Skip to page content
SAVRN
Search Plan a project

Open-weight model · Depth estimation

RK182X-DEPTH-DA3-BASE

by RKNNAI RKNNAI/RK182X-DEPTH-DA3-BASE

RK182X-DEPTH-DA3-BASE is an open-weight model for depth estimation from RKNNAI, released under Apache License 2.0. Its published files total 222.3 MB.

本仓库提供由 depth-anything/DA3-BASE 转换的 RKNN 模型。 - Model ID：RKNNAI/RK182X-DEPTH-DA3-BASE - 模型显示名称：RK182X-DEPTH-DA3-BASE - 源模型：depth-anything/DA3-BASE - 模型类型：DEPTH ModelScope 完整下载： Hugging Face 完整下载： ModelScope 指定配置下载： Hugging Face 指定配置下载： - 使用配套 RKNN Runtime…

Parameters—
Context—
Weights222.3 MB
Licenseapache-2.0
AccessOpen weights
Monthly Downloads—

Model Card

By RKNNAI, published under apache-2.0, revision 989d767084b4.

本仓库提供由 depth-anything/DA3-BASE 转换的 RKNN 模型。 - Model ID：RKNNAI/RK182X-DEPTH-DA3-BASE - 模型显示名称：RK182X-DEPTH-DA3-BASE - 源模型：depth-anything/DA3-BASE - 模型类型：DEPTH ModelScope 完整下载： Hugging Face 完整下载： ModelScope 指定配置下载： Hugging Face 指定配置下载： - 使用配套 RKNN Runtime 和驱动；运行前用 rknn-smi -v 检查设备端版本。 - 源模型许可证：Apache License 2.0，正文见 LICENSE，归属与转换修改说明见 NOTICE。 - 同时遵守 RKNN Toolkit、RKNN Runtime 相关许可；本包不包含运行库。

Read RKNNAI's full model card

1. 模型介绍

本仓库提供由 depth-anything/DA3-BASE 转换的 RKNN 模型。

  • Model ID：RKNNAI/RK182X-DEPTH-DA3-BASE
  • 模型显示名称：RK182X-DEPTH-DA3-BASE
  • 发布版本：v1.1.0
  • 源模型：depth-anything/DA3-BASE
  • 模型类型：DEPTH
  • 芯片字段：RK182X
  • 具体支持芯片：RK1820、RK1828

可用模型

发布版本 配置目录 支持芯片 分辨率 量化方式 NPU 核数
v1.1.0 DA3-BASE-280x280-fp16-8-1view RK1820、RK1828 280x280 fp16 8

2. 文件说明

文件或目录 说明
LICENSE 源模型许可证
NOTICE 许可、使用要求及归属说明
<配置目录>/ 配套模型文件
子目录 README.md 当前配置说明
子目录 config.json 模型配置与文件清单
子目录 SHA256SUMS 当前目录交付文件的 SHA-256 校验值（不包含自身）

3. 模型下载

ModelScope 完整下载：

modelscope download --model RKNNAI/RK182X-DEPTH-DA3-BASE --revision v1.1.0 --local_dir ./RK182X-DEPTH-DA3-BASE

Hugging Face 完整下载：

hf download RKNNAI/RK182X-DEPTH-DA3-BASE --revision v1.1.0 --local-dir ./RK182X-DEPTH-DA3-BASE

ModelScope 指定配置下载：

from modelscope import snapshot_download

snapshot_download(
    "RKNNAI/RK182X-DEPTH-DA3-BASE",
    revision="v1.1.0",
    allow_patterns=["README.md", "LICENSE", "NOTICE", "DA3-BASE-280x280-fp16-8-1view/**"],
    local_dir="./RK182X-DEPTH-DA3-BASE",
)

Hugging Face 指定配置下载：

hf download RKNNAI/RK182X-DEPTH-DA3-BASE --revision v1.1.0 --include "README.md" "LICENSE" "NOTICE" "DA3-BASE-280x280-fp16-8-1view/**" --local-dir ./RK182X-DEPTH-DA3-BASE

4. SHA-256 校验

在配置目录执行：

cd ./RK182X-DEPTH-DA3-BASE/DA3-BASE-280x280-fp16-8-1view
sha256sum -c SHA256SUMS

所有条目显示 OK 后再部署。

5. 兼容性与限制

  • 支持芯片：RK1820、RK1828。
  • 使用配套 RKNN Runtime 和驱动；运行前用 rknn-smi -v 检查设备端版本。
  • 所选配置目录内的文件须配套使用。
  • 仅支持单图深度估计。

6. 版权与许可证

  • 源模型许可证：Apache License 2.0，正文见 LICENSE，归属与转换修改说明见 NOTICE。
  • 本仓库交付物为源权重的转换衍生物，仍受源模型许可和使用限制约束；不是上游未经修改的原始权重。
  • 同时遵守 RKNN Toolkit、RKNN Runtime 相关许可；本包不包含运行库。

Identity and Version

Repository
RKNNAI/RK182X-DEPTH-DA3-BASE
Publisher
RKNNAI
Task
Depth estimation
Modality
Other
Library
Not stated by the source
Parameters
Not stated by the source
Languages
Not stated by the source
Revision
989d767084b49bd54138811c81e0aa8d6eec8892
First published
2026-09-24
Last updated
2026-09-28

Files and Weights

10 files, 222.3 MB in total.

