A PyTorch based deep learning library for drug pair scoring.

Overview


PyPI Version Docs Status Code Coverage Build Status

Documentation | External Resources | Datasets | Examples

ChemicalX is a deep learning library for drug-drug interaction, polypharmacy side effect and synergy prediction. The library consists of data loaders and integrated benchmark datasets. It also includes state-of-the-art deep neural network architectures that solve the drug pair scoring task. Implemented methods cover traditional SMILES string based techniques and neural message passing based models.


Drug Pair Scoring Explained

Our framework solves the so called drug pair scoring task of computational chemistry. In this task a machine learning model has to predict the outcome of administering two drugs together in a biological or chemical context. Deep learning models which solve this task have an architecture with two distinctive parts:

  1. A drug encoder layer which takes a pair of drugs as an input (blue and red drugs below).
  2. A head layer which outputs scores in the administration context - polypharmacy in our explanatory figure.


Case Study Tutorials

We provide in-depth case study tutorials in the Documentation, each covers an aspect of ChemicalX’s functionality.


Citing

If you find ChemicalX and the new datasets useful in your research, please consider adding the following citation:

@inproceedings{chemicalx,
               author = {Benedek Rozemberczki and Charles Tapley Hoyt and Benjamin Gyori},
               title = {{ChemicalX: A Deep Learning Library fo Drug Pair Scoring}},
               year = {2022},
}

A simple example



Methods Included

In detail, the following temporal graph neural networks were implemented.

2017

2018

2019

2020

2021


Auxiliary Layers


Head over to our documentation to find out more about installation, creation of datasets and a full list of implemented methods and available datasets. For a quick start, check out the examples in the examples/ directory.

If you notice anything unexpected, please open an issue. If you are missing a specific method, feel free to open a feature request.


Installation

Binaries are provided for Python version <= 3.9.

PyTorch 1.9.0

To install the binaries for PyTorch 1.9.0, simply run

pip install torch-scatter -f https://pytorch-geometric.com/whl/torch-1.9.0+${CUDA}.html
pip install torch-sparse -f https://pytorch-geometric.com/whl/torch-1.9.0+${CUDA}.html
pip install torch-cluster -f https://pytorch-geometric.com/whl/torch-1.9.0+${CUDA}.html
pip install torch-spline-conv -f https://pytorch-geometric.com/whl/torch-1.9.0+${CUDA}.html
pip install torch-geometric
pip install chemicalx

where ${CUDA} should be replaced by either cpu, cu102, or cu111 depending on your PyTorch installation.

cpu cu102 cu111
Linux
Windows
macOS
Expand to see installation guides for older PyTorch versions...

PyTorch 1.8.0

To install the binaries for PyTorch 1.8.0, simply run

$ pip install torch-scatter -f https://pytorch-geometric.com/whl/torch-1.8.0+${CUDA}.html
$ pip install torch-sparse -f https://pytorch-geometric.com/whl/torch-1.8.0+${CUDA}.html
$ pip install torch-cluster -f https://pytorch-geometric.com/whl/torch-1.8.0+${CUDA}.html
$ pip install torch-spline-conv -f https://pytorch-geometric.com/whl/torch-1.8.0+${CUDA}.html
$ pip install torch-geometric
$ pip install torch-geometric-temporal

where ${CUDA} should be replaced by either cpu, cu101, cu102, or cu111 depending on your PyTorch installation.

cpu cu101 cu102 cu111
Linux
Windows
macOS

PyTorch 1.7.0

To install the binaries for PyTorch 1.7.0, simply run

$ pip install torch-scatter==latest+${CUDA} -f https://pytorch-geometric.com/whl/torch-1.7.0.html
$ pip install torch-sparse==latest+${CUDA} -f https://pytorch-geometric.com/whl/torch-1.7.0.html
$ pip install torch-cluster==latest+${CUDA} -f https://pytorch-geometric.com/whl/torch-1.7.0.html
$ pip install torch-spline-conv==latest+${CUDA} -f https://pytorch-geometric.com/whl/torch-1.7.0.html
$ pip install torch-geometric
$ pip install torch-geometric-temporal

where ${CUDA} should be replaced by either cpu, cu92, cu101, cu102 or cu110 depending on your PyTorch installation.

cpu cu92 cu101 cu102 cu110
Linux
Windows
macOS

PyTorch 1.6.0

To install the binaries for PyTorch 1.6.0, simply run

$ pip install torch-scatter==latest+${CUDA} -f https://pytorch-geometric.com/whl/torch-1.6.0.html
$ pip install torch-sparse==latest+${CUDA} -f https://pytorch-geometric.com/whl/torch-1.6.0.html
$ pip install torch-cluster==latest+${CUDA} -f https://pytorch-geometric.com/whl/torch-1.6.0.html
$ pip install torch-spline-conv==latest+${CUDA} -f https://pytorch-geometric.com/whl/torch-1.6.0.html
$ pip install torch-geometric
$ pip install torch-geometric-temporal

where ${CUDA} should be replaced by either cpu, cu92, cu101 or cu102 depending on your PyTorch installation.

cpu cu92 cu101 cu102
Linux
Windows
macOS

Running tests

$ python setup.py test

License

Comments
  • Add the DeepDDI model

    Add the DeepDDI model

    Dear @hzcheney,

    • Please read the paper first. It is here.
    • After that read the contributing guidelines.
    • If there is an existing open source version of the model please take a look.
    • ChemicalX is built on top of PyTorch 1.10. and torchdrug.
    • A similar model is which uses to generate drug representations. Take a look at the layer definition here.
    • The library heavily builds on top on torchdrug and molecules in batches are PackedGraphs.
    • There is already a model class under ./chemicalx/models/
    • Context features, drug level features and labels are all FloatTensors.
    • Look at the examples and tests under ./examples/ and ./tests/.
    • Add auxiliary layers as you see fit - please document these, add tests and add these layers to the main readme.md if needed.
    • Add typing to the initialisation and forward pass.
    • Non data dependent hyperparameters should have default values.
    • Please add tests under ./tests/ and make sure that your model/layer is tested with real data.
    • Write an example under ./examples/. What is the AUC on the test set? Is it reasonable?
    model 
    opened by benedekrozemberczki 13
  • Implement DeepDDI model

    Implement DeepDDI model

    Closes #2

    • [x] Unit tests provided for these changes
    • [ ] Documentation and docstrings added for these changes

    Changes

    • add DeepDDI model
    • add DeepDDI examples
    • add DeepDDI testcase
    model 
    opened by hzcheney 11
  • Adding DrugBank DDI and Two Sides.

    Adding DrugBank DDI and Two Sides.

    Summary

    • Adding DrugBank DDI and TwoSides.

    • [X] Code passes all tests

    • [X] Unit tests provided for these changes

    • [X] Documentation and docstrings added for these changes

    Changes

    • Adds the DrugBank DDI and TwoSides Datasets.
    • Adds the loaders.
    • Adds tests.
    • Adds documentation of data cleaning.
    • Adds the data cleaning scripts.
    dataset 
    opened by benedekrozemberczki 10
  • Add the SSI-DDI Model

    Add the SSI-DDI Model

    • Please read the paper first. It is here.
    • There is also code-release with the paper here.
    • After that read the contributing guidelines.
    • If there is an existing open-source version of the model please take a look.
    • ChemicalX is built on top of PyTorch 1.10. and torchdrug.
    • A similar model is EPGCNDS which usesGraphConvolutions to generate drug representations. Take a look at the layer definition here. You should use the layers from torchdrug not the models.
    • The library heavily builds on top on torchdrug and molecules in batches are PackedGraphs.
    • There is already a model class under ./chemicalx/models/
    • Context features, drug level features, and labels are all FloatTensors.
    • Look at the examples and tests under ./examples/ and ./tests/.
    • Add auxiliary layers as you see fit - please document these, add tests, and add these layers to the main readme.md if needed.
    • Add typing to the initialization and forward pass.
    • Non-data-dependent hyper-ammeters should have default values.
    • Please add tests under ./tests/ and make sure that your model/layer is tested with real data.
    • Write an example under ./examples/. What is the AUC on the test set? Is it reasonable?
    model 
    opened by benedekrozemberczki 10
  • Add multi-GPU support with `accelerate`

    Add multi-GPU support with `accelerate`

    Summary

    Enable GPU support (+more) via the Accelerate library.

