Machine learning

Machine learning is the practice of teaching a computer to learn. The concept uses pattern recognition, as well as other forms of predictive algorithms, to make judgments on incoming data. This field is closely related to artificial intelligence and computational statistics.

Please make sure that this is a documentation issue. As per our GitHub Policy, we only address code/doc bugs, performance issues, feature requests and build/installation issues on GitHub. tag:doc_template

System information

TensorFlow version: 1.13.1
Doc Link: https://www.tensorflow.org/api_docs/python/tf/cus

@fchollet

(e.g. for links and images), because some of these examples are now being rendered in the docs.

Added by @fchollet in requests for contributions.

🐛 Bug

I stumbled upon excessive CPU usage for my training code running on GPU. After some investigations I found the culprit.
It basically was

x = torch.eye(256).to('cuda')

To Reproduce

This is quick and loads single CPU core.

%%timeit
    torch.eye(181)
6.43 µs ± 218 ns per loop (mean ± std. dev. of 7 runs, 100000 loops each)

This is 3 times slowe

It appears that the docs for Logistic Regression differ based on solvers and penalties. The "penalty" parameter states that "The ‘newton-cg’, ‘sag’ and ‘lbfgs’ solvers support only l2 penalties," while the "solver" parameter states that "‘newton-cg’, ‘lbfgs’, ‘sag’ and ‘saga’ handle L2 or no penalty" (attaching some screenshots). This was actually a little unclear to me, as I wasn't sure if the n

Julia 1.6.0-rc3

runtests.jl:

using Test

d = Dict("hello" => "world")
@test keys(d) == ["hello"]

Test output:

     Testing Running tests...
Test Failed at /Users/fons/Documents/Pluto.jl/test/runtests.jl:4
  Expression: keys(d) == ["hello"]
   Evaluated: ["hello"] == ["hello"]
ERROR: LoadError: There was an error during testing
in expression starting at /Users/

Currently many more Python projects like dask and optuna are using Python type hints. With the Python package of xgboost gaining more and more features, we should also adopt mypy as a safe guard against some type errors and for better code documentation.

Feb	MAR	Apr
	28
2020	2021	2022

Machine learning

Here are 58,042 public repositories matching this topic...

tensorflow / tensorflow

keras-team / keras

pytorch / pytorch

🐛 Bug

To Reproduce

This is quick and loads single CPU core.

This is 3 times slowe

scikit-learn / scikit-learn

aymericdamien / TensorFlow-Examples

tesseract-ocr / tesseract

ageitgey / face_recognition

deepfakes / faceswap

JuliaLang / julia

Avik-Jain / 100-Days-Of-ML-Code

BVLC / caffe

binhnguyennus / awesome-scalability

GokuMohandas / madewithml

ZuzooVn / machine-learning-for-software-engineers

terryum / awesome-deep-learning-papers

ageron / handson-ml

Developer-Y / cs-video-courses

d2l-ai / d2l-zh

fengdu78 / Coursera-ML-AndrewNg-Notes

dmlc / xgboost

fastai / fastai

CMU-Perceptual-Computing-Lab / openpose

donnemartin / data-science-ipython-notebooks

explosion / spaCy

eriklindernoren / ML-From-Scratch

sebastianruder / NLP-progress

trekhleb / homemade-machine-learning

microsoft / CNTK

mozilla / DeepSpeech

ChristosChristofidis / awesome-deep-learning