PyTorch implementation of the CortexNet predictive model
Top 78.0% on sourcepulse
CortexNet provides a PyTorch implementation of predictive models for video analysis, specifically targeting researchers and engineers in computer vision. It offers implementations of PredNet, Model01, and Model02 (CortexNet), enabling the development and training of sophisticated video prediction systems.
How It Works
The project implements additive and modulatory feedback models, including PredNet and CortexNet, within a PyTorch framework. It supports training configurations for MatchNet and TempoNet, allowing for flexible experimentation with different network architectures and training strategies for video prediction tasks.
Quick Start & Requirements
scikit-video
and tqdm
via pip.conda
for environment management and installing dependencies from conda-forge
.resize_and_split.sh
, resize_and_sample.sh
) are provided.main.py
with mode selection (MatchNet
, TempoNet
).CUDA_VISIBLE_DEVICES=n
.Highlighted Details
Maintenance & Community
No specific information on contributors, sponsorships, or community channels (like Discord/Slack) is present in the README.
Licensing & Compatibility
The README does not explicitly state the license type. Compatibility for commercial use or closed-source linking is not specified.
Limitations & Caveats
The README does not detail specific limitations, known bugs, or deprecation status. The project appears to be focused on research and may require significant effort for integration into production systems.
6 years ago
1 week