Lightwood is Legos for Machine Learning.

Last update: Jan 08, 2023

Overview

Lightwood is like Legos for Machine Learning.

A Pytorch based framework that breaks down machine learning problems into smaller blocks that can be glued together seamlessly with one objective:

Make it so simple that you can build predictive models with as little as one line of code.

Documentation

Learn more from the Lightwood's docs.

Try it out

Installation

You can install Lightwood from pip:

pip3 install lightwood

Note: depending on your environment, you might have to use pip instead of pip3 in the above command.

Usage

Given the simple sensor_data.csv let's predict sensor3 values.

sensor1	sensor2	sensor3
1	-1	-1
0	1	0
-1	- 1	1

Import Predictor from Lightwood

from lightwood import Predictor

Train the model.

import pandas
sensor3_predictor = Predictor(output=['sensor3']).learn(from_data=pandas.read_csv('sensor_data.csv'))

You can now predict what sensor3 value will be.

prediction = sensor3_predictor.predict(when={'sensor1':1, 'sensor2':-1})

You can also try Lightwood in Google Colab:

Contributing

Thanks for your interest. There are many ways to contribute to this project. Please, check out our Contribution guide.

Current contributors

Made with contributors-img.

License

Lightwood License

Comments

ImportError: cannot import name 'Imputer' from 'sklearn.preprocessing'
Describe the bug Installing the latest version of lightwood throws ImportError. I guess the issue is related to the sciki-learn.

To Reproduce Steps to reproduce the behavior:

Train model, the issue is not related to a specific dataset

See error

from cesium import featurize

File "/home/zoran/MyProjects/lightwood/l/lib/python3.7/site-packages/cesium-0.9.9-py3.7-linux-x86_64.egg/cesium/featurize.py", line 10, in from sklearn.preprocessing import Imputer ImportError: cannot import name 'Imputer' from 'sklearn.preprocessing' (/home/zoran/MyProjects/lightwood/l/lib/python3.7/site-packages/scikit_learn-0.22rc3-py3.7-linux-x86_64.egg/sklearn/preprocessing/init.py)

Screenshots
bug
opened by ZoranPandovski 23
CSV with the dataset from the deernet paper

I loved this paper: https://arxiv.org/pdf/2106.07465.pdf and I'd love to add the dataset they are using to our benchmark.

However, I'm unsure how to use the physics library required to generate the data and would rather just have a simple CSV with the data (csv columns can contain arrays if need be, but I don't think this will be required here).

Feel free to PR this csv into https://github.com/mindsdb/benchmarks

This will count 3 points towards the hacktoberfest deep learning laptop raffle.
good first issue test hacktoberfest

opened by George3d6 15
fix wrong time-series alignment and add WA for StatsForcastAutoARIMA
a proposed fix for time-series alignment error and issue of StatsForcastAutoARIMA

see https://github.com/mindsdb/mindsdb/issues/3234 for detail about the alignment issue

see https://mindsdbcommunity.slack.com/archives/C037482KJ22/p1665911392587569 for more detail about the issue of StatsForcastAutoARIMA

the proposed fix is tested with house-sale tutorial only. It might need more review to consider the impact of the change
opened by bachng2017 9
ImportError: cannot import name 'COLUMN_DATA_TYPES'

When I am trying to import column data from light wood following error occurs: in ----> 1 from lightwood import COLUMN_DATA_TYPES, BUILTIN_MIXERS, BUILTIN_ENCODERS 2 config = { 3 4 ## REQUIRED: 5 'input_features': [

ImportError: cannot import name 'COLUMN_DATA_TYPES'

opened by iamharikrishnank 9
quantum mixer implementation
closes #641

implementing a quantum class neural network from https://qiskit.org/textbook/ch-machine-learning/machine-learning-qiskit-pytorch.html

implementation notes

currently using QClassic wrapper around the Neural mixer

its easier to error out the unit test

because qiskit is an optional dependency

QClassicNet is quite rudimentary

returns a quantum modified value as per the tutorial

hacktoberfest-accepted
opened by ongspxm 8
Improvements to Travis
Ignore Doc change #109

Fail travis build for errors in scripts (unit tests) #110

@George3d6 This is just the same replication from mindsdb/mindsdb and I think will be useful as I was going through Lightwood
bug discussion test
opened by ritwik12 8
feat: added prospector code analysis tool

This pull request will fix this issue.

