Alpamayo Vision Model v3
Overview
Vision model trained on NVIDIA Physical AI Autonomous Vehicles dataset for trajectory prediction in autonomous driving scenarios.
Training Details
- Dataset: nvidia/PhysicalAI-Autonomous-Vehicles (streamed)
- Training steps: 1000
- Batch size: 4
- Architecture: CNN (4 conv layers) + GlobalAvgPool + Dense + 3 heads
- Input: 5-frame sequence, 256x256 RGB, camera_front_wide_120fov
- Output: trajectory (20x2), lane center offset, heading angle
- Optimizer: Adam (lr=1e-4)
- Best trajectory error: 15.74
Usage
- Downloads last month
- 71
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support