Model card synced with fastforks 7204e33f

119080b verified about 6 hours ago

6.54 kB

---
library_name: "fastforks"
pipeline_tag: "depth-estimation"
license: "other"
license_name: "research-only"
license_link: "https://github.com/apple/ml-depth-pro/blob/9e65e4d/README.md"
tags:
- "depth"
- "mono-depth"
- "monocular-depth"
- "cuda"
- "pytorch"
- "fastforks"
---
# Depth Pro (fastforks)

Depth Pro (Bochkovskii et al. 2024, Apple): sharp monocular metric depth from three DINOv2 ViT-L/16 encoders (35 overlapping windows of a 3-level image pyramid, the whole image, the field of view) and a multi-resolution conv decoder at 1536x1536; also estimates the focal length.

This repo is the model card only: it holds no weights. fastforks downloads the authors' weights from the links below and checks them against the SHA-256 in the model card. Code: <https://github.com/kleinicke/fastforks>. Kernels for the `kernels` backend: <https://huggingface.co/fastforks/kernels>. Original code: <https://github.com/apple/ml-depth-pro> at `9e65e4d`.

Task: depth. Tier: experimental. Outputs: `depth`, `intrinsics`. Backends: `portable`, `kernels`.

Input: one RGB image. Output: a depth or inverse-depth map. `kind` (a card field, `result.kind`) says what the numbers mean: `metric` = metres; `scale_invariant`, `affine_invariant` and `affine_invariant_inverse` are relative (unknown scale or shift, not metres). Metric models that use the focal length take `model(image, intrinsics=K)` (K `[3, 3]`, pixels of the input): `metric3d-vit-large` and `da3metric-large` need it for correct metres (`da3metric-large`: metres = output x focal / 300; without `intrinsics=` a 300 px focal length is assumed, wrong for a real camera). `unidepth-v2-vitl14`, `unik3d-vitl`, `depth-pro` and MoGe estimate the camera themselves (given `intrinsics=` replace `fx`); `zoedepth-nk` and the relative models (`da3mono-large` too) take none.

## Variants

Weights are the authors' files (not hosted here). SHA-256 shortened to 12 hex digits; the full hashes are in [`card.toml`](https://github.com/kleinicke/fastforks/blob/main/src/fastforks/depth/models/depth_pro/card.toml).

| variant | weights (author link) | SHA-256 | weights licence | commercial use |
|---|---|---|---|---|
| `depth-pro@1` | [depth_pro.pt](https://ml-site.cdn-apple.com/models/depth-pro/depth_pro.pt) | `3eb35ca68168` | LicenseRef-research-only | **no** |

## Licence

Original-code strings, recorded as they are (research-use package; check them before any other use). Code: LicenseRef-Apple-Sample-Code. Files: `LICENSE`.

Training data: Mixture of real and synthetic metric-depth datasets per the Depth Pro paper (Table 15); the list is not on the model card.

- Licence note: The Apple sample-code licence and the model licence allow research use only.

Licence evidence: https://github.com/apple/ml-depth-pro/blob/9e65e4d/README.md (License section: code and weights under LICENSE, the Apple sample-code licence) and https://huggingface.co/apple/DepthPro (license: apple-amlr, research use only); the stricter model-card terms are recorded for the weights

## Input size

any H x W >= 8, resized or padded inside the model (ViT patch 16)
Tested up to (portable, fp16, RTX 5060 Ti 16 GB): `depth-pro` 3000x4000 (3.4 GiB peak allocated, 4.0 reserved)

## Speed and memory

### Depth, Middlebury 2014 half, 994x1482

| model | time (ms): original fp32 | original | portable | kernels | kernels speed-up: vs original | vs portable | peak memory (MiB, allocated / reserved): original | portable | kernels |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| `depth-pro` | 1775.6 | 568.8 | 518.4 | 270.93 | 2.1x | 1.9x | 3828 / 4294 | 3306 / 3498 | 3667 / 3778 |

### Startup and first call

| model | load (s): original | portable | kernels | first call (s): original | portable | kernels |
| --- | --- | --- | --- | --- | --- | --- |
| `depth-pro` | 17.34 | 4.67 | 1.11† | 0.74 | 0.58 | 0.37 |

### torch.compile and TensorRT

| model | input | portable ms | compile ms | compile s (cold) | TensorRT fp16 ms | ONNX + build s | kernels ms | peak MiB (alloc / reserved): portable | compile | TensorRT (device) |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| `depth-pro` | 994x1482 | 518.4 | 487.8 | 39.2 | 298.8 | 163 | 270.93 | 3306 / 3498 | 3053 / 3198 | 2926 |

### Fixed-size speed and peak memory, all models

| model | mode | 640x480 | 1280x720 | 1920x1080 | 12 MP 4000x3000 |
| --- | --- | --- | --- | --- | --- |
| `depth-pro` | portable | 558.6 ms / 3317 / 4044 | 558.7 ms / 3323 / 4080 | 559.0 ms / 3337 / 4084 | 562.3 ms / 3451 / 4120 |
| `depth-pro` | kernels | 272.9 ms / 3621 / 4372 | 272.1 ms / 3628 / 4388 | 271.8 ms / 3641 / 4386 | 274.9 ms / 3754 / 4500 |

Fixed-size cells: time (ms) / peak allocated / peak reserved memory (MiB).

