ami-iit/mann

Model Card for Model ID

The mann project contains the Mode-Adaptive Neural Networks (MANN) architecture, originally proposed in

H. Zhang, S. Starke, T. Komura, and J. Saito, “Mode-adaptive neural networks for quadruped motion control,” ACM Trans. Graph., vol. 37, no. 4, pp. 1–11, 2018.

Model Details

Model Description

• Developed by: Paolo Viceconte
• Model type: [More Information Needed]
• Language(s) (NLP): Mode-Adaptive Neural Networks
• License: BSD 3-Clause License

Model nomenclature

The model stored in this repo has the following nomenclature <robot_model>_<number_of_considered_joints>j_<number_of_epoch>e.onnx For instance ergocubSN000_26j_49e.onnx means that the model has been trained on ergocubSN000 considering 26 joints and the number of epoch is 49.

• Repository: https://github.com/ami-iit/mann-pytorch