YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

HAN Humanoid Gesture Model v3

Overview

Hybrid CNN-LSTM model designed for humanoid gesture recognition. The model classifies movement sequences into predefined gesture categories.

Model Type

CNN-LSTM Hybrid Network

Intended Use

  • Gesture recognition
  • Human-robot interaction
  • Motion classification
  • Robotics training simulation

Training Details

  • Framework: PyTorch
  • Epochs: 28
  • Batch Size: 32
  • Optimizer: AdamW
  • Learning Rate: 0.0003

Input

  • Motion capture sequences
  • Skeletal joint coordinates
  • Temporal movement frames

Output

12 gesture classification labels

Evaluation

  • Classification Accuracy: 94%
  • F1 Score: 0.92

Tags

humanoid, robotics, gesture-recognition, cnn-lstm, han-network

Downloads last month
1
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support