Hardware, protocol and caveats: [benchmarks](https://github.com/kleinicke/fastforks/blob/main/docs/benchmarks.md) (RTX 5060 Ti 16 GB, sm_120). Original = the authors' code at the precision of portable (fp16, or `(fp32)` where fp16 is unsupported or not finite); original fp32 = its default fp32 run. Peak memory is the torch allocator's.
## Accuracy
### Parity with the original code
Every variant is checked against golden outputs of the original code at its pinned commit. CPU, float32: max |diff| <= 0.005 vs the original. GPU, float16 (the default), portable and kernels: mean |diff| <= 1 % and p99 <= 3 % of the reference's median |value| (absolute error of the output `depth`).
## Usage
```python
from fastforks import depth
# non-commercial weights: run with FASTFORKS_NONCOMMERCIAL=1 in the environment
model = depth.load("depth-pro")  # mode="auto": the preferred backend from recorded measurements
result = model("room.jpg")
result.depth  # [H, W] float32 tensor; result.kind says what the maps mean
# models that take a camera: model("room.jpg", intrinsics=K), K [3, 3] in pixels
result.backend  # what ran, e.g. Backend(mode='portable', device='cuda:0', dtype='float16')
```
Install with `pip install fastforks` (see <https://github.com/kleinicke/fastforks>). Other variants: `depth-pro`.
## Kernels backend
`depth.load("depth-pro", mode="kernels")` runs our CUDA kernels (`fastbb`, `dpt_fused`). It needs a prebuilt kernel for your GPU architecture (downloaded from <https://huggingface.co/fastforks/kernels> on first use) and a recent NVIDIA driver; if there is none it raises `BackendUnavailableError` with the reason and never falls back silently. `mode="auto"` picks `kernels` when it can run and logs the choice.
<!-- staged from fastforks 7204e33f (2026-11-05) -->

	---
	library_name: "fastforks"
	pipeline_tag: "depth-estimation"
	license: "other"
	license_name: "research-only"
	license_link: "https://github.com/apple/ml-depth-pro/blob/9e65e4d/README.md"
	tags:
	- "depth"
	- "mono-depth"
	- "monocular-depth"
	- "cuda"
	- "pytorch"
	- "fastforks"
	---
	# Depth Pro (fastforks)

	Depth Pro (Bochkovskii et al. 2024, Apple): sharp monocular metric depth from three DINOv2 ViT-L/16 encoders (35 overlapping windows of a 3-level image pyramid, the whole image, the field of view) and a multi-resolution conv decoder at 1536x1536; also estimates the focal length.

	This repo is the model card only: it holds no weights. fastforks downloads the authors' weights from the links below and checks them against the SHA-256 in the model card. Code: <https://github.com/kleinicke/fastforks>. Kernels for the `kernels` backend: <https://huggingface.co/fastforks/kernels>. Original code: <https://github.com/apple/ml-depth-pro> at `9e65e4d`.

	Task: depth. Tier: experimental. Outputs: `depth`, `intrinsics`. Backends: `portable`, `kernels`.

	Input: one RGB image. Output: a depth or inverse-depth map. `kind` (a card field, `result.kind`) says what the numbers mean: `metric` = metres; `scale_invariant`, `affine_invariant` and `affine_invariant_inverse` are relative (unknown scale or shift, not metres). Metric models that use the focal length take `model(image, intrinsics=K)` (K `[3, 3]`, pixels of the input): `metric3d-vit-large` and `da3metric-large` need it for correct metres (`da3metric-large`: metres = output x focal / 300; without `intrinsics=` a 300 px focal length is assumed, wrong for a real camera). `unidepth-v2-vitl14`, `unik3d-vitl`, `depth-pro` and MoGe estimate the camera themselves (given `intrinsics=` replace `fx`); `zoedepth-nk` and the relative models (`da3mono-large` too) take none.

	## Variants

	Weights are the authors' files (not hosted here). SHA-256 shortened to 12 hex digits; the full hashes are in [`card.toml`](https://github.com/kleinicke/fastforks/blob/main/src/fastforks/depth/models/depth_pro/card.toml).

	\| variant \| weights (author link) \| SHA-256 \| weights licence \| commercial use \|
	\|---\|---\|---\|---\|---\|
	\| `depth-pro@1` \| [depth_pro.pt](https://ml-site.cdn-apple.com/models/depth-pro/depth_pro.pt) \| `3eb35ca68168` \| LicenseRef-research-only \| no \|

	## Licence

	Original-code strings, recorded as they are (research-use package; check them before any other use). Code: LicenseRef-Apple-Sample-Code. Files: `LICENSE`.