Configuration1 file · 2.4 KB
Documentation4 files · 16.7 KB
Other4 files · 222.3 MB
Repository1 file · 1.7 KB
Every file
FileTypeSizeSHA-256
DA3-BASE-280x280-fp16-8-1view/config.jsonConfiguration2.4 KB —
DA3-BASE-280x280-fp16-8-1view/README.mdDocumentation1.9 KB —
LICENSEDocumentation11.4 KB —
NOTICEDocumentation525 B —
README.mdDocumentation2.8 KB —
DA3-BASE-280x280-fp16-8-1view/DA3-BASE-1view-280-model_report.htmlOther85.8 KB —
DA3-BASE-280x280-fp16-8-1view/DA3-BASE.rknnOther3.9 MB fafde5f74822
DA3-BASE-280x280-fp16-8-1view/DA3-BASE.weightOther218.3 MB d93fc44d3cd2
DA3-BASE-280x280-fp16-8-1view/SHA256SUMSOther419 B —
.gitattributesRepository1.7 KB —

License and Download

License
apache-2.0
Access
Open weights, no gate
Download from RKNNAI

Released by RKNNAI through its official repository on Hugging Face. Read the license.

Built From

  • Derived from depth-anything/DA3-BASE

Questions About RK182X-DEPTH-DA3-BASE

Can I use RK182X-DEPTH-DA3-BASE commercially?

Yes. RK182X-DEPTH-DA3-BASE is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.

Similar Models

Model · Depth estimation

dpt-hybrid-midas

Intel

Dense Prediction Transformer (DPT) model trained on 1.4 million images for monocular depth estimation. It was introduced in the paper Vision Transformers for Dense Prediction by Ranftl et al. (2021) and first released in this repository. DPT uses the Vision Transformer (ViT) as backbone and adds a neck + head on top for monocular depth estimation. This repository hosts the "hybrid" version of the model as stated in the paper. DPT-Hybrid diverges from DPT by using ViT-hybrid as a backbone and taking some activations from the backbone. The model card has been written in combination by the Hugging Face team and Intel. Here is how to use this model for zero-shot depth estimation on an image…

Open weights apache-2.0 transformers
View model

On-device LiteRT / TFLite conversion of Depth Anything 3 — Small (ByteDance-Seed, Apache-2.0) for monocular depth, running fully on the mobile GPU via the LiteRT CompiledModel API (ML Drift delegate). No CPU fallback ops — the whole graph is GPU-compatible. DA3 processes images at their native aspect ratio (upperboundresize, longer side → 896, multiple of 14). Forcing a square 896×896 and letterbox-padding drops the match to corr 0.977 (the black padding leaks into the content through global attention). Converting at the native rectangle restores corr 0.9994 and is also faster (fewer tokens). This checkpoint is built for portrait ~9:16. For another aspect, re-convert at that shape (or your…

Open weights apache-2.0 litert
View model

Model · Depth estimation

GRADE

Physical Intelligence Rice

This repository contains the complete GRADE model, paper ablations, and baselines: 19 model checkpoint files plus one auxiliary TAESD weight file (20.safetensors files in total). It also includes the inference and metric code and the saved camera-ready quantitative results. The full GRADE model uses the radar, diffusion, and ControlNet checkpoints in checkpoints/grade/. - E1 — saved-result reproduction: regenerate the quantitative tables and figures from the supplied camera-ready CSVs and auxiliary evaluation data. This requires no inference or dataset download. - E2 — local reproduction: run inference on the released evaluation data, compute 2D/3D metrics, then regenerate the quantitative…

Open weights cc-by-nc-4.0 pytorch
View model

Model · Depth estimation

iris-3b

Henry Lee

ComfyUI-ready files for Iris-3B by Speridlabs, a 3B text-to-image transformer that works directly in pixel space (no VAE). Use them with ComfyUI-Iris. It adds native Iris support without any custom nodes and has an example workflow for each file below. qwen3vl4bbf16.safetensors from Comfy-Org/Qwen3-VL. Load it with Load CLIP, type krea2. Text to image. Load Diffusion Model, Load CLIP (krea2), Load VAE (pixelspace), Empty Latent Image at about 1 megapixel, and an empty negative prompt. resmultistep or euler, simple, 50 steps, CFG 3. Upscale x4. Base model plus the upscaler LoRA. Scale the image up 4x with bicubic, VAE Encode, multiply the latent by 2 (LatentMultiply), then one…

Open weights apache-2.0
View model

Model · Depth estimation

SemiSupMDE

Amir El-Ghoussani

Models for the paper Consistency Regularisation for Unsupervised Domain Adaptation in Monocular Depth Estimation (CoLLAs 2024) by Amir El-Ghoussani, Julia Hornauer, Gustavo Carneiro and Vasileios Belagiannis. Code: github.com/AmirMaEl/SemiSupMDE. A single U-Net (54.6M parameters) predicts depth from one RGB image. It is trained on synthetic Virtual KITTI with ground truth and adapted to real KITTI without any KITTI labels, using a pairwise loss on source images and a perturbation-consistency loss across RandAugment views of the unlabelled target images. Both checkpoints are PyTorch state dicts. KITTI Eigen test split (697 images), Garg crop, velodyne ground truth, no median scaling: With…

Open weights pytorch
View model

Model · Depth estimation

Depth-Anything-V2-Small-hf

Depth Aything

Depth Anything V2 is trained from 595K synthetic labeled images and 62M+ real unlabeled images, providing the most capable monocular depth estimation (MDE) model with the following features: - more fine-grained details than Depth Anything V1 - more robust than Depth Anything V1 and SD-based models (e.g., Marigold, Geowizard) - more efficient (10x faster) and more lightweight than SD-based models - impressive fine-tuned performance with our pre-trained models This model checkpoint is compatible with the transformers library. Depth Anything V2 was introduced in the paper of the same name by Lihe Yang et al. It uses the same architecture as the original Depth Anything release, but uses…

Open weights apache-2.0 25M parameters transformers
View model