-
Notifications
You must be signed in to change notification settings - Fork 953
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
add tf #133
Open
heruohan
wants to merge
112
commits into
ae-rnn
Choose a base branch
from
master
base: ae-rnn
Could not load branches
Branch not found: {{ refName }}
Loading
Could not load tags
Nothing to show
Loading
Are you sure you want to change the base?
Some commits from the old base branch may be removed from the timeline,
and old review comments may become outdated.
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
Reason for edit: the sample line below requires the sum(p) == 1. This is not the case always, due to int32 type rounding "errors". Instead, let's implement a sampling algorithm that samples per weighted p.
Changed Sampling Procedure in model.py
Updated code in order to work with the newest tensorflow version 0.7.1
Python3 compatibility
suggested sampling type argument --sample
…plus_b Added tf.matmul(x, w) + b
Conflicts: train.py
when training, model can be initialized from previously saved model
Better error message
Added the last save
refactored for tensorflow 0.9
Add encoding parameter to TextLoader, default to utf-8.
Make sample play nicer with unicode.
They were saved in binary mode so they must be opened in binary mode as well.
There is a random segfault in Travis even if the command generates valid output. So test that output looks good, not if the command exits cleanly. Revisit this later as it may lead to tests passing when they shouldn't. Also adds build status shield to README
Use tmp directory for CI build save/log dirs
Show defaults in --help
…els with data not containing a space.
- Add an appropriate unix shebang - chmod u+x
- ordered so that parameters of the model are separated from other non meaningfull configuration (paths, save freq...) - add some more information to help newcommers like me understand some parameters
TensorFlow no longer supports Python 3.3
Removed unnecessary line
pep8 is now pycodestyle
Add explanatory comments to files
Improve readme and command line help
…ipts Enable execution of main Python scripts train.py and sample.py
Use most fequent character as prime instead of ' ' to not fail on mod…
This is to make the output more readable and assessable.
decoding again from the utf-8 format
@heruohan OK to close this test now? |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
sorry,this is a test.