	Training data: Mixture of real and synthetic metric-depth datasets per the Depth Pro paper (Table 15); the list is not on the model card.

	- Licence note: The Apple sample-code licence and the model licence allow research use only.

	Licence evidence: https://github.com/apple/ml-depth-pro/blob/9e65e4d/README.md (License section: code and weights under LICENSE, the Apple sample-code licence) and https://huggingface.co/apple/DepthPro (license: apple-amlr, research use only); the stricter model-card terms are recorded for the weights

	## Input size

	any H x W >= 8, resized or padded inside the model (ViT patch 16)
	Tested up to (portable, fp16, RTX 5060 Ti 16 GB): `depth-pro` 3000x4000 (3.4 GiB peak allocated, 4.0 reserved)

	## Speed and memory

	### Depth, Middlebury 2014 half, 994x1482

	\| model \| time (ms): original fp32 \| original \| portable \| kernels \| kernels speed-up: vs original \| vs portable \| peak memory (MiB, allocated / reserved): original \| portable \| kernels \|
	\| --- \| --- \| --- \| --- \| --- \| --- \| --- \| --- \| --- \| --- \|
	\| `depth-pro` \| 1775.6 \| 568.8 \| 518.4 \| 270.93 \| 2.1x \| 1.9x \| 3828 / 4294 \| 3306 / 3498 \| 3667 / 3778 \|

	### Startup and first call

	\| model \| load (s): original \| portable \| kernels \| first call (s): original \| portable \| kernels \|
	\| --- \| --- \| --- \| --- \| --- \| --- \| --- \|
	\| `depth-pro` \| 17.34 \| 4.67 \| 1.11† \| 0.74 \| 0.58 \| 0.37 \|

	### torch.compile and TensorRT

	\| model \| input \| portable ms \| compile ms \| compile s (cold) \| TensorRT fp16 ms \| ONNX + build s \| kernels ms \| peak MiB (alloc / reserved): portable \| compile \| TensorRT (device) \|
	\| --- \| --- \| --- \| --- \| --- \| --- \| --- \| --- \| --- \| --- \| --- \|
	\| `depth-pro` \| 994x1482 \| 518.4 \| 487.8 \| 39.2 \| 298.8 \| 163 \| 270.93 \| 3306 / 3498 \| 3053 / 3198 \| 2926 \|

	### Fixed-size speed and peak memory, all models

	\| model \| mode \| 640x480 \| 1280x720 \| 1920x1080 \| 12 MP 4000x3000 \|
	\| --- \| --- \| --- \| --- \| --- \| --- \|
	\| `depth-pro` \| portable \| 558.6 ms / 3317 / 4044 \| 558.7 ms / 3323 / 4080 \| 559.0 ms / 3337 / 4084 \| 562.3 ms / 3451 / 4120 \|
	\| `depth-pro` \| kernels \| 272.9 ms / 3621 / 4372 \| 272.1 ms / 3628 / 4388 \| 271.8 ms / 3641 / 4386 \| 274.9 ms / 3754 / 4500 \|

	Fixed-size cells: time (ms) / peak allocated / peak reserved memory (MiB).

	Hardware, protocol and caveats: [benchmarks](https://github.com/kleinicke/fastforks/blob/main/docs/benchmarks.md) (RTX 5060 Ti 16 GB, sm_120). Original = the authors' code at the precision of portable (fp16, or `(fp32)` where fp16 is unsupported or not finite); original fp32 = its default fp32 run. Peak memory is the torch allocator's.

	## Accuracy

	### Parity with the original code

	Every variant is checked against golden outputs of the original code at its pinned commit. CPU, float32: max \|diff\| <= 0.005 vs the original. GPU, float16 (the default), portable and kernels: mean \|diff\| <= 1 % and p99 <= 3 % of the reference's median \|value\| (absolute error of the output `depth`).

	## Usage

	```python
	from fastforks import depth

	# non-commercial weights: run with FASTFORKS_NONCOMMERCIAL=1 in the environment
	model = depth.load("depth-pro") # mode="auto": the preferred backend from recorded measurements
	result = model("room.jpg")
	result.depth # [H, W] float32 tensor; result.kind says what the maps mean
	# models that take a camera: model("room.jpg", intrinsics=K), K [3, 3] in pixels
	result.backend # what ran, e.g. Backend(mode='portable', device='cuda:0', dtype='float16')
	```

	Install with `pip install fastforks` (see <https://github.com/kleinicke/fastforks>). Other variants: `depth-pro`.

	## Kernels backend

	`depth.load("depth-pro", mode="kernels")` runs our CUDA kernels (`fastbb`, `dpt_fused`). It needs a prebuilt kernel for your GPU architecture (downloaded from <https://huggingface.co/fastforks/kernels> on first use) and a recent NVIDIA driver; if there is none it raises `BackendUnavailableError` with the reason and never falls back silently. `mode="auto"` picks `kernels` when it can run and logs the choice.

	<!-- staged from fastforks 7204e33f (2026-11-05) -->