This pull request adds Prospector as a static code analysis tool to run an analysis each time a PR is opened through the use of GitHub actions.

opened by vickywane 7
Add new ensembles that improve accuracy on the benchmark suite
Task

Lightwood's core component is the encoder, which takes the predictions from the mixers and combines the final prediction.

This task involves implementing any ensemble which you think can improve lightwood's accuracy. A PR will be accepted as long as the relative accuracy is increased by at least 1% with no modifications other than adding the new ensembles and using it in json_ai.py.

Multiple people can try this PR assuming no plagiarism between the designs.

Steps :male_detective: :female_detective:

Fork the Lightwood repository, checkout the staging branch and from it create a new one.

Implement your custom ensemble and edit the api/json_ai.py file to replace the BestOf ensemble

Run the benchmarks following the instructions here

Note: If you can't afford to run all the benchmarks, test on a subset of small datasets you think your ensemble is good at using --datasets=x,y,z | Alternatively, contact us (or make a PR) and we will provide compute for you to do this.

Make the PR and address any comments that reviewers might make.

enhancement help wanted good first issue
opened by George3d6 7
Implement an audio encoder
Task

Lightwood handles many different data types, and we're always looking to include more.

One possible data type to experiment with is an audio encoder; if you are interested in tackling this, please ping the research team (either me, @hakunanatasha or @George3d6) in the discussion here, to propose your initial approach and scope your contribution together ✨.

Ensure you implement a unit test plus any modifications needed to obtain an encoded representation from audio in order for this PR to be accepted.

Steps :male_detective: :female_detective:

Fork the Lightwood repository, checkout the staging branch and from it create a new one.

Implement a unit test that generates an instance of your encoder, some (potentially synthetic) audio data, and proceed to encode-decode it. This unit test can be useful as a reference, and the (outdated) AmplitudeTs encoder as inspiration or starting point for your own encoder (in fact, feel free to replace it).

Accuracy of the encoder is to be discussed with our team, so don't get discouraged if encoded representations are not perfect; this is a hard problem!

Make the PR and address any comments that reviewers might make.

Additional rewards :1st_place_medal:

Each encoder PR brings 5️⃣ points for entry into the draw for a :computer: Deep Learning Laptop powered by the NVIDIA RTX 3080 Max-Q GPU or other swag :shirt: :bear: . For more info check out https://mindsdb.com/hacktoberfest/
enhancement help wanted good first issue hacktoberfest
opened by paxcema 7

CUDA error

Python version: 3.6.9
Lightwood version: last staging
Additional info if applicable: print(torch.version) => 1.7.0

I have old GPU (geforce 660), so assume cuda should not be used during predictor training, but in log i see:

ERROR:mindsdb-logger-9c6604ca-5708-11eb-a3e2-2c56dc4ecd27---no_report:/home/maxs/dev/mdb/venv_new/lib/python3.6/site-packages/mindsdb_native/libs/phases/model_interface/lightwood_backend.py:417 - Traceback (most recent call last):
  File "/home/maxs/dev/mdb/venv_new/lib/python3.6/site-packages/mindsdb_native/libs/phases/model_interface/lightwood_backend.py", line 411, in train
    test_data=lightwood_test_ds
  File "/home/maxs/dev/mdb/venv_new/lib/python3.6/site-packages/lightwood/api/predictor.py", line 137, in learn
    self._mixer.fit(train_ds=train_ds, test_ds=test_ds)
  File "/home/maxs/dev/mdb/venv_new/lib/python3.6/site-packages/lightwood/mixers/base_mixer.py", line 37, in fit
    self._fit(train_ds, test_ds, **kwargs)
  File "/home/maxs/dev/mdb/venv_new/lib/python3.6/site-packages/lightwood/mixers/nn.py", line 270, in _fit
    for epoch, training_error in enumerate(self._iter_fit(subset_train_ds, subset_id=subset_id)):
  File "/home/maxs/dev/mdb/venv_new/lib/python3.6/site-packages/lightwood/mixers/nn.py", line 571, in _iter_fit
    outputs = self.net(inputs)
  File "/home/maxs/dev/mdb/venv_new/lib/python3.6/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
    result = self.forward(*input, **kwargs)
  File "/home/maxs/dev/mdb/venv_new/lib/python3.6/site-packages/lightwood/mixers/helpers/default_net.py", line 125, in forward
    output = self._foward_net(input)
  File "/home/maxs/dev/mdb/venv_new/lib/python3.6/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
    result = self.forward(*input, **kwargs)
  File "/home/maxs/dev/mdb/venv_new/lib/python3.6/site-packages/torch/nn/modules/container.py", line 117, in forward
    input = module(input)
  File "/home/maxs/dev/mdb/venv_new/lib/python3.6/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
    result = self.forward(*input, **kwargs)
  File "/home/maxs/dev/mdb/venv_new/lib/python3.6/site-packages/torch/nn/modules/linear.py", line 93, in forward
    return F.linear(input, self.weight, self.bias)
  File "/home/maxs/dev/mdb/venv_new/lib/python3.6/site-packages/torch/nn/functional.py", line 1690, in linear
    ret = torch.addmm(bias, input, weight.t())
RuntimeError: CUDA error: no kernel image is available for execution on the device


ERROR:mindsdb-logger-9c6604ca-5708-11eb-a3e2-2c56dc4ecd27---no_report:/home/maxs/dev/mdb/venv_new/lib/python3.6/site-packages/mindsdb_native/libs/phases/model_interface/lightwood_backend.py:418 - Exception while running NnMixer

Training finish well, predictor is queryable.

bug

opened by StpMax 7

Setup linter

Describe the bug Setup python linter for project

Expected behavior Linting code

I know this is not the main purpose of the project, but I think that setup linter will be better for project maintenance.

How do you think?
enhancement help wanted good first issue

opened by kination 7
sequential encoder execution
Pending:

[ ] Flag that enables choosing parallel (multiprocess) or sequential preparation

[ ] Better automated policy that picks the "correct" choice without user input

Research
opened by paxcema 0
[docs] Optional classes are not documented

The automated doc system is not picking up the docstrings in classes that require optional dependencies. For example, the mixers LightGBM, LightGBMArray and NHitsMixer.

We should either change the CI to install all extra deps or change the doc system to pick up these classes regardless of whether the dependencies are installed or not.
enhancement

opened by paxcema 0
Improve error message if no mixers could be trained

If the final list of trained mixers is empty, we should communicate the reasons why each of them failed. E.g. if a user specifies a mixer that is not compatible with the target dtype, they should get this in the raised exception.
enhancement help wanted qa-er

opened by paxcema 0

Releases(v22.12.2.0)

v22.12.2.0(Dec 15, 2022)
Changelog

Features

XGBoost mixer (#1066)

Store global insights inside predictor object (#1074)

Force infer_row in bulk ts predictions (#1075)

Fixes

Other

Bump transformers to 4.21.0 (#1070)

Bump sktime 0.14.0 (#1077)

Lightgbm-based mixers are now optional (#1080)

Source code(tar.gz)
Source code(zip)
v22.11.2.0(Nov 11, 2022)
Changelog:

Features:

[ENH] Custom output distributions in GluonTS mixer (#1042)

[ENH] Restores py3.7 support (#1039)

Bug fixes:

[Fix] Parameters to be optimized (#1035)

Others:

[Maint] Migrate to type_infer (#1024)

[Test] Improve time series test (#1041)

Source code(tar.gz)
Source code(zip)
v22.10.4.0(Oct 26, 2022)
Features

Argument to override device setting #1004

Implement a RandomForest mixer #1017

[ENH] ICP: aggregated sum over horizon #995

Add lightwood library version to predictor #1018

Add GluonTS mixer #1019

Improve random forest mixer #1031

Simpler TS evaluation #1032

Fixes

Added original amount of columns #1014

Fix supported python version spec >=3.7,<3.10 #1015

Fix wrong time-series alignment and add WA for StatsForcastAutoARIMA #1022

Fix: workaround for StatsForecastAutoARIMA #1025

Fix: gluonts improvements #1030

Other

Add test for forecast offset alignment #1023

Remove n-hits & prophet from default mixer list #1028

Thanks to @alexandre-dz-oscore @riadhlaabidi @jaredc07 @akhildevelops @adripo @bachng2017 for contributing to this release!
Source code(tar.gz)
Source code(zip)
v22.9.1.0(Sep 6, 2022)
Release 22.9.1.0

Features

[ENH] PyOD analysis block (#983)

[ENH] Infer offset in SkTime mixers (#989)

Fixes

[Fix] minor idx error in fh setting (#991)

[Fix] stacked ensemble agg_dim (#992)

Benchmarks
Source code(tar.gz)
Source code(zip)
v22.8.1.0(Aug 5, 2022)
Changelog

Features

Conformal forecasting #862

Improved JsonAI templating for analysis blocks #960

Some feature importance changes #961

Fixes

Default NHITS space params #956

Add data limits to PFI block #963

Source code(tar.gz)
Source code(zip)
v22.7.4.0(Jul 26, 2022)
Changelog

Features

[ENH] New defaults for sktime mixer, new AutoETS and AutoARIMA mixers (#946)

[ENH] Enforce bounded_ts_accuracy as default (#950)

Fixes

fix quick start guide #943 (thanks to @ameliatheamazin!)

[FIX] kwarg setting for LightGBM GPU (#944)

[FIX] Hotfix: use defaults in new groups (#952)

Other

[FIX] New bias description (#947)

[ENH] Message for missing values (#948)

Source code(tar.gz)
Source code(zip)
v22.7.3.0(Jul 20, 2022)
Features

[ENH] Add tn_conf for categorical targets (#936)

Bug fixes

Better sp detection (#935)

Various small fixes (#940)

Others

Change supported Python versions to 3.7 and 3.8 (#930)

Use prophet 1.1 with wheels (#911, thanks @abitrolly !)

order_by is now a single column #938

Source code(tar.gz)
Source code(zip)
v22.7.2.0(Jul 11, 2022)
Release 22.7.2.0

Benchmarks

Features

Experimental N-HITS forecasting mixer (#886)

Differencing blocks for time series tasks (#903)

Linear tree for LightGBMArray mixer (#902)

STL decomposition blocks for time series tasks (#907)

Fixes

Restored statsforecast as default backend for ARIMA models (#904)

Other

N/A
Source code(tar.gz)
Source code(zip)
v22.6.1.2(Jun 3, 2022)
Changelog

Features

#894

Fixes

#889

#895

#896

#897

Other

#789

Benchmarks:

#8b07e93

#b92c8fd

Source code(tar.gz)
Source code(zip)
v22.5.1.0(May 6, 2022)
Changelog:

Features

#865 - ProphetMixer to forecast

Bug fixes

#866 & #872 - Fix TS float cleaner can't deal with malformed input

#873 - Fix non-null TS delta analysis

Other

Benchmarks
Source code(tar.gz)
Source code(zip)
v22.4.1.0(Apr 1, 2022)
Lightwood 22.4.1.0 changelog:

Features: -

Bug fixes:

#848 - Log runtime per mixer

#855 - Fix dimension error in neural mixer

Other

#850 - Restore Windows CI

Full Changelog:

https://github.com/mindsdb/lightwood/compare/b05e8b4a502352caeaf1816fc6b4b5add0e465e8...v22.4.1.0
Source code(tar.gz)
Source code(zip)
v22.2.1.0(Feb 3, 2022)
Lightwood 22.2.1.0 changelog:

Features:

Simpler and better Json AI #826

Compute & log time per phase #828

Bug fixes: -

Other:

Remove anomaly_error_rate arg in favor of fixed_confidence #825

Full Changelog: https://github.com/mindsdb/lightwood/compare/v22.1.4.0...v22.2.1.0
Source code(tar.gz)
Source code(zip)
v22.1.4.0(Jan 27, 2022)
Lightwood 22.1.4.0 changelog:

Moving forward, our release versioning schema will follow this format: [year's last two digits].[month].[week].[patch]

(note: other MindsDB repositories will also switch to this)

Features:

ConfStats block (#800): provides calibration insights for the lightwood predictor

Temperature scaling block (#795, experimental & non-default): alternative to ICP block for confidence estimation

Improved documentation pages (#806)

Replaced default encoder for time series forecasting tasks (from RNN to simple MA features, #805)

Explicit detrend and deseasonalize options for sktime mixer (#812)

Bug fixes:

Updated update model tutorial (#774)

Fix forecast horizon lower bound (#801)

Handle empty input when predicting (#811)

Other

Rename nr_predictions parameter to horizon (#803)

Set allow_incomplete_history to True by default (#818)

Full Changelog

https://github.com/mindsdb/lightwood/compare/v1.9.0...v22.1.4.0
Source code(tar.gz)
Source code(zip)
v1.9.0(Dec 27, 2021)
Lightwood 1.9.0 changelog:

Features:

Improved T+N forecast bounds (#788)

Optimized classifier ICP block for confidence estimation (#798)

Bug fixes:

Fixed initialization issues in confidence normalizer (#788)

Fixed no analysis mode (+ parameter to specify this in a problem definition, #791)

Fixed temporal delta estimation for ungrouped series (#792)

Other

Add original query index column in output (used internally in MindsDB, #794)

Streamlined explain() arg passing #797

Source code(tar.gz)
Source code(zip)
v1.8.0(Dec 22, 2021)
Lightwood 1.8.0 changelog:

Features:

SkTime mixer 2.0 (#758, #767)

Improve time aim feature (#763)

Improved OHE and binary encoders, standardized a few more (#755, #785)

Streamlined predictor.adjust signature (#762)

Add precision, recall, f1 (#776)

Bug fixes:

Do not drop single-group-by column (#761, #756)

OH and Binary Encoders weighting fix (#769)

LGBM array mixer does not modify the datasource (#771)

Fixes missing torchvision import (#784)

Other

Make image encoder optional (#778)

Revamp notebooks test docs (#764)

Source code(tar.gz)
Source code(zip)
v1.7.0(Nov 17, 2021)
Lightwood 1.7.0 changelog:

Features:

Simplified type mapping in Json AI (#724)

Setter for neural mixer # epochs (#737)

Improved nan handling (#720)

Drop columns with no information (#736)

LightGBM mixer supports weights (#749)

Improved OneHot and Binary encoders' logic around weights (#749)

New accuracy function lookup hierarchy (#754)

Better warning logs when nan or inf values are encountered (#754)

Bug fixes:

Fixed LightGBM error on CPU (#726)

Cast TS group by values to string to avoid TypeError (#727)

Check target values when transforming time series if task requires them (#747)

Streamline encode/decode in TsArrayNumericEncoder (#748)

target_weights argument is now used properly (#749)

Use custom R2 accuracy to account for edge cases (#754)

Fixed target dropping behavior (#754)

Other

Update README.md example (#731)

Separate branch for docs (#740)

Docs for image and audio encoders; LightGBM and LinearRegression mixers (#721, #722)

Source code(tar.gz)
Source code(zip)
v1.6.0(Nov 1, 2021)
Lightwood 1.6.0 changelog:

Many thanks to our community contributors for this release! @MichaelLantz @mrandri19 @ongspxm @vaithak

Features:

SHAP analysis block (#679, @mrandri19)

Disable GlobalFeatureImportance when we have too many columns (#681, @ongspxm; #698)

Added cleaner support for file path data types (image, audio, video) (#675)

Add partial_fit() to sktime mixer (#689)

Add ModeEnsemble (#692, @mrandri19)

Add weighted MeanEnsembler (#680, @vaithak)

Bug fixes:

Normalized column importance range (#690)

Fix ensemble supports_proba in calibrate.py (#694, @mrandri19)

Remove self-referential import (#696)

Make a integration test for time_aim (#685, @MichaelLantz)

Fix for various datasets (#700)

Other

Improve logging for analysis blocks (#677; @MichaelLantz)

Custom block example: LabelEncoder (#663)

Implement ShapleyValues analysis (#679)

Move array/TS normalizers to generic helpers (#702)

Source code(tar.gz)
Source code(zip)
v1.5.0(Oct 22, 2021)
Lightwood 1.5.0 changelog:

Many thanks to this month's community contributors! @alteregoprofile, @LyndonFan, @MichaelLantz, @mrandri19, @ongspxm

Features:

MFCC-based audio encoder (#625, #638; @mrandri19)

Quantum mixer (#645, @ongspxm)

Identity encoders (#623; @LyndonFan)

Simpler default splitter (#624)

MeanEnsemble (#658; @mrandri19)

Improved interface to predict with all mixers (#627)

API: predictor_from_json_ai (#633; @mrandri19)

One-hot encoder mode to work without unknown categories (#639; @mrandri19)

System for handling optional dependencies (#640)

Bug fixes:

Img2Vec encoder bug fixes and tests (#619, #622; @mrandri19)

Fix encoder prepare calls (#630)

Black formatter fix (#650)

Docs: doc_build triggers during pull_request (#653, #665; @MichaelLantz)

ArrayEncoder fixes (#604, @alteregoprofile)

Other

Rename fit_on_validation to fit_on_all (#626)

Smaller test datasets (#631)

Docs: add a time series forecasting tutorial (#635)

Improved documentation coverage (#654, #660)

Docs: doc_build automatically runs jupyter notebooks (#657)

Source code(tar.gz)
Source code(zip)
v1.4.0(Oct 11, 2021)
Lightwood 1.4.0 changelog:

Features:

Streamlined dynamic .predict() argument passing (#563)

Set default logging level with environment variable (@mrandri19, #603)

Colored logs (@mrandri19, #608)

Bug fixes:

JsonAI blocks are now Modules (#569)

Ignore column drop error if column is not in the dataframe (#579)

LightGBM dependency issue (#609)

Other

Introduction to statistical analyzer tutorial (#577)

Custom cleaner tutorial (#581)

Custom mixer tutorial (#575)

Custom analysis block tutorial (#576)

Docstring for BaseEncoder (#587)

Native Jupyter notebook support inside docs (#586)

Automated docs deployment (#610)

Updated CLA bot (#612)

Improved README.md and CONTRIBUTING.md (#613)

Note: benchmarks will not run on the latest commit for this release, they were instead successfully ran for commit 79f27325a0877bb95709373007a97161fc9bb2eb.
Source code(tar.gz)
Source code(zip)
v1.3.0(Oct 7, 2021)
Lightwood 1.3.0 changelog:

Features:

Modular Cleaner (#538 and #568)

Modular Analysis (#539)

Better Imports (#540)

Improved Json AI default arguments (#543)

Add seed to splitter (#553)

Stratification and 3-way splitting (#542, #571)

Use MASE metric for TS model selection (#499)

Bug fixes:

Allow quantity as target (#546)

Fix for LightGBM device check (#544)

Select OneHotEncoder at Json AI build time and fix pd.None bugs (#549)

Miscellaneous fixes (#570)

Other

Improved CONTRIBUTING.md (#550)

Source code(tar.gz)
Source code(zip)
1.2.0(Sep 23, 2021)
Features:

Better defaults for Neural model in time series tasks (#461)

Seed keyword passed (#482)

Handle ' and " in dataset column names (#503)

Helper function to split grouped time series (#501)

Enhanced date-time + tag histograms (#502)

Nonconformist speed optimizations (#497)

Add dtype.tsarray (#530)

Bug fixes:

Fix analysis memory usage (#485)

Fix incorrect return value for order column in time series tasks (#488)

Fix time series encoding issue (#495)

Remove deprecated logic (#518)

Make explainer work with categorical targets not present in the training data (#500)

Fix sktime dependency (#524)

Better detection, cleaning and encoding of arrays (#512)

Use correct accuracy score for binary data (#532)

allow_incomplete_history for time series predictors (#525)

Other

Automated documentation (NOTE: still in beta; #519, #528)

Rename model to mixer; folds to subsets (#534)

Source code(tar.gz)
Source code(zip)

Owner

MindsDB Inc

GitHub Repository

Generating synthetic mobility data for a realistic population with RNNs to improve utility and privacy

lbs-data Motivation Location data is collected from the public by private firms via mobile devices. Can this data also be used to serve the public goo

11 Sep 22, 2022

Knowledge Management for Humans using Machine Learning & Tags

HyperTag HyperTag helps humans intuitively express how they think about their files using tags and machine learning.

165 Nov 04, 2022

ResNEsts and DenseNEsts: Block-based DNN Models with Improved Representation Guarantees

ResNEsts and DenseNEsts: Block-based DNN Models with Improved Representation Guarantees This repository is the official implementation of the empirica

2 Oct 02, 2022

Fight Recognition from Still Images in the Wild @ WACVW2022, Real-world Surveillance Workshop

Fight Detection from Still Images in the Wild Detecting fights from still images is an important task required to limit the distribution of social med

10 Nov 09, 2022

Source code for models described in the paper "AudioCLIP: Extending CLIP to Image, Text and Audio" (https://arxiv.org/abs/2106.13043)

AudioCLIP Extending CLIP to Image, Text and Audio This repository contains implementation of the models described in the paper arXiv:2106.13043. This

458 Jan 02, 2023

Tutorial on active learning with the Nvidia Transfer Learning Toolkit (TLT).

Active Learning with the Nvidia TLT Tutorial on active learning with the Nvidia Transfer Learning Toolkit (TLT). In this tutorial, we will show you ho

25 Dec 03, 2022

A deep learning CNN model to identify and classify and check if a person is wearing a mask or not.

Face Mask Detection The Model is designed to check if any human is wearing a mask or not. Dataset Description The Dataset contains a total of 11,792 i

1 Mar 01, 2022

A High-Quality Real Time Upscaler for Anime Video

Anime4K Anime4K is a set of open-source, high-quality real-time anime upscaling/denoising algorithms that can be implemented in any programming langua

15.7k Jan 06, 2023

Novel Instances Mining with Pseudo-Margin Evaluation for Few-Shot Object Detection

Novel Instances Mining with Pseudo-Margin Evaluation for Few-Shot Object Detection (NimPme) The official implementation of Novel Instances Mining with

12 Sep 08, 2022

《Single Image Reflection Removal Beyond Linearity》(CVPR 2019)

Single-Image-Reflection-Removal-Beyond-Linearity Paper Single Image Reflection Removal Beyond Linearity. Qiang Wen, Yinjie Tan, Jing Qin, Wenxi Liu, G

51 Jun 24, 2022

This repository is for Contrastive Embedding Distribution Refinement and Entropy-Aware Attention Network (CEDR)

CEDR This repository is for Contrastive Embedding Distribution Refinement and Entropy-Aware Attention Network (CEDR) introduced in the following paper

3 Feb 27, 2022

OpenMMLab Model Deployment Toolset

Introduction English | 简体中文 MMDeploy is an open-source deep learning model deployment toolset. It is a part of the OpenMMLab project. Major features F

1.5k Dec 30, 2022

PyTorch implementation for our paper Learning Character-Agnostic Motion for Motion Retargeting in 2D, SIGGRAPH 2019

Learning Character-Agnostic Motion for Motion Retargeting in 2D We provide PyTorch implementation for our paper Learning Character-Agnostic Motion for

367 Dec 22, 2022

This folder contains the implementation of the multi-relational attribute propagation algorithm.

MrAP This folder contains the implementation of the multi-relational attribute propagation algorithm. It requires the package pytorch-scatter. Please

6 Dec 06, 2022

🤖 A Python library for learning and evaluating knowledge graph embeddings

PyKEEN PyKEEN (Python KnowlEdge EmbeddiNgs) is a Python package designed to train and evaluate knowledge graph embedding models (incorporating multi-m

1.1k Jan 09, 2023

Kaggle G2Net Gravitational Wave Detection : 2nd place solution

33 Dec 26, 2022

Pytorch0.4.1 codes for InsightFace

InsightFace_Pytorch Pytorch0.4.1 codes for InsightFace 1. Intro This repo is a reimplementation of Arcface(paper), or Insightface(github) For models,

1.5k Jan 01, 2023

[CVPR2022] Bridge-Prompt: Towards Ordinal Action Understanding in Instructional Videos

Bridge-Prompt: Towards Ordinal Action Understanding in Instructional Videos Created by Muheng Li, Lei Chen, Yueqi Duan, Zhilan Hu, Jianjiang Feng, Jie

58 Dec 23, 2022

Consensus Learning from Heterogeneous Objectives for One-Class Collaborative Filtering

Consensus Learning from Heterogeneous Objectives for One-Class Collaborative Filtering This repository provides the source code of "Consensus Learning

6 Apr 29, 2022

Static-test - A playground to play with ideas related to testing the comparability of the code

Static test playground ⚠️ The code is just an experiment. Compiles and runs on U

4 Feb 18, 2022

Lightwood is Legos for Machine Learning.

Related tags

Overview

Documentation

Try it out

Installation

Usage

Contributing

Current contributors

License

Comments

implementation notes

Task

Steps :male_detective: :female_detective:

Task

Steps :male_detective: :female_detective:

Additional rewards :1st_place_medal:

Releases(v22.12.2.0)

v22.12.2.0(Dec 15, 2022)

Changelog

Features

Fixes

Other

v22.11.2.0(Nov 11, 2022)

Changelog:

Features:

Bug fixes:

Others:

v22.10.4.0(Oct 26, 2022)

Features

Fixes

Other

v22.9.1.0(Sep 6, 2022)

Release 22.9.1.0

Features

Fixes

v22.8.1.0(Aug 5, 2022)

Changelog

Features

Fixes

v22.7.4.0(Jul 26, 2022)

Changelog

Features

Fixes

Other

v22.7.3.0(Jul 20, 2022)

Features

Bug fixes

Others

v22.7.2.0(Jul 11, 2022)

Release 22.7.2.0

Features

Fixes

Other

v22.6.1.2(Jun 3, 2022)

Changelog

Features

Fixes

Other

Benchmarks:

v22.5.1.0(May 6, 2022)

Changelog:

Features

Bug fixes

Other

v22.4.1.0(Apr 1, 2022)

Lightwood 22.4.1.0 changelog:

Features: -

Bug fixes:

Other

Full Changelog:

v22.2.1.0(Feb 3, 2022)

Lightwood 22.2.1.0 changelog:

Features:

Bug fixes: -

Other:

Full Changelog: https://github.com/mindsdb/lightwood/compare/v22.1.4.0...v22.2.1.0

v22.1.4.0(Jan 27, 2022)

Lightwood 22.1.4.0 changelog:

Features: