New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Chatbot responds to every question with "I am a not . " #47
Comments
The training time greatly depends of your hardware and the parameters you give. You probably don't train the network enough. Wait a few more hours. The results from the doc where with using only very short sentences ( |
Which settings would you recommend @Conchylicultor for a robust output using a high end GPU? |
A key hyper-parameter to tune for performance on GPU is the batch size. Read this post for details on performance optimization, in short, a value of 256 or 512 is ideal: https://svail.github.io/rnn_perf/ Below is a snippet of test conversation after training with the following: AWS EC2 p2.xlarge (1GPU with 12GB) Training time ~10 hours Q: Hi Q: Hi! Q: Are you conscious? Q: How are you? Q: What is your name ? Q: Are you alive ? Q: Luke, I am your father! Q: You shall not pass! Q: I'm going to kill you! Q: Are you ready ? Q: When are you ready ? Q: What color is the sky? Q: How old are you ? Q: Can you say 'Hello' ? Q: Can you say 'French fries' ? Q: Can you say Hello ? Q: Can you say French fries ? Q: Can you say yes ? Q: Can you say no ? Q: Is this sentence false ? Q: How do you say hello in french? Q: Speak french. Q: Bonjour. Q: Bonjour ? Q: Hello world! Q: Netflix and chill ? Q: Good night. Q: Are you ok ? Q: Will Google hire me ? Q: Tell me the alphabet ? Q: Tell me the alphabet, please ? Q: What is the first letter of the alphabet ? Q: What is a letter of the alphabet ? Q: How is John ? Q: How is Oliver ? Q: How is Laura ? Q: How is Jenny ? Q: Who is John ? Q: Who is Oliver ? Q: Who is Laura ? |
@Conchylicultor I left it in overnight, so it's been training for 12 hours. Now, it responds to everything with i 'm not a little . |
You can see if the network is still learning by looking at the loss using TensorBoard. During the first iterations, the network usually only predict the same sentences as in your case. |
@eschnou Am I right in assuming that the non-zero |
Here are my results for "python main.py --test":
**Q: Hi
A: i 'm a not .
Q: Hi!
A: i 'm a not .
Q: Are you conscious?
A: i 'm a not .
Q: How are you?
A: i 'm a not .
Q: What is your name ?
A: i 'm a not .
Q: Are you alive ?
A: i 'm a not .
Q: Luke, I am your father!
A: i 'm a not .
Q: You shall not pass!
A: i 'm a not .
Q: I'm going to kill you!
A: i 'm a not .
Q: Are you ready ?
A: i 'm a not .
Q: When are you ready ?
A: i 'm a not .
Q: What color is the sky?
A: i 'm a not .
Q: How old are you ?
A: i 'm a not .
Q: Can you say 'Hello' ?
A: i 'm a not .
Q: Can you say 'French fries' ?
A: i 'm a not .
Q: Can you say Hello ?
A: i 'm a not .
Q: Can you say French fries ?
A: i 'm a not .
Q: Can you say yes ?
A: i 'm a not .
Q: Can you say no ?
A: i 'm a not .
Q: Is this sentence false ?
A: i 'm a not .
**
I didn't edit any of the source code-- I ran main.py for about an hour. It said in the docs that that time would give me some results. What am I doing wrong?
I've tried this multiple times, and I still encounter this program after training it. I've restarted the program, and even re-downloaded the repo, so it's not a glitch in my code. I'm pretty sure that I installed the dependencies correctly.
Any thoughts?
The text was updated successfully, but these errors were encountered: