All Projects → TymonXie → tymon

TymonXie / tymon

Licence: Apache-2.0 license
An AI Assistant More Than a Toolkit

Programming Languages

python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to tymon

Emotion Recognition Using Speech
Building and training Speech Emotion Recognizer that predicts human emotions using Python, Sci-kit learn and Keras
Stars: ✭ 159 (+245.65%)
Mutual labels:  sklearn
Mozart
An optical music recognition (OMR) system. Converts sheet music to a machine-readable version.
Stars: ✭ 241 (+423.91%)
Mutual labels:  sklearn
Word2VecAndTsne
Scripts demo-ing how to train a Word2Vec model and reduce its vector space
Stars: ✭ 45 (-2.17%)
Mutual labels:  sklearn
Tensorflow Ml Nlp
텐서플로우와 머신러닝으로 시작하는 자연어처리(로지스틱회귀부터 트랜스포머 챗봇까지)
Stars: ✭ 176 (+282.61%)
Mutual labels:  sklearn
Python Ai Assistant
Python AI assistant 🧠
Stars: ✭ 219 (+376.09%)
Mutual labels:  sklearn
A-B-testing-with-Machine-Learning
Implemented an A/B Testing solution with the help of machine learning
Stars: ✭ 37 (-19.57%)
Mutual labels:  sklearn
Mlmodels
mlmodels : Machine Learning and Deep Learning Model ZOO for Pytorch, Tensorflow, Keras, Gluon models...
Stars: ✭ 145 (+215.22%)
Mutual labels:  sklearn
techloop-ml-plus
Archives and Tasks for ML+ sessions
Stars: ✭ 23 (-50%)
Mutual labels:  sklearn
Gam
A PyTorch implementation of "Graph Classification Using Structural Attention" (KDD 2018).
Stars: ✭ 227 (+393.48%)
Mutual labels:  sklearn
merkalysis
A marketing tool that helps you to market your products using organic marketing. This tool can potentially save you 1000s of dollars every year. The tool predicts the reach of your posts on social media and also suggests you hashtags for captions in such a way that it increases your reach.
Stars: ✭ 28 (-39.13%)
Mutual labels:  sklearn
Data Science Notebook
📖 每一个伟大的思想和行动都有一个微不足道的开始
Stars: ✭ 196 (+326.09%)
Mutual labels:  sklearn
Machine Learning
从零基础开始机器学习之旅
Stars: ✭ 209 (+354.35%)
Mutual labels:  sklearn
overview-and-benchmark-of-traditional-and-deep-learning-models-in-text-classification
NLP tutorial
Stars: ✭ 41 (-10.87%)
Mutual labels:  sklearn
Danmf
A sparsity aware implementation of "Deep Autoencoder-like Nonnegative Matrix Factorization for Community Detection" (CIKM 2018).
Stars: ✭ 161 (+250%)
Mutual labels:  sklearn
trt pose hand
Real-time hand pose estimation and gesture classification using TensorRT
Stars: ✭ 137 (+197.83%)
Mutual labels:  sklearn
Fenchel Young Losses
Probabilistic classification in PyTorch/TensorFlow/scikit-learn with Fenchel-Young losses
Stars: ✭ 152 (+230.43%)
Mutual labels:  sklearn
Igel
a delightful machine learning tool that allows you to train, test, and use models without writing code
Stars: ✭ 2,956 (+6326.09%)
Mutual labels:  sklearn
machine-learning-templates
Template codes and examples for Python machine learning concepts
Stars: ✭ 40 (-13.04%)
Mutual labels:  sklearn
ml
Base machine learning image and environment.
Stars: ✭ 15 (-67.39%)
Mutual labels:  sklearn
imbalanced-ensemble
Class-imbalanced / Long-tailed ensemble learning in Python. Modular, flexible, and extensible. | 模块化、灵活、易扩展的类别不平衡/长尾机器学习库
Stars: ✭ 199 (+332.61%)
Mutual labels:  sklearn

tymon

An AI Assistant More Than a Toolkit The reason for creating framework tymon is simple. making AI more like an assistant, helping us to complete daily AI tasks we want to accomplish, rather than just a tool. I prefer it to be interactive and "human".

Installation

pip install tymon

Example

Timeseries Assistant

prediction task with LSTM

instant a timeseries assistant object, and choose model, set datapath.

from tymon.assistant import TimeSeries
assistant_object = TimeSeries(model_name='LSTM',data_path='./international-airline-passengers.csv')
assistant_object.run() 

run the code you will get a window to set the parameters for model.
parameters_image
set parameters to what you want, click the start button to train the model.
train_process
you will get final model in ./ and its performance image.
result_image

Related Blog

基于tymon,无需搭建LSTM,航班人数预测

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].