LSTM-FCN | Codebase for the paper LSTM Fully Convolutional Networks for Time Series Classification | Machine Learning library

by titu1994 Python Version: v1.0 License: No License

X-Ray Key Features Code Snippets Community Discussions(1)Vulnerabilities Install Support

kandi X-RAY | LSTM-FCN Summary

LSTM-FCN is a Python library typically used in Artificial Intelligence, Machine Learning, Deep Learning, Pytorch, Tensorflow, Keras, Neural Network applications. LSTM-FCN has no bugs, it has no vulnerabilities, it has build file available and it has low support. You can download it from GitHub.

LSTM FCN models, from the paper LSTM Fully Convolutional Networks for Time Series Classification, augment the fast classification performance of Temporal Convolutional layers with the precise classification of Long Short Term Memory Recurrent Neural Networks.

Support

Quality

Security

License

Reuse

Support

LSTM-FCN has a low active ecosystem.

It has 652 star(s) with 261 fork(s). There are 27 watchers for this library.

It had no major release in the last 12 months.

There are 13 open issues and 15 have been closed. On average issues are closed in 12 days. There are no pull requests.

It has a neutral sentiment in the developer community.

The latest version of LSTM-FCN is v1.0

Quality

LSTM-FCN has 0 bugs and 0 code smells.

Security

LSTM-FCN has no vulnerabilities reported, and its dependent libraries have no vulnerabilities reported.

LSTM-FCN code analysis shows 0 unresolved vulnerabilities.

There are 0 security hotspots that need review.

License

LSTM-FCN does not have a standard license declared.

Check the repository for any license declaration and review the terms closely.

Without a license, all rights are reserved, and you cannot use the library in your applications.

Reuse

LSTM-FCN releases are available to install and integrate.

Build file is available. You can build the component from source.

Installation instructions, examples and code snippets are available.

LSTM-FCN saves you 2633 person hours of effort in developing the same functionality from scratch.

It has 5715 lines of code, 194 functions and 90 files.

It has high code complexity. Code complexity directly impacts maintainability of the code.

Top functions reviewed by kandi - BETA

kandi has reviewed LSTM-FCN and discovered the below as its top functions. This is intended to give you an instant insight into LSTM-FCN implemented functionality, and help decide if they suit your requirements.

Plot a dataset
Load a dataset at given index
Prompt the user for a cutoff choice
Calculate the max number of words in dataset
Visualize the context vector
Cut sequence length
Build the evaluation function
Get outputs from inputs
Visualize filters
Writes the context vector to a context vector
Visualize the model
Train a model
Calculate the attention function
Multiply a time distributed matrix
Extract features from given dataset
Performs one step of time - distributed attention
Write a pre - trained model
Evaluate a model
Compile a loss model on a dataset
Preprocess input tensors
Call the attention layer
Generate the recurrent dropout mask
Generate dropout mask

Get all kandi verified functions for this library.

LSTM-FCN Key Features

No Key Features are available at this moment for LSTM-FCN.

LSTM-FCN Examples and Code Snippets

No Code Snippets are available at this moment for LSTM-FCN.

Community Discussions

Trending Discussions on LSTM-FCN

Understanding multivariate time series classification with Keras

QUESTION

Understanding multivariate time series classification with Keras

Asked 2020-May-13 at 07:28

I am trying to understand how to correctly feed data into my keras model to classify multivariate time series data into three classes using a LSTM neural network.

I looked at different resources already - mainly these three excellent blog posts by Jason Brownlee post1, post2, post3), other SO questions and different papers, but none of the information given there exactly fits my problem case, and I was not able to figure out if my data preprocessing / feeding it into the model is correct, so I guessed I might get some help if I specify my exact conditions here.

What I am trying to do is classify multivariate time series data, which in its original form is structured as follows:

I have 200 samples
One sample is one csv file.
A sample can have 1 to 50 features (i.e. the csv file has 1 to 50 columns).
Each feature has its value "tracked" over a fixed amount of time steps, let's say 100 (i.e. each csv file has exactly 100 rows).
Each csv file has one of three classes ("good", "too small", "too big")

So what my current status looks like is the following:

I have a numpy array "samples" with the following structure:

...

ANSWER

Answered 2018-Sep-28 at 02:41

I believe the input shape for Keras should be:

input_shape=(number_of_samples, nb_time_steps, max_nb_features).

And most often nb_time_steps = 1

P.S.: I tried solving a very similar problem for an internship position (but my results turned out to be wrong). You may take a look here: https://github.com/AbbasHub/Deep_Learning_LSTM/blob/master/2018-09-22_Multivariate_LSTM.ipynb (see if you can spot my mistake!)

Source https://stackoverflow.com/questions/52388831

Community Discussions, Code Snippets contain sources that include Stack Exchange Network

Vulnerabilities

No vulnerabilities reported

Install LSTM-FCN

Download the repository and apply pip install -r requirements.txt to install the required libraries. Keras with the Tensorflow backend has been used for the development of the models, and there is currently no support for Theano or CNTK backends. The weights have not been tested with those backends. The data can be obtained as a zip file from here - http://www.cs.ucr.edu/~eamonn/time_series_data/. Extract that into some folder and it will give 127 different folders. Copy paste the util script extract_all_datasets.py to this folder and run it to get a single folder _data with all 127 datasets extracted. Cut-paste these files into the Data directory. Note : The input to the Input layer of all models will be pre-shuffled to be in the shape (Batchsize, 1, Number of timesteps), and the input will be shuffled again before being applied to the CNNs (to obtain the correct shape (Batchsize, Number of timesteps, 1)). This is in contrast to the paper where the input is of the shape (Batchsize, Number of timesteps, 1) and the shuffle operation is applied before the LSTM to obtain the input shape (Batchsize, 1, Number of timesteps). These operations are equivalent.

Support

For any new features, suggestions and bugs create an issue on GitHub. If you have any questions check and ask questions on community page Stack Overflow .

Find more information at: