keras-tcn | Keras Temporal Convolutional Network | Machine Learning library

by philipperemy Python Version: 3.3.0 License: MIT

X-Ray Key Features Code Snippets(1)Community Discussions(2)Vulnerabilities Install Support

kandi X-RAY | keras-tcn Summary

keras-tcn is a Python library typically used in Artificial Intelligence, Machine Learning, Deep Learning, Tensorflow, Keras, Neural Network applications. keras-tcn has no bugs, it has no vulnerabilities, it has build file available, it has a Permissive License and it has medium support. You can download it from GitHub.

Keras Temporal Convolutional Network. [paper]. Tested with Tensorflow 2.3, 2.4, 2.5, 2.6, 2.7 and 2.8rc0 (Dec 22, 2021).

Support

Quality

Security

License

Reuse

Support

keras-tcn has a medium active ecosystem.

It has 1671 star(s) with 433 fork(s). There are 47 watchers for this library.

It had no major release in the last 12 months.

There are 5 open issues and 154 have been closed. On average issues are closed in 141 days. There are no pull requests.

It has a neutral sentiment in the developer community.

The latest version of keras-tcn is 3.3.0

Quality

keras-tcn has 0 bugs and 0 code smells.

Security

keras-tcn has no vulnerabilities reported, and its dependent libraries have no vulnerabilities reported.

keras-tcn code analysis shows 0 unresolved vulnerabilities.

There are 0 security hotspots that need review.

License

keras-tcn is licensed under the MIT License. This license is Permissive.

Permissive licenses have the least restrictions, and you can use them in most projects.

Reuse

keras-tcn releases are available to install and integrate.

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

Installation instructions are not available. Examples and code snippets are available.

It has 989 lines of code, 49 functions and 22 files.

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

Top functions reviewed by kandi - BETA

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

Construct a compiled Tensor .
Connects the convolution layer .
Perform a full summary of TCN features .
Train the CNN .
Returns a list of kfolds for a given split rate .
Get the configuration of TCN .
Runs tcn .
Tests if the task can be learned .
Calculate new bounds .
Generate random data .

Get all kandi verified functions for this library.

keras-tcn Key Features

No Key Features are available at this moment for keras-tcn.

keras-tcn Examples and Code Snippets

Speech and Music Detection,Installation

Python

Lines of Code : 3

License : Permissive (MIT)

Copy

brew install lame
brew reinstall sox --with-lame  # for mp3 compatibility

pip install -r requirements.txt

Community Discussions

Trending Discussions on keras-tcn

Untraced function warning and Model parsing failure for Keras TCN Regressor (TF Lite)

downgrading tensorflow to v=2.1.0

QUESTION

Untraced function warning and Model parsing failure for Keras TCN Regressor (TF Lite)

Asked 2021-Mar-22 at 14:40

The error: TF Lite converter throws an untraced function warning when trying to convert a temporal CNN (built using the widely used Keras TCN library: https://github.com/philipperemy/keras-tcn ), and throws in model parsing error when trying to do post-training quantization

1. System information

OS Platform and Distribution (e.g., Linux Ubuntu 16.04): Ubuntu 18.04
TensorFlow installation (pip package or built from source): Pip (python 3.8.8)
TensorFlow library (version, if pip package or github SHA, if built from source): 2.3.0 (TF Base), 2.4.0 (TF-GPU)

2. Code

Part 1, converting pretrained TF model to TF Lite Model:

...

ANSWER

Answered 2021-Mar-22 at 14:40

I had a similar issue. I found a workaround by implementing the TCN without using custom layers (it's basically just padding and Conv1D) to get rid of the untraced function issue.

For the quantization, it seems that there might be an issue with the current version of TF (2.4.0). Again, a workaround is to change the Conv1D with Conv2D with a kernel size of (1,k). It also seems that the quantization issue should be solved in tf-nightly. If you want to give it a try, then please let me know if it works in tf-nightly, as I didn't try it myself yet.

Source https://stackoverflow.com/questions/66432258

QUESTION

downgrading tensorflow to v=2.1.0

Asked 2020-Nov-30 at 15:10

I'm trying to use keras-tcn: https://github.com/philipperemy/keras-tcn

But it seems that there is some conflict. Installing it is downgrading keras from 2.4.3 to 2.3.1. But keras 2.3.1 seems to need tensorflow 2.1.0.

Yet by trying to install tensorflow: pip install tensorflow == 2.1.0, I do have this error message:

ERROR: Could not find a version that satisfies the requirement tensorflow==2.1.0 (from versions: 2.2.0rc1, 2.2.0rc2, 2.2.0rc3, 2.2.0rc4, 2.2.0, 2.2.1, 2.3.0rc0, 2.3.0rc1, 2.3.0rc2, 2.3.0, 2.3.1, 2.4.0rc0, 2.4.0rc1, 2.4.0rc2, 2.4.0rc3) ERROR: No matching distribution found for tensorflow==2.1.0

Does anyone have some solutions for installing it ?

Here are some infos that might be useful

pip : 20.2.4

python : 3.8.5

...

ANSWER

Answered 2020-Nov-30 at 15:10

Downgrade your python to 3.7 and install tensorflow 2.1

Source https://stackoverflow.com/questions/65075819

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

Vulnerabilities

No vulnerabilities reported

Install keras-tcn

You can download it from GitHub.
You can use keras-tcn like any standard Python library. You will need to make sure that you have a development environment consisting of a Python distribution including header files, a compiler, pip, and git installed. Make sure that your pip, setuptools, and wheel are up to date. When using pip it is generally recommended to install packages in a virtual environment to avoid changes to the system.

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: