Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Deep Learning for Time Series Classification
| Date | Stars |
|---|---|
| 2026-07-31 | 1658 |
| 2026-08-02 | 1658 |
| 2026-08-06 | 1658 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# Deep Learning for Time Series Classification This is the companion repository for [our paper](https://link.springer.com/article/10.1007%2Fs10618-019-00619-1) titled "Deep learning for time series classification: a review" published in [Data Mining and Knowledge Discovery](https://link.springer.com/journal/10618), also available on [ArXiv](https://arxiv.org/pdf/1809.04356.pdf).  ## Docker Assuming you have [docker](https://hub.docker.com) installed. You can now use the docker image provided [here](https://hub.docker.com/repository/docker/hassanfawaz/dl-4-tsc/general). Access the docker container via: ```bash docker run --name somename --gpus all -idt hassanfawaz/dl-4-tsc:0.3 docker exec -it somename bash ``` To run you will need to manually download the UCR archive into `/dl-4-tsc/archives/`: ```bash cd /dl-4-tsc/archives wget https://www.cs.ucr.edu/~eamonn/time_series_data_2018/UCRArchive_2018.zip unzip -P $password UCRArchive_2018.zip ``` The password can be found [here](https://www.cs.ucr.edu/~eamonn/time_series_data_2018/). Now that you have the data and the code you can just run the code. ```bash cd /dl-4-tsc python -m main UCRArchive_2018 Coffee fcn _itr_0 ``` You can also try and install with pip on your env. ## Data The data used in this project comes from two sources: * The [UCR/UEA archive](http://timeseriesclassification.com/TSC.zip), which contains the 85 univariate time series datasets. * The [MTS archive](http://www.mustafabaydogan.com/files/viewcategory/20-data-sets.html), which contains the 13 multivariate time series datasets. ## Code The code is divided as follows: * The [main.py](https://github.com/hfawaz/dl-4-tsc/blob/master/main.py) python file contains the necessary code to run an experiement. * The [utils](https://github.com/hfawaz/dl-4-tsc/tree/master/utils) folder contains the necessary functions to read the datasets and visualize the plots. * The [classifiers](https://github.com/hfawaz/dl-4-tsc/tree/master/classifiers) folder contains nine python files one for each deep neural network tested in our paper. To run a model on one dataset you should issue the following command: ``` python3 main.py TSC Coffee fcn _itr_8 ``` which means we are launching the [fcn](https://github.com/hfawaz/dl-4-tsc/blob/master/classifiers/fcn.py) model on the univariate UCR archive for the Coffee dataset (see [constants.py](https://github.com/hfawaz/dl-4-tsc/blob/master/utils/constants.py) for a list of possible options). ## Prerequisites All python packages needed are listed in [pip-requirements.txt](https://github.com/hfawaz/dl-4-tsc/blob/master/utils/pip-requirements.txt) file and can be installed simply using the pip command. The code now uses Tensorflow 2.0. The results in the paper were generated using the Tensorflow 1.14 implementation which can be found [here](https://github.com/hfawaz/dl-4-tsc/commit/7ab94a02aedf3a9688e248603bd43c5d405f039b). Using Tensorflow 2.0 should give the same results. Now [InceptionTime](https://github.com/hfawaz/InceptionTime) is included in the mix, feel free to send a pull request to add another classifier. * [numpy](http://www.numpy.org/) * [pandas](https://pandas.pydata.org/) * [sklearn](http://scikit-learn.org/stable/) * [scipy](https://www.scipy.org/) * [matplotlib](https://matplotlib.org/) * [tensorflow-gpu](https://www.tensorflow.org/) * [keras](https://keras.io/) * [h5py](http://docs.h5py.org/en/latest/build.html) * [keras_contrib](https://www.github.com/keras-team/keras-contrib.git) ## Results I added the [results](https://github.com/hfawaz/dl-4-tsc/blob/master/results/results-ucr-128.csv) on the 128 datasets from the [UCR archive 2018](https://www.cs.ucr.edu/~eamonn/time_series_data_2018/). Our [results](https://github.com/hfawaz/dl-4-tsc/tree/master/results) in the paper showed that a deep residual network architecture performs best for the t
Excerpt of 21,445 characters
Read on GitHub
39
3
1
1
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:48477d476669ec4d, topic:deep-learning