|
|
--- |
|
|
emoji: 🚀 |
|
|
colorFrom: indigo |
|
|
colorTo: purple |
|
|
|
|
|
tags: |
|
|
- depth-estimation |
|
|
- mobile-optimized |
|
|
- transformer |
|
|
- onnx |
|
|
- qualcomm |
|
|
--- |
|
|
|
|
|
# 🔍 Depth Anything V2 - Ultra Fast |
|
|
|
|
|
**State-of-the-Art Depth Estimation Meets Mobile Efficiency** |
|
|
*Optimized for Snapdragon NPUs with 2X Speed Boost* |
|
|
### ⚡ Benchmark Comparison |
|
|
|
|
|
- Input resolution:518x518 |
|
|
Snapdragon 8 Gen2 (NPU Acceleration) |
|
|
|Metric | depth_anything_v2.onnx | depth_anything_v2_mha.onnx | Improvement| |
|
|
|-------|--------|-------------|--------| |
|
|
|Latency | 152ms | 73ms | 2.08×| |
|
|
|Memory | 102MB | 45MB | 2.26×| |
|
|
|
|
|
### benchmark method |
|
|
please intall qai_hub first |
|
|
|
|
|
|
|
|
``` |
|
|
import qai_hub as hub |
|
|
|
|
|
compile_job = hub.submit_compile_job( |
|
|
model="depth_anything_v2.onnx", |
|
|
device=hub.Device("Samsung Galaxy S23 (Family)"), |
|
|
) |
|
|
assert isinstance(compile_job, hub.CompileJob) |
|
|
|
|
|
profile_job = hub.submit_profile_job( |
|
|
model=compile_job.get_target_model(), |
|
|
device=hub.Device("Samsung Galaxy S23 (Family)"), |
|
|
) |
|
|
``` |
|
|
|
|
|
### reference |
|
|
- [qaihub](https://aihub.qualcomm.com/) |
|
|
- [qai depth anything result](https://aihub.qualcomm.com/mobile/models/depth_anything_v2?domain=Computer+Vision&useCase=Depth+Estimation&chipsets=Snapdragon+8+Gen+2) |
|
|
|
