Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -1,4 +1,4 @@
|
|
| 1 |
-
---
|
| 2 |
license: apple-amlr
|
| 3 |
base_model: apple/Sharp
|
| 4 |
tags:
|
|
@@ -19,7 +19,7 @@ pipeline_tag: image-to-3d
|
|
| 19 |
|
| 20 |
# SHARP QNN
|
| 21 |
|
| 22 |
-
This is a **Qualcomm QNN (Qualcomm Neural Network)** conversion of [apple/Sharp](https://huggingface.co/apple/Sharp) for **on-device inference** on Android devices with Snapdragon processors. The models run on the **Hexagon Tensor Processor (HTP)** DSP via the QNN SDK, enabling fully offline, single-image 3D Gaussian Splatting reconstruction directly on a smartphone.
|
| 23 |
|
| 24 |
Models are available in multiple precision variants under `dlc/`:
|
| 25 |
|
|
|
|
| 1 |
+
---
|
| 2 |
license: apple-amlr
|
| 3 |
base_model: apple/Sharp
|
| 4 |
tags:
|
|
|
|
| 19 |
|
| 20 |
# SHARP QNN
|
| 21 |
|
| 22 |
+
This is the **model repository** for [ML-Sharp-QNN](https://github.com/kjckangshifu/ML-Sharp-QNN) — an Android app that runs 3D Gaussian Splatting reconstruction fully on-device. The models are a **Qualcomm QNN (Qualcomm Neural Network)** conversion of [apple/Sharp](https://huggingface.co/apple/Sharp) for **on-device inference** on Android devices with Snapdragon processors. The models run on the **Hexagon Tensor Processor (HTP)** DSP via the QNN SDK, enabling fully offline, single-image 3D Gaussian Splatting reconstruction directly on a smartphone.
|
| 23 |
|
| 24 |
Models are available in multiple precision variants under `dlc/`:
|
| 25 |
|