Comments (7)
delesley
commented on August 12, 2024
1
Ah, I see your point. If you Map a Metric over the output sequence, then
you can extract the outputs from TensorFlow as a matrix where each row
corresponds to one output. It's a bit painful when dealing with a batch of
sequences of different lengths, because all the outputs will be
concatenated together, but if you know the original input lengths then you
can split the output matrix appropriately.
-DeLesley
…On Thu, Mar 30, 2017 at 1:25 PM, Olivier Gagnon ***@***.***> wrote:
I'm not sure I understand. The output of an RNN block is a sequence (which
I would like). However, I don't think I can concatenate the output of the
sequence as an output.
P.S. Is there a tag on stack overflow for these kind of question? I feel
this is not the right place.
—
You are receiving this because you commented.
Reply to this email directly, view it on GitHub
<#42 (comment)>, or mute
the thread
<https://github.com/notifications/unsubscribe-auth/AGGbTZLYufmKyBvUHsi_TTC2zClZVwoDks5rrA_TgaJpZM4Mulky>
.
--
DeLesley Hutchins | Software Engineer | [email protected] | 505-206-0315
from fold.
leconteur
commented on August 12, 2024
I also wonder if there is a way to compile an output sequence in this context.
from fold.
delesley
commented on August 12, 2024
Training a seq2seq model is straightforward. You feed in both the input
and the expected output sequences. Do a Fold over the input sequence, and
feed the result into an RNN block over the output sequence, with a Metric
to grab the prediction loss.
Running a seq2seq model in inference mode is much trickier. You don't know
the length of the output sequence in advance, so you need to iterate until
the model outputs an end-of-sequence. The Fold library can't yet make
control-flow decisions based on intermediate values, so there's no good way
to do this as of yet.
…On Thu, Mar 30, 2017 at 12:26 PM, Olivier Gagnon ***@***.***> wrote:
I also wonder if there is a way to compile an output sequence in this
context.
—
You are receiving this because you are subscribed to this thread.
Reply to this email directly, view it on GitHub
<#42 (comment)>, or mute
the thread
<https://github.com/notifications/unsubscribe-auth/AGGbTbvT9o0f7J5CBZRqHp1IIWZtzxlgks5rrAHKgaJpZM4Mulky>
.
--
DeLesley Hutchins | Software Engineer | [email protected] | 505-206-0315
from fold.
leconteur
commented on August 12, 2024
If I know that my output sequence is the same length as my input sequence, is there a way to do it?
from fold.
delesley
commented on August 12, 2024
Use the RNN block.
…On Thu, Mar 30, 2017 at 12:41 PM, Olivier Gagnon ***@***.***> wrote:
If I know that my output sequence is the same length as my input sequence,
is there a way to do it?
—
You are receiving this because you commented.
Reply to this email directly, view it on GitHub
<#42 (comment)>, or mute
the thread
<https://github.com/notifications/unsubscribe-auth/AGGbTaF8y2AXqGikbqSol-LK5rEIk7PHks5rrAVRgaJpZM4Mulky>
.
--
DeLesley Hutchins | Software Engineer | [email protected] | 505-206-0315
from fold.
leconteur
commented on August 12, 2024
I'm not sure I understand. The output of an RNN block is a sequence (which I would like). However, I don't think I can concatenate the output of the sequence as an output.
P.S. Is there a tag on stack overflow for these kind of question? I feel this is not the right place.
from fold.
coopie
commented on August 12, 2024
Thanks both! I've managed to get something working.
from fold.
Related Issues (20)
- NEAT Algorithm implementation HOT 1
- How do I get the root embedding tensors after training the model? HOT 1
- Is it still live?
- Compatability with Tensorflow 2.4+ HOT 3
- Not able to find GPU version of Fold
- can current fold work with tensorflow 1.3? Is it tested? HOT 8
- How to use fold in serving? HOT 2
- Fold & Eager HOT 3
- "undefined symbol" caused by building fold from source HOT 3
- Not compiled to use: SSE4.1 SSE4.2
- Is Fold not compatible with tensorflow-1.4.0? HOT 1
- Typos in sample
- using tf.constant() in td.Composition HOT 1
- "import tensorflow_fold" problem HOT 7
- How to build child-sum tree using tensorflow fold? HOT 2
- How to print intermediate outputs in recursion in TF Fold? HOT 4
- Printing predictions HOT 7
- Making Windows compatible HOT 2
- tensorflow_fold-0.0.1-cp27-cp27mu-manylinux1_x86_64.whl is not a supported wheel on this platform. HOT 1
- fold incompatible with TF-gpu 1.10.1 HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from fold.