    This is still work in progress - there's still some bugs to be ironed out around multi-gpu and some models.

    TODO:

    • [ ] add documentation for accelerate
    • [ ] multi-gpu tests
    • [ ] test with all models

    • [ ] Unit tests provided for these changes
    • [ ] Documentation and docstrings added for these changes using the sphinx style

    Changes

    • Add Accelerate as a dependency
    • Adjust the pipeline code to use accelerate
    opened by GavEdwards 8
  • Implement DeepDrug model

    Implement DeepDrug model

    Closes #14

    Added the DeepDrug model, trying to copy as much as possible from their approach. The paper didn't use any context features, but I implemented the model so that it could be used in both ways. I ran the model with and without context feats on DrugCombDB with around 0.76 AUROC (no context features led to a minor drop in AUROC).

    Provided an example that runs the model and a unit test which tests both the context and no-context modes of this model.

    • [X] Unit tests provided for these changes
    • [X] Documentation and docstrings added for these changes
    model 
    opened by kajocina 8
  • KeyError: 'node_feature' from running deepdds_example.py

    KeyError: 'node_feature' from running deepdds_example.py

    Please see the following log.

     File "deepdds.py", line 27, in <module>
        main()
      File "deepdds.py", line 14, in main
        results = pipeline(
      File "/storage/htc/nih-tcga/sc724/conda/synergy/lib/python3.8/site-packages/chemicalx/pipeline                                                        .py", line 155, in pipeline
        prediction = model(*model.unpack(batch))
      File "/storage/htc/nih-tcga/sc724/conda/synergy/lib/python3.8/site-packages/torch/nn/modules/m                                                        odule.py", line 1110, in _call_impl
        return forward_call(*input, **kwargs)
      File "/storage/htc/nih-tcga/sc724/conda/synergy/lib/python3.8/site-packages/chemicalx/models/d                                                        eepdds.py", line 176, in forward
        features_left = self._forward_molecules(molecules_left)
      File "/storage/htc/nih-tcga/sc724/conda/synergy/lib/python3.8/site-packages/chemicalx/models/d                                                        eepdds.py", line 158, in _forward_molecules
        features = self.drug_conv(molecules, molecules.data_dict["node_feature"])["node_feature"]
    KeyError: 'node_feature'
    
    opened by cshukai 7
  • Implement DeepDDS

    Implement DeepDDS

    Closes #19

    Adds the DeepDDS model implementation

    • [ ] Code passes all tests
    • [x] Unit tests provided for these changes
    • [x] Documentation and docstrings added for these changes

    Changes

    • Add DeepDDS
    • Add new file, deepdds_examples.py containing an example
    model 
    opened by kkaris 7
  • Add compatibility layer for `PackedGraph`

    Add compatibility layer for `PackedGraph`

    Summary

    This PR adds a compatibility layer for the packed graph class from torch drug while we're waiting for an upstream fix (https://github.com/DeepGraphLearning/torchdrug/pull/70). This layer makes sure there's a to() function that takes a device, as we usually expect torch stuff to do.

    • [x] Unit tests provided for these changes
    • [x] Documentation and docstrings added for these changes using the sphinx style

    Changes

    • Add a new module chemicalx.compat
    • Implement a subclass of torchdrug.data.PackedGraph that implements the to() function
    • Implement subclass of torchdrug.data.Graph that uses the monkey patched PackedGraph when called in chemicalx.data.drugfeatureset
    opened by cthoyt 6
  • MHCADDI model

    MHCADDI model

    Closes #13

    Summary

    Please provide a high-level summary of the changes for the changes and notes for the reviewers

    • [x] Unit tests provided for these changes
    • [x] Documentation and docstrings added for these changes using the sphinx style

    Changes

    ! This is a draft, the model still need a bit of refactoring, documentation etc

    model 
    opened by sebastiandro 6
  • Provide base class for dataset loaders

    Provide base class for dataset loaders

    Summary

    This PR abstracts the essential components of the dataset loader into a base class to allow for future implementations of eager datasets (e.g., all parts of the dataset are already in memory) and for other lazy local dataset loaders.

    • [x] Code passes all tests
    • [x] Unit tests provided for these changes
    • [x] Documentation and docstrings added for these changes

    Changes

    • Create abstract base class with unimplemented methods for getting drugs, contexts, and labeled triples
    • Rename mid-level class to RemoteDatasetLoader

    Next steps

    The following shows an implementation of an eager dataset, which might be more useful for local datasets.

    @dataclass
    class EagerDatasetLoader(DatasetLoader):
        """An eager dataset."""
    
        context_feature_set: ContextFeatureSet
        drug_feature_set: DrugFeatureSet
        labeled_triples: LabeledTriples
    
        def get_labeled_triples(self) -> LabeledTriples:
            """Get the labeled triples file from the storage."""
            return self.labeled_triples
    
        def get_context_features(self) -> ContextFeatureSet:
            """Get the context feature set."""
            return self.context_feature_set
    
        def get_drug_features(self):
            """Get the drug feature set."""
            return self.drug_feature_set
    
    opened by cthoyt 6
  • Is this repo dead? Improve communication of its status

    Is this repo dead? Improve communication of its status

    I'm under the impression that AstraZeneca isn't allocating resources to maintaining this repository or answering questions. Is this correct?

    I don't feel comfortable answering questions or maintaining this as long as it lives in the AstraZeneca namespace and I'm not being paid for consulting.

    I don't recall anyone else being active in the repository besides minor model-specific contributions pre-publication. If it's the case that AZ doesn't have any plans for this, then I think we should minimally put a notice on the README saying so and also potentially archive this repository.

    opened by cthoyt 0
  • Inconsistent labels in DrugCombDB

    Inconsistent labels in DrugCombDB

    Hi , it looks like there are a few drug pairs within the same context are labelled inconsistently . For example , drug 59691338 and drug 11960529 in EFM192B.

    opened by cshukai 0
  • Incorporate various dataset splits

    Incorporate various dataset splits

    I also have one suggestion for future updates of this library perhaps. The current dataloaders, if I'm not mistaken, are not considering the different dataset split strategies. Recent works have highlighted the importance of evaluations on different dataset splits, e.g. split pairs, split drugs, split cell lines (for synergy), etc. It would be great to see this library also having such features.

    opened by jasperhyp 1
  • How are the methods implemented outside of the domain they are designed for?

    How are the methods implemented outside of the domain they are designed for?

    For example, DeepSynergy and MatchMaker are requiring cell line information, and they are both implemented in the DrugBankDDI & TWOSIDES benchmarks where no cell line information is available at all (and TWOSIDES is even at the patient level), with DS reaching the highest performance among all methods. What then was the "cell line gene expression" component in both methods replaced within those tasks? Also, does this ensure a fair comparison?

    opened by jasperhyp 1
  • Tensor's device mismatch

    Tensor's device mismatch

    Hi! I have found a bug during the training of the caster model. It was caused by the torch.eye manipulation, simply it did not specify the device. When the Cuda is available, torch.eye will create the tensor on the CPU while the whole model is on the GPU.

    opened by hzcheney 3
Releases(v0.1.0)
  • v0.1.0(Feb 9, 2022)

    🚀 What's Changed

    Models

    • Implement MatchMaker by @andrejlamov in https://github.com/AstraZeneca/chemicalx/pull/67
    • Implement GCN-BMP by @mughetto in https://github.com/AstraZeneca/chemicalx/pull/71
    • Implement DeepDrug by @kajocina in https://github.com/AstraZeneca/chemicalx/pull/68
    • Implement DeepDDI by @hzcheney in https://github.com/AstraZeneca/chemicalx/pull/63
    • Implement CASTER by @andriy-nikolov in https://github.com/AstraZeneca/chemicalx/pull/73
    • Implement MHCADDI by @sebastiandro in https://github.com/AstraZeneca/chemicalx/pull/74
    • Implement DeepDDS by @kkaris in https://github.com/AstraZeneca/chemicalx/pull/53
    • Implement SSIDDI by @YuWVandy in https://github.com/AstraZeneca/chemicalx/pull/77
    • Implement DeepDDS and CASTER defaults and remove DeepDDS Softmax bug by @benedekrozemberczki in https://github.com/AstraZeneca/chemicalx/pull/81
    • Implement MRGNN by @benedekrozemberczki in https://github.com/AstraZeneca/chemicalx/pull/82
    • Simplify existing models by @cthoyt in https://github.com/AstraZeneca/chemicalx/pull/69
    • Clean up models and provide abstractions by @cthoyt in https://github.com/AstraZeneca/chemicalx/pull/83

    💾 Data Cleaning

    • Clean up DrugBank and TWOSIDES importers by @cthoyt in https://github.com/AstraZeneca/chemicalx/pull/57
    • Add additional datasets by @cthoyt in https://github.com/AstraZeneca/chemicalx/pull/61

    🤖 Design

    • Provide base class for dataset loaders by @cthoyt in https://github.com/AstraZeneca/chemicalx/pull/59
    • Move back the BatchGenerator to the data namespace. by @benedekrozemberczki in https://github.com/AstraZeneca/chemicalx/pull/80

    🏠 House keeping

    • Black update conformity by @benedekrozemberczki in https://github.com/AstraZeneca/chemicalx/pull/66
    • Remove check box that's automated with CI by @cthoyt in https://github.com/AstraZeneca/chemicalx/pull/64
    • Standardize documentation style with darglint by @cthoyt in https://github.com/AstraZeneca/chemicalx/pull/70
    • Update citations and add additional testing by @cthoyt in https://github.com/AstraZeneca/chemicalx/pull/72
    • New release updates, citation modification and correcting paper references by @benedekrozemberczki in https://github.com/AstraZeneca/chemicalx/pull/85

    New Contributors

    • @andrejlamov made their first contribution in https://github.com/AstraZeneca/chemicalx/pull/67
    • @kajocina made their first contribution in https://github.com/AstraZeneca/chemicalx/pull/68
    • @mughetto made their first contribution in https://github.com/AstraZeneca/chemicalx/pull/71
    • @hzcheney made their first contribution in https://github.com/AstraZeneca/chemicalx/pull/63
    • @andriy-nikolov made their first contribution in https://github.com/AstraZeneca/chemicalx/pull/73
    • @kkaris made their first contribution in https://github.com/AstraZeneca/chemicalx/pull/53
    • @YuWVandy made their first contribution in https://github.com/AstraZeneca/chemicalx/pull/77
    • @sebastiandro made their first contribution in https://github.com/AstraZeneca/chemicalx/pull/74

    Full Changelog: https://github.com/AstraZeneca/chemicalx/compare/v0.0.9...v0.1.0

    Source code(tar.gz)
    Source code(zip)
  • v0.0.9(Jan 21, 2022)

    What's Changed

    • Re-enable flake8 check by @cthoyt in https://github.com/AstraZeneca/chemicalx/pull/26
    • Remove circular imports by @benedekrozemberczki in https://github.com/AstraZeneca/chemicalx/pull/31
    • Cleanup testing configuration by @cthoyt in https://github.com/AstraZeneca/chemicalx/pull/33
    • Add more flake8 checks by @cthoyt in https://github.com/AstraZeneca/chemicalx/pull/35
    • Remove DPDDI and AUDNNSynergy by @benedekrozemberczki in https://github.com/AstraZeneca/chemicalx/pull/36
    • Update documentation build by @cthoyt in https://github.com/AstraZeneca/chemicalx/pull/38
    • Add unified training and evaluation pipeline by @cthoyt in https://github.com/AstraZeneca/chemicalx/pull/32
    • Read the docs deployment fix. by @benedekrozemberczki in https://github.com/AstraZeneca/chemicalx/pull/39
    • Adding Default Read The Docs Path by @benedekrozemberczki in https://github.com/AstraZeneca/chemicalx/pull/40
    • Adding the autodoc hinting by @benedekrozemberczki in https://github.com/AstraZeneca/chemicalx/pull/41
    • DeepCCI removal and out channel parameters by @benedekrozemberczki in https://github.com/AstraZeneca/chemicalx/pull/43
    • Update CI by @cthoyt in https://github.com/AstraZeneca/chemicalx/pull/44
    • Update README python code comments and remove DeepCCI by @benedekrozemberczki in https://github.com/AstraZeneca/chemicalx/pull/45
    • Add additional model tests by @cthoyt in https://github.com/AstraZeneca/chemicalx/pull/46
    • Adding DrugBank DDI and Two Sides. by @benedekrozemberczki in https://github.com/AstraZeneca/chemicalx/pull/48
    • Fix unit tests for DDI and TwoSides by @benedekrozemberczki in https://github.com/AstraZeneca/chemicalx/pull/51
    • Expose dataset properties by @cthoyt in https://github.com/AstraZeneca/chemicalx/pull/52
    • Reorganize batching by @cthoyt in https://github.com/AstraZeneca/chemicalx/pull/54
    • Clean up feature sets and labels flag by @cthoyt in https://github.com/AstraZeneca/chemicalx/pull/55
    • ChemicalX 0.0.9 Release by @benedekrozemberczki in https://github.com/AstraZeneca/chemicalx/pull/56

    Full Changelog: https://github.com/AstraZeneca/chemicalx/compare/v0.0.8...v0.0.9

    Source code(tar.gz)
    Source code(zip)
  • v0.0.8(Jan 14, 2022)

    What's Changed

    • Add Dataset Resolver around Dataset Loader Class by @cthoyt in https://github.com/AstraZeneca/chemicalx/pull/24
    • DeepSynergy and EPGCN-DS by @benedekrozemberczki in https://github.com/AstraZeneca/chemicalx/pull/27

    Full Changelog: https://github.com/AstraZeneca/chemicalx/compare/v0.0.7...v0.0.8

    Source code(tar.gz)
    Source code(zip)
  • v0.0.7(Jan 13, 2022)

  • v0.0.6(Jan 12, 2022)

    What's Changed

    • Add base model and implement model class resolution by @cthoyt
    • Batch generators
    • Batch class

    New Contributors

    • @cthoyt made their first contribution in https://github.com/AstraZeneca/chemicalx/pull/18

    Full Changelog: https://github.com/AstraZeneca/chemicalx/compare/v0.0.5...v0.0.6

    Source code(tar.gz)
    Source code(zip)
  • v0.0.5(Jan 11, 2022)

    • Adds Data Loaders for DrugComb and DrugCombDB 👾 🤖 🎃
    • Drug Feature Set for feature storage 👾 🤖 🎃
    • Labeled Triples 👾 🤖 🎃
    Source code(tar.gz)
    Source code(zip)
  • v0.0.4(Jan 10, 2022)

    • Integrates DrugCombDB 🧬 💊
    • Integrated DrugComb 🧬 💊
    • Defines ContextFeatureSets with the class methods 🧬 💊
    • Add tests for ContextFeatureSets 🧬 💊
    Source code(tar.gz)
    Source code(zip)
  • v_00003(Dec 23, 2021)

  • v_00002(Dec 20, 2021)

  • v_00001(Dec 15, 2021)

Owner
AstraZeneca
Data and AI: Unlocking new science insights
AstraZeneca
A Python framework for developing parallelized Computational Fluid Dynamics software to solve the hyperbolic 2D Euler equations on distributed, multi-block structured grids.

pyHype: Computational Fluid Dynamics in Python pyHype is a Python framework for developing parallelized Computational Fluid Dynamics software to solve

Mohamed Khalil 21 Nov 22, 2022
Pytorch implementation for reproducing StackGAN_v2 results in the paper StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networks

StackGAN-v2 StackGAN-v1: Tensorflow implementation StackGAN-v1: Pytorch implementation Inception score evaluation Pytorch implementation for reproduci

Han Zhang 809 Dec 16, 2022
A Game-Theoretic Perspective on Risk-Sensitive Reinforcement Learning

Officile code repository for "A Game-Theoretic Perspective on Risk-Sensitive Reinforcement Learning"

Mathieu Godbout 1 Nov 19, 2021
CN24 is a complete semantic segmentation framework using fully convolutional networks

Build status: master (production branch): develop (development branch): Welcome to the CN24 GitHub repository! CN24 is a complete semantic segmentatio

Computer Vision Group Jena 123 Jul 14, 2022
Compressed Video Action Recognition

Compressed Video Action Recognition Chao-Yuan Wu, Manzil Zaheer, Hexiang Hu, R. Manmatha, Alexander J. Smola, Philipp Krähenbühl. In CVPR, 2018. [Proj

Chao-Yuan Wu 479 Dec 26, 2022
SustainBench: Benchmarks for Monitoring the Sustainable Development Goals with Machine Learning

Datasets | Website | Raw Data | OpenReview SustainBench: Benchmarks for Monitoring the Sustainable Development Goals with Machine Learning Christopher

67 Dec 17, 2022
The dynamics of representation learning in shallow, non-linear autoencoders

The dynamics of representation learning in shallow, non-linear autoencoders The package is written in python and uses the pytorch implementation to ML

Maria Refinetti 4 Jun 08, 2022
Official implementations of PSENet, PAN and PAN++.

