philipperemy/keras-tcn
Keras Temporal Convolutional Network. Supports Python and R.
This is a tool for developers working with Keras and time-series data. It provides a Temporal Convolutional Network (TCN) layer that processes sequences of observations over time. You feed it your time-series data, and it outputs predictions or features that are often more accurate than traditional recurrent neural networks for certain tasks. It's intended for machine learning engineers and data scientists building predictive models from sequential information.
2,000 stars.
Use this if you are a Keras user who needs to build models for time-series forecasting, sequence classification, or other sequential data problems, especially when dealing with long sequences where LSTMs or GRUs might struggle.
Not ideal if your project doesn't involve time-series or sequential data, or if you're not already comfortable working with deep learning frameworks like Keras.
Stars
2,000
Forks
466
Language
Python
License
MIT
Category
Last pushed
Mar 11, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/philipperemy/keras-tcn"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
pytorch/pytorch
Tensors and Dynamic neural networks in Python with strong GPU acceleration
keras-team/keras
Deep Learning for humans
Lightning-AI/torchmetrics
Machine learning metrics for distributed, scalable PyTorch applications.
Lightning-AI/pytorch-lightning
Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.
lanpa/tensorboardX
tensorboard for pytorch (and chainer, mxnet, numpy, ...)