数…
-
## 0. 論文
### タイトル
AliMe Chat: A Sequence to Sequence and Rerank based Chatbot Engine
### 論文リンク
https://www.aclweb.org/anthology/papers/P/P17/P17-2079/
### 著者
Minghui Qiu, Feng-Lin Li, Siyu Wang,…
-
I trained the net for 38100 steps reaching perplexity lower than 5 and wanted to test, but when I change to test mode I get this error:
```
>> Mode : test
Reading model parameters from working_…
-
after running `python inference.py` I got
Starting interactive mode (first response will take a while):
>
I typed hello and I got many warnings, after that, the program freezes. I tried to pres…