integrating changes for work on integrate_lbann_moses back to personal fork, pull request to update master of sams fork with those changes #3
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
* FCD from fcd_torch * evaluation script gpu -> device * pyTorch 1.0.1 * shm-size * save config and vocab first * jtnn sampling fix * device in run.py * minor fixes * minor fixes * share pool * share pool * close pool
* updated VAE, AAE, CharRNN, JTN-VAE * Update README.md * codestyle for metrics
* updated VAE, AAE, CharRNN, JTN-VAE * Update README.md * codestyle for metrics * added fast_JTN * merged * updated plots * train metrics * train metrics * train metrics * train metrics
* updated VAE, AAE, CharRNN, JTN-VAE * Update README.md * codestyle for metrics * added fast_JTN * merged * updated plots * train metrics * train metrics * train metrics * train metrics * travis init, added density plots, some code style * README updated * updated travis * README updated * merged * moved tests * updated metrics * metrics * added samples * repo * added metrics files
* prepared configs for aae, vae and char_rnn * pep8 for AAE * pep8 for everything * organ possible fix * cannonize fix * updated metrics 1 * aae schedule * aae reset * updated metrics * citation fix * table fix * flake8 * flake8 * flake8 * PyPi * 0.1.2 * uncomment run.py * Updated installation guide * updated images
* cPickle -> pickle * version * cPickle
* updated char_rnn results * updated tqdm * fix arrow direction
…sets#49) Catch "ValueError: Sanitization error: Explicit valence for atom greater than permitted" as invalid molecule, during call to compute_scaffold().
* novelty metric, models refactored, hyperparameters tuned * updated results * fix table layout * temporary fix pytorch version * updated description
* Docker Documentation * Docker image size * Docker image size reducing * Docker size * bug in tensorflow GPU fixed * 4Gb to download * dockerignore * dockerfile before fix * miniconda version python fixed * miniconda 4.6.14 fixe * fixed nonexisting pytorch version * dockerignore fixed * Dockerfile updated
* Docker Documentation * Docker image size * Docker image size reducing * Docker size * bug in tensorflow GPU fixed * 4Gb to download * dockerignore * dockerfile before fix * miniconda version python fixed * miniconda 4.6.14 fixe * fixed nonexisting pytorch version * dockerignore fixed * Dockerfile updated * data dir path updated in accordance with the documenation * README updated * README updated: run with several seeds
…anymore (molecularsets#58) * use local cache of ZINC dataset, since original URL is not available anymore * fix flake8
* Added LatentGAN * attempt to remove submodule in LatentGAN * attempt to remove submodule from LatentGAN * removed ddc_pub submodule * Added refactored LatentGAN * attempt to remove submodule * removed data directory from git during development * untracking pointer files from git-lfs * re-added data files from origin * merged with changes from main MOSES repo * added the latentgan model * refactored latentgan code to comply with travis ci * removed temporary files and too heavy pretrained models
* latent gan metrics * update image * fix unicode * update pandas in Docker * update list of models * 11_p0.smi.gz -> LFS
* CircularBuffer fix * remove auto import re-order
* Added LatentGAN * attempt to remove submodule in LatentGAN * attempt to remove submodule from LatentGAN * removed ddc_pub submodule * Added refactored LatentGAN * attempt to remove submodule * removed data directory from git during development * untracking pointer files from git-lfs * re-added data files from origin * merged with changes from main MOSES repo * added the latentgan model * refactored latentgan code to comply with travis ci * removed temporary files and too heavy pretrained models * fixed bug with sampling not importing model checkpoints * updated results table and distribution images * corrected an uploaded sample and re-drew distrubution plots * corrected the bold font of table to reflect new values * fixed bolded numbers in int_div table * added forgotten sd on Unique@1K for LatentGAN * added the pretrained heteroencoder of LatentGAN * clarified README of LatentGAN * set default heteroencoder to pretrained moses * fixed flake8 style issue * added shell script for installing all dependencies
* updated Dockerfile for LatentGAN * updated README * add rdkit version * remove rdkit from external installation script * TF 1.14 * pip instead of conda
* pylint + fix ks argument type * flake8 * pylint for scripts
* Install MOSES dataset in moses package * PEP8 * Fix CI * fix typo Co-authored-by: Daniil Polykovskiy <[email protected]>
…rmatting was done, some functions such as the moses/char_rnn/model.py were tweaked to allow for more general functionality
… the moses sample.py script that was due to simple formatting difference
…merging back into my fork then submitting PR to master on sams fork
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.
This is getting things back to the fork and pull workflow. this PR contains changes I made that were reflected on the integrate_lbann_moses branch of sam's fork of moses.