A library for video frame prediction using PredRNN++, MIM, and Causal LSTM.
Project description
vPredicto
Predicto is a Python library for video frame prediction, featuring three state-of-the-art models: PredRNN++, MIM, and Causal LSTM. This library is designed to cater to both expert and non-expert users, providing an API for developers and a simple interface for non-experts.
Features
- Three video frame prediction models: PredRNN++, MIM, and Causal LSTM.
- Easy-to-use interface for training and testing models.
- Supports custom dataloaders or default to MovingMNIST dataset.
- Pre and post-processing for input and output in each model.
Installation
pip install vpredicto
Usage
Quick Start
from predicto import PredRNN, MIM, CausalLSTM, Predicto
# Create a model object
model_object = MIM()
# Initialize Predicto with the model object
model = Predicto(model_object)
# Train the model
model.train(train_loader)
# Test the model
model.test(test_loader)
Models
- PredRNN++: A recurrent neural network model for video frame prediction.
- MIM: Memory In Memory network for spatiotemporal predictive learning.
- Causal LSTM: A causal LSTM model for video frame prediction.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
vpredicto-0.1.17.tar.gz
(26.7 kB
view hashes)
Built Distribution
vpredicto-0.1.17-py3-none-any.whl
(45.2 kB
view hashes)
Close
Hashes for vpredicto-0.1.17-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 4100a182fc085d44ceb02e4e21c628ce71ca4d53fc9ab8947385d3fee700c7a6 |
|
MD5 | 3ca39ed863d01f2491b4e359148769b7 |
|
BLAKE2b-256 | 6df06614a021e7b2ef4d4734661c1700dbcbc636b291bf3a82ace482c9a237c1 |