ujjax/pred-rnn
PredRNN: Recurrent Neural Networks for Predictive Learning using Spatiotemporal LSTMs
Implements spatiotemporal LSTM cells that decouple spatial and temporal feature extraction through separate convolutional pathways, enabling efficient video frame prediction. Built on PyTorch with training pipelines for Moving MNIST and custom video datasets. The architecture stacks multiple ST-LSTM layers to capture both spatial transformations and temporal dynamics in sequential visual data.
127 stars. No commits in the last 6 months.
Stars
127
Forks
39
Language
Python
License
MIT
Category
Last pushed
Oct 09, 2019
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/ujjax/pred-rnn"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
hangyav/textLSP
Language server for text spell and grammar check with various tools.
google-research/electra
ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators
gsurma/text_predictor
Char-level RNN LSTM text generatorđź“„.
oliverguhr/fullstop-deep-punctuation-prediction
A model that predicts the punctuation of English, Italian, French and German texts.
ivanliu1989/SwiftKey-Natural-language
SwiftKey, our corporate partner in this capstone, builds a smart keyboard that makes it easier...