-
Notifications
You must be signed in to change notification settings - Fork 84
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
Using Recurrent and Concat together #30
Comments
Great question. First up. I don't think your Seems like I should add a version of I believe right now it's probably not possible*. As really, Now the problem is that Would you like to try writing it? EDIT:
|
Ah, good to know about how I'll take a stab at a 1D |
Ahh, there's actually another problem. I haven't yet written an instance of I think it's possible, but requires packing all the recurrent (sideways travelling) shapes into a single vector. |
You might have to run both LSTM networks forwards individually for now. The GAN mnist example gives a non-recurrent example of something like this. |
Ah, ok. I had thought about doing that, but hadn't looked closely enough at Seems like Thanks for your help! |
That's right. Edit. Sorry: |
Cool, I'm making progress on this. One question that came up as I was working is whether there's an easy way to construct an all-zero vector for a particular |
You can just use the literal
If you look at the code for |
Please see #32 In that branch, this will compile type R = Recurrent
type F = FeedForward
type ShapeInput = 'D1 10
type LearnPlayer = RecurrentNetwork
'[ R (LSTM 10 20) ]
'[ ShapeInput , D1 20 ]
type LearnOpponent = RecurrentNetwork
'[ R (LSTM 10 20) ]
'[ ShapeInput, D1 20 ]
type RecNet = RecurrentNetwork
'[ R (
ConcatRecurrent
(D1 20)
(R LearnPlayer)
(D1 20)
(R LearnOpponent)
)
]
'[ ShapeInput, 'D1 40 ]
randomNet :: MonadRandom m => m RecNet
randomNet = randomRecurrent |
I believe this is fixed, but feel free to follow up with any problems you're having. |
I'm trying to use Recurrent and Concat together in the same network. In particular, I'm trying to run two LSTMs in parallel against different subsets of the input, and then want to
Concat
the results together.I have something like this, so far:
On compilation, the error I'm getting is:
Is there any way to accomplish what I'm looking for with Grenade right now?
P.S. I also tried this way, and got the same error:
The text was updated successfully, but these errors were encountered: