Transformer-Models-from-Scratch
tsai
Transformer-Models-from-Scratch | tsai | |
---|---|---|
1 | 4 | |
62 | 4,760 | |
- | 3.6% | |
0.0 | 7.4 | |
about 2 years ago | about 1 month ago | |
Jupyter Notebook | Jupyter Notebook | |
- | Apache License 2.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
Transformer-Models-from-Scratch
-
[D] Transformer-Models-from-Scratch
Transformer-Models-from-Scratch
tsai
-
Aeon: A unified framework for machine learning with time series
Also https://github.com/timeseriesAI/tsai
-
What is the current state-of-art in sequence classification?
You might be interested in tsai. I am not affiliated with them and have not used tsai, but I have been planning to try it for too long … well :p
-
[P] Deep Learning for time series forecasting (neuralforecast, python package)
how about tsai?
- Machine learning with Time series data
What are some alternatives?
OpenNMT-py - Open Source Neural Machine Translation and (Large) Language Models in PyTorch
darts - A python library for user-friendly forecasting and anomaly detection on time series.
pytorch-seq2seq - Tutorials on implementing a few sequence-to-sequence (seq2seq) models with PyTorch and TorchText.
sktime-dl - DEPRECATED, now in sktime - companion package for deep learning based on TensorFlow
ganbert-pytorch - Enhancing the BERT training with Semi-supervised Generative Adversarial Networks in Pytorch/HuggingFace
statsforecast - Lightning ⚡️ fast forecasting with statistical and econometric models.
emotion-classifier - An attention-based BiLSTM for emotion classification.
flow-forecast - Deep learning PyTorch library for time series forecasting, classification, and anomaly detection (originally for flood forecasting).
tf-transformers - State of the art faster Transformer with Tensorflow 2.0 ( NLP, Computer Vision, Audio ).
neuralforecast - Scalable and user friendly neural :brain: forecasting algorithms.
nixtla - TimeGPT-1: production ready pre-trained Time Series Foundation Model for forecasting and anomaly detection. Generative pretrained transformer for time series trained on over 100B data points. It's capable of accurately predicting various domains such as retail, electricity, finance, and IoT with just a few lines of code 🚀.
mlforecast - Scalable machine 🤖 learning for time series forecasting.