💡 Learnergy is a Python library for energy-based machine learning models.

Overview

Learnergy: Energy-based Machine Learners

Latest release DOI Build status Open issues License

Welcome to Learnergy.

Did you ever reach a bottleneck in your computational experiments? Are you tired of implementing your own techniques? If yes, Learnergy is the real deal! This package provides an easy-to-go implementation of energy-based machine learning algorithms. From datasets to fully-customizable models, from internal functions to external communications, we will foster all research related to energy-based machine learning.

Use Learnergy if you need a library or wish to:

  • Create your energy-based machine learning algorithm;
  • Design or use pre-loaded learners;
  • Mix-and-match different strategies to solve your problem;
  • Because it is incredible to learn things.

Read the docs at learnergy.readthedocs.io.

Learnergy is compatible with: Python 3.6+.


Package guidelines

  1. The very first information you need is in the very next section.
  2. Installing is also easy if you wish to read the code and bump yourself into, follow along.
  3. Note that there might be some additional steps in order to use our solutions.
  4. If there is a problem, please do not hesitate, call us.

Citation

If you use Learnergy to fulfill any of your needs, please cite us:

@misc{roder2020learnergy,
    title={Learnergy: Energy-based Machine Learners},
    author={Mateus Roder and Gustavo Henrique de Rosa and João Paulo Papa},
    year={2020},
    eprint={2003.07443},
    archivePrefix={arXiv},
    primaryClass={cs.LG}
}

Getting started: 60 seconds with Learnergy

First of all. We have examples. Yes, they are commented. Just browse to examples/, choose your subpackage, and follow the example. We have high-level examples for most of the tasks we could think.

Alternatively, if you wish to learn even more, please take a minute:

Learnergy is based on the following structure, and you should pay attention to its tree:

- learnergy
    - core
        - dataset
        - model
    - math
        - metrics
        - scale
    - models
        - bernoulli
            - conv_rbm
            - discriminative_rbm
            - dropout_rbm
            - e_dropout_rbm
            - rbm
        - deep
            - conv_dbn
            - dbn
            - residual_dbn
        - extra
            - sigmoid_rbm
        - gaussian
            - gaussian_conv_rbm        
            - gaussian_rbm
    - utils
        - constants
        - exception
        - logging
    - visual
        - convergence
        - image
        - tensor

Core

Core is the core. Essentially, it is the parent of everything. You should find parent classes defining the basis of our structure. They should provide variables and methods that will help to construct other modules.

Math

Just because we are computing stuff, it does not means that we do not need math. Math is the mathematical package, containing low-level math implementations. From random numbers to distributions generation, you can find your needs on this module.

Models

This is the heart. All models are declared and implemented here. We will offer you the most fantastic implementation of everything we are working with. Please take a closer look into this package.

Utils

This is a utility package. Common things shared across the application should be implemented here. It is better to implement once and use as you wish than re-implementing the same thing over and over again.

Visual

Everyone needs images and plots to help visualize what is happening, correct? This package will provide every visual-related method for you. Check a specific image, your fitness function convergence, plot reconstructions, weights, and much more.


Installation

We believe that everything has to be easy. Not tricky or daunting, Learnergy will be the one-to-go package that you will need, from the very first installation to the daily-tasks implementing needs. If you may just run the following under your most preferred Python environment (raw, conda, virtualenv, whatever):

pip install learnergy

Alternatively, if you prefer to install the bleeding-edge version, please clone this repository and use:

pip install -e .

Environment configuration

Note that sometimes, there is a need for additional implementation. If needed, from here, you will be the one to know all of its details.

Ubuntu

No specific additional commands needed.

Windows

No specific additional commands needed.

MacOS

No specific additional commands needed.


Support

We know that we do our best, but it is inevitable to acknowledge that we make mistakes. If you ever need to report a bug, report a problem, talk to us, please do so! We will be available at our bests at this repository or [email protected] and [email protected].


Comments
  • Naming of models' class attributes

    Naming of models' class attributes

    The variable names used in the getters and setters of each model class are different than what is initialized in the constructor.

    Screen Shot 2021-06-14 at 7 37 42 PM

    Note that the name 'W' is used in init, but '_W' is used as the variable name in the getters and setters, both of which have the same name as the variable initialized in init 'W'. This issue is the same for all member variables. I have tested the DBN and GaussianVarianceRBM subclasses as well, and it looks like the issue persists across all other subclasses.

    Screen Shot 2021-06-14 at 7 38 32 PM
    • OS: CentOS 7.8
    • Virtual Environment conda 4.10.1
    • Python Version 3.8

    This causes issues when trying to make copies of classes for things like multi-GPU training via torch.nn.DistributedDataParallel

    bug 
    opened by nlahaye 14
  • Probabilistic Max Pooling

    Probabilistic Max Pooling

    Hi Gustavo!

    I hope you are doing well!

    I was wondering if you had looked into / planned to add probabilistic max-pooling, as descibed in: H. Lee, et al., Convolutional Deep Belief Networksfor Scalable Unsupervised Learning of Hierarchical Representations Proceedings of the 26th annual international conference on machine learning (2009).

    I am happy to help, but figured it would be best to consult you first.

    Thanks! Nick

    enhancement 
    opened by nlahaye 7
  • probability bug

    probability bug

    When I use GaussianRBM to run rbm_classification.py on GPU, these errors appear.

    11%|█ | 51/469 [00:01<00:07, 58.24it/s]C:/cb/pytorch_1000000000000/work/aten/src\ATen/native/cuda/DistributionTemplates.h:591: block: [6,0,0], thread: [416,0,0] Assertion 0 <= p4 && p4 <= 1 failed. C:/cb/pytorch_1000000000000/work/aten/src\ATen/native/cuda/DistributionTemplates.h:591: block: [6,0,0], thread: [417,0,0] Assertion 0 <= p4 && p4 <= 1 failed. C:/cb/pytorch_1000000000000/work/aten/src\ATen/native/cuda/DistributionTemplates.h:591: block: [6,0,0], thread: [418,0,0] Assertion 0 <= p4 && p4 <= 1 failed. C:/cb/pytorch_1000000000000/work/aten/src\ATen/native/cuda/DistributionTemplates.h:591: block: [6,0,0], thread: [419,0,0] Assertion 0 <= p4 && p4 <= 1 failed. C:/cb/pytorch_1000000000000/work/aten/src\ATen/native/cuda/DistributionTemplates.h:591: block: [6,0,0], thread: [420,0,0] Assertion 0 <= p4 && p4 <= 1 failed. C:/cb/pytorch_1000000000000/work/aten/src\ATen/native/cuda/DistributionTemplates.h:591: block: [6,0,0], thread: [421,0,0] Assertion 0 <= p4 && p4 <= 1 failed. C:/cb/pytorch_1000000000000/work/aten/src\ATen/native/cuda/DistributionTemplates.h:591: block: [6,0,0], thread: [422,0,0] Assertion 0 <= p4 && p4 <= 1 failed. C:/cb/pytorch_1000000000000/work/aten/src\ATen/native/cuda/DistributionTemplates.h:591: block: [6,0,0], thread: [423,0,0] Assertion 0 <= p4 && p4 <= 1 failed. C:/cb/pytorch_1000000000000/work/aten/src\ATen/native/cuda/DistributionTemplates.h:591: block: [6,0,0], thread: [424,0,0] Assertion 0 <= p4 && p4 <= 1 failed. C:/cb/pytorch_1000000000000/work/aten/src\ATen/native/cuda/DistributionTemplates.h:591: block: [6,0,0], thread: [425,0,0] Assertion 0 <= p4 && p4 <= 1 failed. C:/cb/pytorch_1000000000000/work/aten/src\ATen/native/cuda/DistributionTemplates.h:591: block: [6,0,0], thread: [426,0,0] Assertion 0 <= p4 && p4 <= 1 failed. C:/cb/pytorch_1000000000000/work/aten/src\ATen/native/cuda/DistributionTemplates.h:591: block: [6,0,0], thread: [427,0,0] Assertion 0 <= p4 && p4 <= 1 failed. C:/cb/pytorch_1000000000000/work/aten/src\ATen/native/cuda/DistributionTemplates.h:591: block: [6,0,0], thread: [428,0,0] Assertion 0 <= p4 && p4 <= 1 failed. C:/cb/pytorch_1000000000000/work/aten/src\ATen/native/cuda/DistributionTemplates.h:591: block: [6,0,0], thread: [429,0,0] Assertion 0 <= p4 && p4 <= 1 failed. C:/cb/pytorch_1000000000000/work/aten/src\ATen/native/cuda/DistributionTemplates.h:591: block: [6,0,0], thread: [430,0,0] Assertion 0 <= p4 && p4 <= 1 failed. C:/cb/pytorch_1000000000000/work/aten/src\ATen/native/cuda/DistributionTemplates.h:591: block: [6,0,0], thread: [431,0,0] Assertion 0 <= p4 && p4 <= 1 failed. C:/cb/pytorch_1000000000000/work/aten/src\ATen/native/cuda/DistributionTemplates.h:591: block: [6,0,0], thread: [432,0,0] Assertion 0 <= p4 && p4 <= 1 failed. C:/cb/pytorch_1000000000000/work/aten/src\ATen/native/cuda/DistributionTemplates.h:591: block: [6,0,0], thread: [433,0,0] Assertion 0 <= p4 && p4 <= 1 failed. C:/cb/pytorch_1000000000000/work/aten/src\ATen/native/cuda/DistributionTemplates.h:591: block: [6,0,0], thread: [434,0,0] Assertion 0 <= p4 && p4 <= 1 failed. C:/cb/pytorch_1000000000000/work/aten/src\ATen/native/cuda/DistributionTemplates.h:591: block: [6,0,0], thread: [435,0,0] Assertion 0 <= p4 && p4 <= 1 failed. C:/cb/pytorch_1000000000000/work/aten/src\ATen/native/cuda/DistributionTemplates.h:591: block: [6,0,0], thread: [436,0,0] Assertion 0 <= p4 && p4 <= 1 failed. C:/cb/pytorch_1000000000000/work/aten/src\ATen/native/cuda/DistributionTemplates.h:591: block: [6,0,0], thread: [437,0,0] Assertion 0 <= p4 && p4 <= 1 failed. C:/cb/pytorch_1000000000000/work/aten/src\ATen/native/cuda/DistributionTemplates.h:591: block: [6,0,0], thread: [438,0,0] Assertion 0 <= p4 && p4 <= 1 failed. C:/cb/pytorch_1000000000000/work/aten/src\ATen/native/cuda/DistributionTemplates.h:591: block: [6,0,0], thread: [439,0,0] Assertion 0 <= p4 && p4 <= 1 failed. C:/cb/pytorch_1000000000000/work/aten/src\ATen/native/cuda/DistributionTemplates.h:591: block: [6,0,0], thread: [440,0,0] Assertion 0 <= p4 && p4 <= 1 failed. C:/cb/pytorch_1000000000000/work/aten/src\ATen/native/cuda/DistributionTemplates.h:591: block: [6,0,0], thread: [441,0,0] Assertion 0 <= p4 && p4 <= 1 failed. C:/cb/pytorch_1000000000000/work/aten/src\ATen/native/cuda/DistributionTemplates.h:591: block: [6,0,0], thread: [442,0,0] Assertion 0 <= p4 && p4 <= 1 failed. C:/cb/pytorch_1000000000000/work/aten/src\ATen/native/cuda/DistributionTemplates.h:591: block: [6,0,0], thread: [443,0,0] Assertion 0 <= p4 && p4 <= 1 failed. C:/cb/pytorch_1000000000000/work/aten/src\ATen/native/cuda/DistributionTemplates.h:591: block: [6,0,0], thread: [444,0,0] Assertion 0 <= p4 && p4 <= 1 failed. C:/cb/pytorch_1000000000000/work/aten/src\ATen/native/cuda/DistributionTemplates.h:591: block: [6,0,0], thread: [445,0,0] Assertion 0 <= p4 && p4 <= 1 failed. C:/cb/pytorch_1000000000000/work/aten/src\ATen/native/cuda/DistributionTemplates.h:591: block: [6,0,0], thread: [446,0,0] Assertion 0 <= p4 && p4 <= 1 failed. C:/cb/pytorch_1000000000000/work/aten/src\ATen/native/cuda/DistributionTemplates.h:591: block: [6,0,0], thread: [447,0,0] Assertion 0 <= p4 && p4 <= 1 failed.

    RuntimeError: CUDA error: device-side assert triggered

    But if I run it on cpu, the error while like this: RuntimeError: Expected p_in >= 0 && p_in <= 1 to be true, but got false.

    It seems like the function hidden_sampling dosen't run correctly.

    bug question 
    opened by kyyongh 6
  • nan in probs

    nan in probs

    Hello,

    Thank you very much for developing this superb library!!

    I believe that I found an issue, but I am not able to find the root cause.

    From time to time I receive this error:

    Traceback (most recent call last): File "/Users/supermario/LNIssue/run_rbm.py", line 26, in epochs=1000000) File "/Users/supermario/LNIssue/venv/lib/python3.7/site-packages/learnergy/models/bernoulli/rbm.py", line 495, in fit _, _, _, _, visible_states = self.gibbs_sampling(samples) File "/Users/supermario/LNIssue/venv/lib/python3.7/site-packages/learnergy/models/bernoulli/rbm.py", line 379, in gibbs_sampling neg_hidden_states, True) File "/Users/supermario/LNIssue/venv/lib/python3.7/site-packages/learnergy/models/bernoulli/rbm.py", line 352, in visible_sampling states = torch.bernoulli(probs) RuntimeError: Expected p_in >= 0 && p_in <= 1 to be true, but got false. (Could this error message be improved? If so, please report an enhancement request to PyTorch.)

    Here is the code to reproduce the error:

    import numpy as np import torch from torch.utils.data import Dataset from learnergy.models.bernoulli.rbm import RBM

    np.random.seed(16) torch.manual_seed(16)

    class CustomDataset(Dataset):

    def __init__(self, custom_data):
        self.custom_data = torch.from_numpy(custom_data)
        self.dummy_y = torch.from_numpy(np.array([0.0]))
    
    def __getitem__(self, index):
        return self.custom_data[index], self.dummy_y[0]
    
    def __len__(self):
        return self.custom_data.shape[0]
    

    rbm = RBM(n_visible=32, n_hidden=64, steps=1, learning_rate=0.0001, momentum=0.9, decay=0.00001, temperature=0, use_gpu=False)

    data = np.random.choice(a=[False, True], size=(5755, 32)).astype(np.float32) data_train = CustomDataset(data)

    rbm.fit(dataset=data_train, batch_size=20, epochs=1000000)

    And requirements: astroid==2.8.4 attrs==21.2.0 coverage==6.1.1 cycler==0.11.0 imageio==2.10.3 importlib-metadata==4.8.2 iniconfig==1.1.1 isort==5.10.1 kiwisolver==1.3.2 lazy-object-proxy==1.6.0 learnergy==1.1.1 matplotlib==3.4.3 mccabe==0.6.1 networkx==2.6.3 numpy==1.21.4 packaging==21.2 Pillow==8.4.0 platformdirs==2.4.0 pluggy==1.0.0 py==1.11.0 pylint==2.11.1 pyparsing==2.4.7 pytest==6.2.5 python-dateutil==2.8.2 PyWavelets==1.2.0 scikit-image==0.18.3 scipy==1.7.2 six==1.16.0 tifffile==2021.11.2 toml==0.10.2 torch==1.9.0 tqdm==4.62.3 typed-ast==1.4.3 typing-extensions==3.10.0.2 wrapt==1.13.3 zipp==3.6.0

    The error should appear at epoch 221/1000000.

    If I add the following torch.nan_to_num in visible_sampling() method, then the error is not present anymore.

    probs = torch.nan_to_num(probs, nan=0.0) Sampling current states states = torch.bernoulli(probs)

    macosx, python 3.7.0

    Thank you! Please let me know if you need additional info.

    bug 
    opened by citizenn19 4
  • [REG] Basis for classification architecture

    [REG] Basis for classification architecture

    Regarding the basic Bernoulli RBM for classification, could I check what is the basis of your implementation? From what I can tell, the training is broken up in two sections:

    1. RBM will perform unsupervised learning to minimize energy (RBM::fit), basically like a feature extractor.
    2. The whole model is then considered as a 2-layer neural network with a sigmoid layer (RBM::forward) and linear transformation layer.

    So, it seems like the RBM is just used as an initializer for the neural network.

    In addition, I noticed that RBM::fit's epoch defaults to 1. Increasing the epoch number does not seem to improve performance. Does this mean that there is no use in training the RBM?

    Lastly, was there any prior work that implemented RBM in this way, or is this your original idea? Are there any published results or study into this architecture? Thank you!

    general 
    opened by shotnothing 3
  • [REG] The purpose of applying Softplus function in RBM

    [REG] The purpose of applying Softplus function in RBM

    I found in the comments of file learnergy/learnergy/models/bernoulli/rbm.py (line 401), you said

    Creating a Softplus function for numerical stability

    The form of Softplus function is f(x) = log(1+exp(x)), which fits the form of the log term of marginal energy of RBM

    E(v)= \sum_i a_i v_i + \sum_j ( log( 1 + exp( \sum_i v_i \lambda_{ij} +b_j ) ) ).

    So I suppose the Softplus function is not used to ensure the numerical stability, but to calculate the marginal energy. I am a beginner to RBM, if I have any wrong perceptions, please point it out.

    Thank you!

    general 
    opened by YemingMeng 3
  • Bump sphinx from 5.2.3 to 5.3.0

    Bump sphinx from 5.2.3 to 5.3.0

    Bumps sphinx from 5.2.3 to 5.3.0.

    Release notes

    Sourced from sphinx's releases.

    v5.3.0

    Changelog: https://www.sphinx-doc.org/en/master/changes.html

    Changelog

    Sourced from sphinx's changelog.

    Release 5.3.0 (released Oct 16, 2022)

    • #10759: LaTeX: add :confval:latex_table_style and support the 'booktabs', 'borderless', and 'colorrows' styles. (thanks to Stefan Wiehler for initial pull requests #6666, #6671)
    • #10840: One can cross-reference including an option value like :option:`--module=foobar```, :option:--module[=foobar]``` or ``:option:--module foobar```. Patch by Martin Liska.
    • #10881: autosectionlabel: Record the generated section label to the debug log.
    • #10268: Correctly URI-escape image filenames.
    • #10887: domains: Allow sections in all the content of all object description directives (e.g. :rst:dir:py:function). Patch by Adam Turner
    Commits

    Dependabot compatibility score

    Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.


    Dependabot commands and options

    You can trigger Dependabot actions by commenting on this PR:

    • @dependabot rebase will rebase this PR
    • @dependabot recreate will recreate this PR, overwriting any edits that have been made to it
    • @dependabot merge will merge this PR after your CI passes on it
    • @dependabot squash and merge will squash and merge this PR after your CI passes on it
    • @dependabot cancel merge will cancel a previously requested merge and block automerging
    • @dependabot reopen will reopen this PR if it is closed
    • @dependabot close will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually
    • @dependabot ignore this major version will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)
    • @dependabot ignore this minor version will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)
    • @dependabot ignore this dependency will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)
    opened by dependabot[bot] 2
  • Bump sphinx from 5.2.3 to 5.3.0 in /docs

    Bump sphinx from 5.2.3 to 5.3.0 in /docs

    Bumps sphinx from 5.2.3 to 5.3.0.

    Release notes

    Sourced from sphinx's releases.

    v5.3.0

    Changelog: https://www.sphinx-doc.org/en/master/changes.html

    Changelog

    Sourced from sphinx's changelog.

    Release 5.3.0 (released Oct 16, 2022)

    • #10759: LaTeX: add :confval:latex_table_style and support the 'booktabs', 'borderless', and 'colorrows' styles. (thanks to Stefan Wiehler for initial pull requests #6666, #6671)
    • #10840: One can cross-reference including an option value like :option:`--module=foobar```, :option:--module[=foobar]``` or ``:option:--module foobar```. Patch by Martin Liska.
    • #10881: autosectionlabel: Record the generated section label to the debug log.
    • #10268: Correctly URI-escape image filenames.
    • #10887: domains: Allow sections in all the content of all object description directives (e.g. :rst:dir:py:function). Patch by Adam Turner
    Commits

    Dependabot compatibility score

    Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.


    Dependabot commands and options

    You can trigger Dependabot actions by commenting on this PR:

    • @dependabot rebase will rebase this PR
    • @dependabot recreate will recreate this PR, overwriting any edits that have been made to it
    • @dependabot merge will merge this PR after your CI passes on it
    • @dependabot squash and merge will squash and merge this PR after your CI passes on it
    • @dependabot cancel merge will cancel a previously requested merge and block automerging
    • @dependabot reopen will reopen this PR if it is closed
    • @dependabot close will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually
    • @dependabot ignore this major version will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)
    • @dependabot ignore this minor version will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)
    • @dependabot ignore this dependency will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)
    opened by dependabot[bot] 2
  • Gaussian RBM with hidden layer SELU activation

    Gaussian RBM with hidden layer SELU activation

    Hi Gustavo, I hope you are having a great week. Over the last few months, I have made a couple of additions to my fork, and I figured I would share them to see if you found them useful for the base repo. No worries if not!

    The first one was adding Gaussian RBM with hidden layer SELU activation. I have had some success using this model for my research, and figured it may be useful for others.

    In addition to the SELU addition, added boolean flags to indicate whether or not to batch normalize and normalize the input within parent GaussianRBM class.

    The batch normalization is removed for SELU RBM, as it self-normalizes. Also, I use a scaling functionality outside of learnergy for the input, so it would be useful to have the normalization internal to learnergy as an option.

    By default input and batch normalization are turned on, as to not cause issues for other users.

    Thanks! Nick

    opened by nlahaye 2
  • Bump sphinx from 5.2.3 to 6.0.0

    Bump sphinx from 5.2.3 to 6.0.0

    Bumps sphinx from 5.2.3 to 6.0.0.

    Release notes

    Sourced from sphinx's releases.

    v6.0.0

    Changelog: https://www.sphinx-doc.org/en/master/changes.html

    v6.0.0b2

    Changelog: https://www.sphinx-doc.org/en/master/changes.html

    v6.0.0b1

    Changelog: https://www.sphinx-doc.org/en/master/changes.html

    v5.3.0

    Changelog: https://www.sphinx-doc.org/en/master/changes.html

    Changelog

    Sourced from sphinx's changelog.

    Release 6.0.0 (released Dec 29, 2022)

    Dependencies

    • #10468: Drop Python 3.6 support
    • #10470: Drop Python 3.7, Docutils 0.14, Docutils 0.15, Docutils 0.16, and Docutils 0.17 support. Patch by Adam Turner

    Incompatible changes

    • #7405: Removed the jQuery and underscore.js JavaScript frameworks.

      These frameworks are no longer be automatically injected into themes from Sphinx 6.0. If you develop a theme or extension that uses the jQuery, $, or $u global objects, you need to update your JavaScript to modern standards, or use the mitigation below.

      The first option is to use the sphinxcontrib.jquery_ extension, which has been developed by the Sphinx team and contributors. To use this, add sphinxcontrib.jquery to the extensions list in conf.py, or call app.setup_extension("sphinxcontrib.jquery") if you develop a Sphinx theme or extension.

      The second option is to manually ensure that the frameworks are present. To re-add jQuery and underscore.js, you will need to copy jquery.js and underscore.js from the Sphinx repository_ to your static directory, and add the following to your layout.html:

      .. code-block:: html+jinja

      {%- block scripts %} {{ super() }} {%- endblock %}

      .. _sphinxcontrib.jquery: https://github.com/sphinx-contrib/jquery/

      Patch by Adam Turner.

