added multi-head attention #1
Closed
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
|
Please make sure all interfaces and even code structures are exactly the same with the Texar TF version. |
|
Closing this due to non-compliant interfaces. |
TomNong
pushed a commit
to TomNong/texar-pytorch
that referenced
this pull request
Aug 7, 2019
TomNong
pushed a commit
to TomNong/texar-pytorch
that referenced
this pull request
Aug 7, 2019
merge from upstream master
TomNong
pushed a commit
to TomNong/texar-pytorch
that referenced
this pull request
Aug 7, 2019
bert polish
gpengzhi
pushed a commit
that referenced
this pull request
Jan 2, 2020
* Add text style transfer (#1) * initial commit * bug fixes and adjusting conv inputs * separate forward function for Discriminator and Generator and disable Gen training for debugging * remove debugger statement * bug fix * detaching stuff before accumulating * refactor and add component as optional parameter * Add optimizer for and backprop against encoder * Add in README * Add text style transfer with improvements (#2) * initial commit * bug fixes and adjusting conv inputs * separate forward function for Discriminator and Generator and disable Gen training for debugging * remove debugger statement * bug fix * detaching stuff before accumulating * refactor and add component as optional parameter * Add optimizer for and backprop against encoder * Add in README * more fixes to eval mode * create optimizers so that they can be saved * fix typo * restore optimizers * Update ctrl_gen_model.py * remove tensorflow import * Add text style transfer (#3) * Add text style transfer (#4) * initial commit * bug fixes and adjusting conv inputs * separate forward function for Discriminator and Generator and disable Gen training for debugging * remove debugger statement * bug fix * detaching stuff before accumulating * refactor and add component as optional parameter * Add optimizer for and backprop against encoder * Add in README * more fixes to eval mode * create optimizers so that they can be saved * fix typo * linting issues * add type annotation for encoder * fix linting * Isolate AE in training * works after changing the learning rate * remove debugger * Add text style transfer (#5) * Reviewed changes * linting * Add text style transfer (#6) * initial commit * linting * Fix docs build issue * Fix typo * init_commit * modularize t5 and comment out debugging statements * Add decorators for pretrained_tests * remove changes from text-style-transfer * remove collect variable changes * remove text-style-transfer from docs * more clean up and removing debugger statements * more clean up * fix linting * more linting * Update utils.rst * linting and fixing minor bugs in gpt2-tests * skipping pretrained tests * fix documentation error * fix linting * Update gpt2_test.py * refactor gin reading function * revert using identity, use nn.Module instead * Update decoder_base.py * fix type for T5Decoder * fix linting * add a standalone test for T5 * Adding T5 Tokenizer * adding import to __init__.py * linting fix * making review changes * reviewed changes
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.
No description provided.