This repository has been archived by the owner on Nov 17, 2023. It is now read-only.
Add RNN model in R #2417
Merged
Add RNN model in R #2417
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
@thirdwing can you review this? |
ziyeqinghan
force-pushed
the
master
branch
2 times, most recently
from
33b8de2 to
0bdd7f5
Compare
|
LGTM. This is mostly refactoring work. Sorry for the delay. I was caught in a bad cold while in Texas. @terrytangyuan I will merge this if you agree. |
|
@thirdwing Go ahead. Looks good. @ziyeqinghan You might need to rebase. |
Merged
|
The branch is rebased. |
zjf
pushed a commit
to zjf/mxnet
that referenced
this pull request
Jun 18, 2016
* refactor lstm model to seperate reusable rnn function like training from lstm model * add Custom RNN model in R * modify the documentation to add explanation of RNN and fix some typos * remove some unuseful comments * fix typo
tqchen
pushed a commit
that referenced
this pull request
Jun 18, 2016
* Update warpctc-inl.h avoid compile error in cpu-only mode * [OP] Support softmax with probability label (#2456) * don't run char rnn test in R (#2459) * [OP] add slice_axis (#2458) * [OP] add slice * optimization * fix some typos (#2450) * add warpctc config to config.mk (#2451) * update lstm.py reshape using shape (#2446) changing target_shape to shape * fix worker node could not exit (#2440) * add target_shape and adj to deconv for friendly using (#2445) * add target_shape and adj to deconv for friendly using * fix typo * Add RNN model in R (#2417) * refactor lstm model to seperate reusable rnn function like training from lstm model * add Custom RNN model in R * modify the documentation to add explanation of RNN and fix some typos * remove some unuseful comments * fix typo
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
I add Custom RNN model and some high-level reusable APIs is provided which is similar to the APIs for LSTM in [#2329]
mx.rnnTraining RNN Unrolled Modelmx.rnn.inference Create a RNN Inference Modelmx.rnn.forwardForward function for RNN inference model