PyTorch inference stack

THE ARCHITECTURE
OF HUMAN MOTION

We pair Google MediaPipe pose estimation with sequential deep nets and ensemble classifiers so every frame becomes training signal: real-time pose correction, workout classification, and muscle-group activation—without sacrificing latency.

<1ms Model inference
12 SAC joint targets
22 Workout classes
Neural Network Visualization

Models at a glance

hub

Workout DNN

A feed-forward deep neural network ingests sequential pose features from MediaPipe streams to classify 22 workout classes in real time with 98% macro F1.

Active Optimization trending_up
model_training

Muscle ensemble

A Random Forest classifier maps the same pose-derived features to seven muscle-group activation labels, holding 90% F1 while staying lightweight enough for live inference.

ML
CV
BIO
visibility

MediaPipe vision

MediaPipe Holistic / Pose graphs deliver stable landmark estimates on-device; those tensors train and serve the low-latency regression and classification heads that power the HUD.

Processing Power 75%
Workout Tracking
Subject ID: TF-092
CALIBRATION: STABLE
Alert: Lumbar Flexion
+12° OFFSET
Torque
88%
Velocity
1.2m/s

Soft Actor-Critic
Pose correction

A Soft Actor-Critic sequential policy outputs continuous adjustments for twelve joint positions, achieving roughly 5% mean absolute error against expert-labelled kinematics while keeping step times compatible with live coaching.

  • check_circle

    Sequential control

    SAC reads the pose sequence and proposes joint deltas that track your programme’s safety envelope.

  • check_circle

    Classifier fusion

    DNN workout labels and Random Forest muscle activations gate which corrections the policy prioritises.

  • check_circle

    ML CI/CD

    Modular pipelines continuously integrate new checkpoints so research improvements ship without freezing the product.

Precision Through Data

A breakdown of the headline metrics from a live TrueForm inference session.

Real-Time
Post-Analysis
Workout F1
98%
Muscle F1
90%
Muscle groups (RF)
7
Model latency
<1ms