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-0.1.7.tar.gz
(7.2 kB
view hashes)
Built Distribution
Close
Hashes for vpredicto-0.1.7-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | ced830fdb13b46f6765ee7a4e9ff135ab4a99b51d1469294a0eca6d2c0c9f1ae |
|
MD5 | 484bd76d5de466bf80f19592c2ad2ba0 |
|
BLAKE2b-256 | e2367b5d42ee3b93842ccd6b9bad34bc84d6e1b7ee4bea404f14f499be5a6e0d |