    • #10471, #10565: Removed deprecated APIs scheduled for removal in Sphinx 6.0. See :ref:dev-deprecated-apis for details. Patch by Adam Turner.

    • #10901: C Domain: Remove support for parsing pre-v3 style type directives and roles. Also remove associated configuration variables c_allow_pre_v3 and c_warn_on_allowed_pre_v3. Patch by Adam Turner.

    Features added

    ... (truncated)

    Commits

    Dependabot compatibility score

    Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.


    Dependabot commands and options

    You can trigger Dependabot actions by commenting on this PR:

    • @dependabot rebase will rebase this PR
    • @dependabot recreate will recreate this PR, overwriting any edits that have been made to it
    • @dependabot merge will merge this PR after your CI passes on it
    • @dependabot squash and merge will squash and merge this PR after your CI passes on it
    • @dependabot cancel merge will cancel a previously requested merge and block automerging
    • @dependabot reopen will reopen this PR if it is closed
    • @dependabot close will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually
    • @dependabot ignore this major version will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)
    • @dependabot ignore this minor version will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)
    • @dependabot ignore this dependency will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)
    opened by dependabot[bot] 1
  • Bump sphinx from 5.2.3 to 6.0.0 in /docs

    Bump sphinx from 5.2.3 to 6.0.0 in /docs

    Bumps sphinx from 5.2.3 to 6.0.0.

    Release notes

    Sourced from sphinx's releases.

    v6.0.0

    Changelog: https://www.sphinx-doc.org/en/master/changes.html

    v6.0.0b2

    Changelog: https://www.sphinx-doc.org/en/master/changes.html

    v6.0.0b1

    Changelog: https://www.sphinx-doc.org/en/master/changes.html

    v5.3.0

    Changelog: https://www.sphinx-doc.org/en/master/changes.html

    Changelog

    Sourced from sphinx's changelog.

    Release 6.0.0 (released Dec 29, 2022)

    Dependencies

    • #10468: Drop Python 3.6 support
    • #10470: Drop Python 3.7, Docutils 0.14, Docutils 0.15, Docutils 0.16, and Docutils 0.17 support. Patch by Adam Turner

    Incompatible changes

    • #7405: Removed the jQuery and underscore.js JavaScript frameworks.

      These frameworks are no longer be automatically injected into themes from Sphinx 6.0. If you develop a theme or extension that uses the jQuery, $, or $u global objects, you need to update your JavaScript to modern standards, or use the mitigation below.

      The first option is to use the sphinxcontrib.jquery_ extension, which has been developed by the Sphinx team and contributors. To use this, add sphinxcontrib.jquery to the extensions list in conf.py, or call app.setup_extension("sphinxcontrib.jquery") if you develop a Sphinx theme or extension.

      The second option is to manually ensure that the frameworks are present. To re-add jQuery and underscore.js, you will need to copy jquery.js and underscore.js from the Sphinx repository_ to your static directory, and add the following to your layout.html:

      .. code-block:: html+jinja

      {%- block scripts %} {{ super() }} {%- endblock %}

      .. _sphinxcontrib.jquery: https://github.com/sphinx-contrib/jquery/

      Patch by Adam Turner.

    • #10471, #10565: Removed deprecated APIs scheduled for removal in Sphinx 6.0. See :ref:dev-deprecated-apis for details. Patch by Adam Turner.

    • #10901: C Domain: Remove support for parsing pre-v3 style type directives and roles. Also remove associated configuration variables c_allow_pre_v3 and c_warn_on_allowed_pre_v3. Patch by Adam Turner.

    Features added

    ... (truncated)

    Commits

    Dependabot compatibility score

    Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.


    Dependabot commands and options

    You can trigger Dependabot actions by commenting on this PR:

    • @dependabot rebase will rebase this PR
    • @dependabot recreate will recreate this PR, overwriting any edits that have been made to it
    • @dependabot merge will merge this PR after your CI passes on it
    • @dependabot squash and merge will squash and merge this PR after your CI passes on it
    • @dependabot cancel merge will cancel a previously requested merge and block automerging
    • @dependabot reopen will reopen this PR if it is closed
    • @dependabot close will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually
    • @dependabot ignore this major version will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)
    • @dependabot ignore this minor version will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)
    • @dependabot ignore this dependency will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)
    opened by dependabot[bot] 1
Releases(v1.1.3)
  • v1.1.3(Oct 21, 2022)

    Changelog

    Description

    Welcome to v1.1.3 release.

    In this release, we have added the MaxPooling2D for convolutional models and optimized the training procedure for deeper models, i.e., DBNs. Such an optimization enables the DBN to train without loading all the dataset on the memory for each hidden layer in this phase.

    Please read the docs at: learnergy.readthedocs.io

    Also, stay tuned for our next updates!

    Includes (or changes)

    • learnergy
    Source code(tar.gz)
    Source code(zip)
  • v1.1.2(Apr 26, 2022)

  • v1.1.1(Dec 23, 2020)

    Changelog

    Description

    Welcome to v1.1.1 release.