News (2021/11/03) Paddle implementation of PAN, see Paddle-PANet. Thanks @simplify23. (2021/04/08) PSENet and PAN are included in MMOCR. Introduction

395 Dec 14, 2022
World Models with TensorFlow 2

World Models This repo reproduces the original implementation of World Models. This implementation uses TensorFlow 2.2. Docker The easiest way to hand

Zac Wellmer 234 Nov 30, 2022
PyTorch implementation of "MLP-Mixer: An all-MLP Architecture for Vision" Tolstikhin et al. (2021)

mlp-mixer-pytorch PyTorch implementation of "MLP-Mixer: An all-MLP Architecture for Vision" Tolstikhin et al. (2021) Usage import torch from mlp_mixer

isaac 27 Jul 09, 2022
Repository for "Space-Time Correspondence as a Contrastive Random Walk" (NeurIPS 2020)

Space-Time Correspondence as a Contrastive Random Walk This is the repository for Space-Time Correspondence as a Contrastive Random Walk, published at

A. Jabri 239 Dec 27, 2022
Rasterize with the least efforts for researchers.

utils3d Rasterize and do image-based 3D transforms with the least efforts for researchers. Based on numpy and OpenGL. It could be helpful when you wan

Ruicheng Wang 8 Dec 15, 2022
Tensorflow Implementation of the paper "Spectral Normalization for Generative Adversarial Networks" (ICML 2017 workshop)

tf-SNDCGAN Tensorflow implementation of the paper "Spectral Normalization for Generative Adversarial Networks" (https://www.researchgate.net/publicati

Nhat M. Nguyen 248 Nov 25, 2022
Neural Module Network for VQA in Pytorch

Neural Module Network (NMN) for VQA in Pytorch Note: This is NOT an official repository for Neural Module Networks. NMN is a network that is assembled

Harsh Trivedi 111 Nov 24, 2022
codes for paper Combining Dynamic Local Context Focus and Dependency Cluster Attention for Aspect-level sentiment classification

DLCF-DCA codes for paper Combining Dynamic Local Context Focus and Dependency Cluster Attention for Aspect-level sentiment classification. submitted t

15 Aug 30, 2022
Training DALL-E with volunteers from all over the Internet using hivemind and dalle-pytorch (NeurIPS 2021 demo)

Training DALL-E with volunteers from all over the Internet This repository is a part of the NeurIPS 2021 demonstration "Training Transformers Together

<a href=[email protected]"> 19 Dec 13, 2022
Model Zoo for AI Model Efficiency Toolkit

We provide a collection of popular neural network models and compare their floating point and quantized performance.

Qualcomm Innovation Center 137 Jan 03, 2023
Pytorch and Torch testing code of CartoonGAN

CartoonGAN-Test-Pytorch-Torch Pytorch and Torch testing code of CartoonGAN [Chen et al., CVPR18]. With the released pretrained models by the authors,

Yijun Li 642 Dec 27, 2022
Code for "Long-tailed Distribution Adaptation"

Long-tailed Distribution Adaptation (Accepted in ACM MM2021) This project is built upon BBN. Installation pip install -r requirements.txt Usage Traini

Zhiliang Peng 10 May 18, 2022
Coarse implement of the paper "A Simultaneous Denoising and Dereverberation Framework with Target Decoupling", On DNS-2020 dataset, the DNSMOS of first stage is 3.42 and second stage is 3.47.

SDDNet Coarse implement of the paper "A Simultaneous Denoising and Dereverberation Framework with Target Decoupling", On DNS-2020 dataset, the DNSMOS

Cyril Lv 43 Nov 21, 2022