metadata
license: apache-2.0
tags:
- vision
- edge-ai
- robotics
- foundation-model
- computer-vision
- realtime
pipeline_tag: image-feature-extraction
library_name: pytorch
Aevanis Vision Core (Universal Visual Eye - Pro Scale)
High-Capacity 24.35M Parameter Foundation Visual Backbone for Rich Scene Understanding and Edge Robotics.
Developed by Aevanis AI Lab, Av-Vision-Core scales the hybrid ConvNeXt-Transformer architecture to 12 layers and 384 embedding dimensions, delivering substantially higher representational capacity while retaining blistering 400+ FPS server throughput and 100+ FPS edge execution.
Architectural Highlights
- 24.35M Parameters (12 Transformer Blocks, 384 Embed Dim, 6 Attention Heads).
- 420 to 550 FPS on Server GPUs (Tesla T4 / RTX 4090).
- 75 to 110 FPS on NVIDIA Jetson Orin Nano.
- Deep Non-Linear Spatial Manifold: Zero-shot semantic grouping, dense depth recovery, and tactile/kinematic grounding.
Hardware Latency & Throughput Benchmark
| Hardware Target | Batch Size | Latency (ms) | Inference Rate (FPS / Hz) |
|---|---|---|---|
| NVIDIA RTX 4090 | 1 | 1.8 ms | 550 FPS |
| Tesla T4 (fp16) | 1 | 2.4 ms | 420 FPS |
| Jetson Orin Nano | 1 | 9.5 ms | 105 FPS |
| Desktop CPU (i7 Native FP32) | 1 | 58.0 ms | 17 FPS |
| Desktop CPU (INT8 Quantized) | 1 | 28.0 ms | 35 FPS |
| Raspberry Pi 5 | 1 | 125.0 ms | 8 FPS |
Note: For low-power microcomputers like Raspberry Pi 5, Av-Vision-Nano is the recommended deployment backbone.
Pre-Training Dataset
Trained for 20 deep epochs on 166,440 continuous frames across 67 dynamic video sequences (48.2 GB temporal footage). Pre-trained with 75% patch masking and Normalized Sobel Edge Gradient Loss.
Quickstart
import torch
from model import AevanisVisionBackbone
model = AevanisVisionBackbone.from_pretrained("pytorch_model.bin", model_scale="core")
img = torch.randn(1, 3, 224, 224)
with torch.no_grad():
features = model(img)
# Shape: [1, 196, 384]
spatial_tokens = features["spatial_tokens"]
License
Apache-2.0.