    In this release, we added the DropConnectRBM and fixed some nasty bugs, as well as improved some unitary tests.

    Please read the docs at: learnergy.readthedocs.io

    Also, stay tuned for our next updates!

    Includes (or changes)

    • models.bernoulli.dropout_rbm
    Source code(tar.gz)
    Source code(zip)
  • v1.1.0(Dec 2, 2020)

    Changelog

    Description

    Welcome to v1.1.0 release.

    In this release, we renamed some packages for a clearer description. Additionally, we have added a GaussianConvRBM class and made some minor adjustments along the package.

    Note that this release might cause incompatibility with previous versions due to some packages being renamed.

    Please read the docs at: learnergy.readthedocs.io

    Also, stay tuned for our next updates!

    Includes (or changes)

    • models
    Source code(tar.gz)
    Source code(zip)
  • v1.0.7(Nov 25, 2020)

  • v1.0.6(Jul 10, 2020)

    Changelog

    Description

    Welcome to v1.0.6 release.

    In this release, we have added a new model, known as Convolutional RBM. Additionally, we have reworked our modules to provide a cleaner environment.

    Please read the docs at: learnergy.readthedocs.io

    Also, stay tuned for our next updates!

    Includes (or changes)

    • learnergy
    Source code(tar.gz)
    Source code(zip)
  • v1.0.5(May 28, 2020)

    Changelog

    Description

    Welcome to v1.0.5 release.

    In this release, we have added a new model, known as Gaussian ReLU RBM. Additionally, we have added progress bars in an attempt to construct a clearer visualization of the training process.

    Please read the docs at: learnergy.readthedocs.io

    Also, stay tuned for our next updates!

    Includes (or changes)

    • learnergy.models.gaussian_rbm
    Source code(tar.gz)
    Source code(zip)
  • v1.0.4(May 7, 2020)

    Changelog

    Description

    Welcome to v1.0.4 release.

    In this release, we have facilitated some classes imports, added the Residual DBN, and corrected some nasty bugs.

    Please read the docs at: learnergy.readthedocs.io

    Also, stay tuned for our next updates!

    Includes (or changes)

    • learnergy
    • learnergy.models.residual_dbn
    Source code(tar.gz)
    Source code(zip)
  • v1.0.3(Mar 31, 2020)

  • v1.0.2(Feb 18, 2020)

    Changelog

    Description

    Welcome to v1.0.2 release.

    In this release, we have rebranded the package to Learnergy. We have also improved all of your packages, including GPU-based versions of our models.

    Please read the docs at: learnergy.readthedocs.io

    Also, stay tuned for our next updates!

    Includes (or changes)

    • learnergy
    Source code(tar.gz)
    Source code(zip)
  • v1.0.1(Sep 12, 2019)

    Changelog

    Description

    Welcome to Recogners v1.0.1. We fixed some issues related to the auto docstringing API, added the Dropout-based RBM and a method to dump important information to the model's history.

    Note that the Gaussian RBM is not yet guaranteed to work. Please await for our next release.

    Includes (or changes)

    • models/dropout_rbm
    • tests
    Source code(tar.gz)
    Source code(zip)
  • v1.0.0(Jul 4, 2019)

    Changelog

    Description

    This is the initial release of Recogners. It includes all basic modules in order to work with it. One can create and use a Restricted Boltzmann Machine, along with some extra functionalities. Please check examples folder or read the docs in order to know how to use this library.

    Includes

    • core
    • datasets
    • math
    • models
    • utils
    • visual
    Source code(tar.gz)
    Source code(zip)
Owner
Gustavo Rosa
There are no programming languages that can match up to programming logic. Machine learning researcher on work time and software engineer on free time.
Gustavo Rosa
Multi-Modal Machine Learning toolkit based on PaddlePaddle.

简体中文 | English PaddleMM 简介 飞桨多模态学习工具包 PaddleMM 旨在于提供模态联合学习和跨模态学习算法模型库,为处理图片文本等多模态数据提供高效的解决方案,助力多模态学习应用落地。 近期更新 2022.1.5 发布 PaddleMM 初始版本 v1.0 特性 丰富的任务

njustkmg 520 Dec 28, 2022
Gym environment for FLIPIT: The Game of "Stealthy Takeover"

gym-flipit Gym environment for FLIPIT: The Game of "Stealthy Takeover" invented by Marten van Dijk, Ari Juels, Alina Oprea, and Ronald L. Rivest. Desi

Lisa Oakley 2 Dec 15, 2021
LaneAF: Robust Multi-Lane Detection with Affinity Fields

LaneAF: Robust Multi-Lane Detection with Affinity Fields This repository contains Pytorch code for training and testing LaneAF lane detection models i

