[pull] master from deepchem:master #2
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
![pull[bot]](https://avatars.githubusercontent.com/in/12910?s=60&v=4){kind=small}
DFT Part-3
Added Cell counting Tutorial
Reduce import warnings
Fix failing torch tests due to missing `pydantic` package
…tion Fix bugs on ligand handling and pdbqt ligand support
* initial * inception v3 * formatting fix * fix for tests * yapf and flake8 fix * test fix * added documention, updated layers.rst, added tests for layers
* Made regressor and classifier classes inheriting the existing class to replicate tf model * reverted robust_multitask * reverted robust in __init__.py * Modified rst file to match new class names for progressive multitask regressor and classifier torchmodel * Comments test_antibody_modeling.py which is causing pytest errors and crashing CI * Changes to correct model in test_progressivemultitask_reload test * HF CI * Minor HF CI
* add layers and docs for SE(3) Transformer implemention * added unitests --------- Co-authored-by: Jose Siguenza <[email protected]>
* Robust classifier * Adds more tasks to the forward test for architecture similarity * Resolves conflict and passes lint tests * Fixes input label processing using default generator * Updates weights files with more appropriate ones with more tasks * Formats for yapf and flake8 * Added tests for classification * Fixes reload test * Added PyTorch robustmultitask classifier model to rst * Added docstring to default generator and logs training per epoch * Removes logger and docstring * Adds docstring to default generator and logs epoch training
…rs (#4184) * added overfit test, updated documentation, fixed yapf and flake8 errors * minor fix
* Robust regressor * Robust regressor pytorch class: * Adds more tasks to the architecture test for robust_regressor * Adds more tasks to architecture similarity test * Fixes mypy error * Added PyTorch robustmultitask regressor model to rst * Rebased and modified for robust multitask classifier and regressor * Fixed __init__.py * Rebased and fixed models.rst
Co-authored-by: Karaka Prasanth Naidu <[email protected]>
* fix flake8 issues * fix mypy issue --------- Co-authored-by: Jose Siguenza <[email protected]>
* fix chemberta code * fix finetuning test * add test for multitask regression * add docstrings
* fix finetuning test * add test for random weight initialization * add test for multitask regression * fix molformer tests * add docstrings
* Parallelized ODE Solver * Updated tests and docs * linting fixes * Updated RK solvers * fixed usage examples * final doc fix 2 * Linting fix * Final doc fix 3 * final clean up + update * linting * doctest fix * doctest fix
* fixed magic numbers, changed name of featurize method, ci issue * ci fix * doctest fix * fixed spelling mistake * fixed doctests and featurizer examples (to use featurize()) * fix doctest
…sing DDP (#4201) * huggingface fix * fix hf model test
* fix lamb optimizer doctest * fix doctest
* Add SE3TransformerFeaturizer for graph data * fix mypy issues and changed name to EquivariantGraphFeaturizer * fix type annotations and import featurizer name * fix yapf and type annotations * fix type annotation for python versions < 3.9 --------- Co-authored-by: Jose Siguenza <[email protected]>
#4197) * Ported the existing TensorFlow cosine similarity function to PyTorch. * adding tests * linting fixes * added a test that uses pre calculated value and made the size of tensor small * adding the layer to layers.rst file for rendering * minor fixes
* pin tf version for weave doctests * unpin tf * fix pyscf install using conda * pyscf install fix 2 * fix typo * fix dgl * pin tf version for weave doctests * fix pyscf install using conda * fix dgl * fix dgl * formatting fixes * fix * fix2 * fix missing Levenshtein package * hf tests fix 1 * fix linting * torch win test install fix * typo fix * pyscf install fix try v1 * disk space fix * move package installs to pip * patch * revert dqclibs change * add missing c libraries * revert pylibxc change * fix python 3.11 install - was failing due to numpy bump * Update test_progressive_multitask.py
* Fixing tutorial * typo fix tutorial * Fixing a tutorial * typo fix
* BLAS error fix for cmake * fix rest of the errors * fix 3? * fix3 v2 * fix 3 v3 * fix 4 * final fix
* tf to torch graphconv * output added
* DAGLayer and DAGGather added * add references * comment fix * correctness test added * linting fix * lint fix2 * lint fix3 * minor fix * mypy fix * mypy fix2
Co-authored-by: Jose Siguenza <[email protected]>
…uivariance_utils.py (#4265) Co-authored-by: Jose Siguenza <[email protected]>
* Robust regressor * Adds more tasks to the architecture test for robust_regressor * Adds more tasks to architecture similarity test * Fixes mypy error * Feat: Initial commit of torch ported PINNs model along with basic tests * Added default model and tests for it * Fix: Reverting robust_multitask * Docs: Added and modified docstrings * Docs: Added PINN to model cheatsheet * Docs: Fixed the name of the PINN model * Feat: Added custom loss function to pinns torch model * Added examples to docstrings for torch pinns model * chore: formatted using yapf and flake8 * Refactor: custom eval function redundancy removed * Docs: Fixes docstrings * Feat: Replaces default NeuralNet class with MultiLayerPerceptron class in torch layers * Feat: Replaces default NeuralNet class with MultiLayerPerceptron class in torch layers * Fix: Uses tanh instead of relu * Fix: Uses 5 layers with 100 neurons as per the original PINNs paper * Fix: Uses 5 layers with 100 neurons as per the original PINNs paper * Adds argument mode for regression and classification * Fix: Fixes boundary loss error * docs: fixe docstring * docs: adds indentation after function definition in the documentation * docs: makes the docs about boundary types easier to understand
* fixed the ODE tutorial * small change in order of function parameters
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.
See Commits and Changes for more details.
Created by
pull[bot]
Can you help keep this open source service alive? 💖 Please sponsor : )