155 Dec 17, 2022
PyTorch implementation of "ContextNet: Improving Convolutional Neural Networks for Automatic Speech Recognition with Global Context" (INTERSPEECH 2020)

ContextNet ContextNet has CNN-RNN-transducer architecture and features a fully convolutional encoder that incorporates global context information into

Sangchun Ha 24 Nov 24, 2022
ICRA 2021 "Towards Precise and Efficient Image Guided Depth Completion"

PENet: Precise and Efficient Depth Completion This repo is the PyTorch implementation of our paper to appear in ICRA2021 on "Towards Precise and Effic

232 Dec 25, 2022
Towards End-to-end Video-based Eye Tracking

Towards End-to-end Video-based Eye Tracking The code accompanying our ECCV 2020 publication and dataset, EVE. Authors: Seonwook Park, Emre Aksan, Xuco

Seonwook Park 76 Dec 12, 2022
source code of “Visual Saliency Transformer” (ICCV2021)

Visual Saliency Transformer (VST) source code for our ICCV 2021 paper “Visual Saliency Transformer” by Nian Liu, Ni Zhang, Kaiyuan Wan, Junwei Han, an

89 Dec 21, 2022
Torchyolo - Yolov3 ve Yolov4 modellerin Pytorch uygulamasıdır

TORCHYOLO : Yolo Modellerin Pytorch Uygulaması Yapılacaklar: Yolov3 model.py ve

Kadir Nar 3 Aug 22, 2022
Local-Global Stratified Transformer for Efficient Video Recognition

DualFormer This repo is the implementation of our manuscript entitled "Local-Global Stratified Transformer for Efficient Video Recognition". Our model

Sea AI Lab 19 Dec 07, 2022
Development Kit for the SoccerNet Challenge

SoccerNetv2-DevKit Welcome to the SoccerNet-V2 Development Kit for the SoccerNet Benchmark and Challenge. This kit is meant as a help to get started w

Silvio Giancola 117 Dec 30, 2022
A curated list of awesome deep long-tailed learning resources.

A curated list of awesome deep long-tailed learning resources.

vanint 210 Dec 25, 2022
Normal Learning in Videos with Attention Prototype Network

Codes_APN Official codes of CVPR21 paper: Normal Learning in Videos with Attention Prototype Network (https://arxiv.org/abs/2108.11055) Overview of ou

11 Dec 13, 2022
NAS Benchmark in "Prioritized Architecture Sampling with Monto-Carlo Tree Search", CVPR2021

NAS-Bench-Macro This repository includes the benchmark and code for NAS-Bench-Macro in paper "Prioritized Architecture Sampling with Monto-Carlo Tree

35 Jan 03, 2023
Label Mask for Multi-label Classification

LM-MLC 一种基于完型填空的多标签分类算法 1 前言 本文主要介绍本人在全球人工智能技术创新大赛【赛道一】设计的一种基于完型填空(模板)的多标签分类算法:LM-MLC,该算法拟合能力很强能感知标签关联性,在多个数据集上测试表明该算法与主流算法无显著性差异,在该比赛数据集上的dev效果很好,但是由

52 Nov 20, 2022
Supervised Sliding Window Smoothing Loss Function Based on MS-TCN for Video Segmentation

SSWS-loss_function_based_on_MS-TCN Supervised Sliding Window Smoothing Loss Function Based on MS-TCN for Video Segmentation Supervised Sliding Window

3 Aug 03, 2022
git《Learning Pairwise Inter-Plane Relations for Piecewise Planar Reconstruction》(ECCV 2020) GitHub:

Learning Pairwise Inter-Plane Relations for Piecewise Planar Reconstruction Code for the ECCV 2020 paper by Yiming Qian and Yasutaka Furukawa Getting

37 Dec 04, 2022
CLOCs: Camera-LiDAR Object Candidates Fusion for 3D Object Detection

CLOCs is a novel Camera-LiDAR Object Candidates fusion network. It provides a low-complexity multi-modal fusion framework that improves the performance of single-modality detectors. CLOCs operates on

Su Pang 254 Dec 16, 2022
PyTorch implementation for "HyperSPNs: Compact and Expressive Probabilistic Circuits", NeurIPS 2021

HyperSPN This repository contains code for the paper: HyperSPNs: Compact and Expressive Probabilistic Circuits "HyperSPNs: Compact and Expressive Prob

8 Nov 08, 2022
Bayesian algorithm execution (BAX)

Bayesian Algorithm Execution (BAX) Code for the paper: Bayesian Algorithm Execution: Estimating Computable Properties of Black-box Functions Using Mut

Willie Neiswanger 38 Dec 08, 2022
[ICCV2021] Official Pytorch implementation for SDGZSL (Semantics Disentangling for Generalized Zero-Shot Learning)

Semantics Disentangling for Generalized Zero-shot Learning This is the official implementation for paper Zhi Chen, Yadan Luo, Ruihong Qiu, Zi Huang, J

25 Dec 06, 2022