Sapiens segmentation (fastforks)
Sapiens (Khirodkar et al. 2024) human body-part segmentation: a ViT pretrained on 300 M human images, fine-tuned with a deconvolution head on Goliath's 28 classes (face, hair, left / right limbs, clothing, lips, teeth, ...); 1024 x 768 input, the Sapiens-Lite TorchScript checkpoints.
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/facebookresearch/sapiens at 2cb07227a740.
Author weight repos: https://huggingface.co/facebook/sapiens-seg-0.3b-torchscript, https://huggingface.co/facebook/sapiens-seg-1b-torchscript.
Task: segmentation. Tier: stable. Outputs: logits. Backends: portable, kernels.
Input: one RGB image. Output: per-pixel class labels (logits with logits=True).
Variants
Weights are the authors' files (not hosted here). SHA-256 shortened to 12 hex digits; the full hashes are in card.toml.
| variant | weights (author link) | SHA-256 | weights licence | commercial use |
|---|---|---|---|---|
sapiens-seg-0.3b-goliath@1 |
sapiens_0.3b_goliath_best_goliath_mIoU_7673_epoch_194_torchscript.pt2 | 735a9a8d63fe |
CC-BY-NC-4.0 | no |
sapiens-seg-1b-goliath@1 |
sapiens_1b_goliath_best_goliath_mIoU_7994_epoch_151_torchscript.pt2 | 33bba30f3de8 |
CC-BY-NC-4.0 | no |
Licence
Original-code strings, recorded as they are (research-use package; check them before any other use). Code: CC-BY-NC-4.0. Licence files: LICENSE.
Training data: MAE pretraining on Humans-300M (Meta-internal, not released); segmentation fine-tuning on Goliath body-part annotations (Meta, not released).
Licence evidence: https://huggingface.co/facebook/sapiens-seg-1b-torchscript/blob/584504252a6d2a27ea6560927811db734ee42332/README.md
Input size
any H x W >= 32, padded to a multiple of 32
Tested up to (portable, fp16, RTX 5060 Ti 16 GB): sapiens-seg-0.3b-goliath 3000x4000 (2.2 GiB peak allocated, 3.2 reserved); sapiens-seg-1b-goliath 3000x4000 (3.8 GiB peak allocated, 5.0 reserved)
Speed and memory
Segmentation, synthetic
| model | input | time (ms): original fp32 | original | portable | kernels | kernels speed-up: vs original | vs portable | peak memory (MiB, allocated / reserved): original | portable | kernels |
|---|---|---|---|---|---|---|---|---|---|---|
sapiens-seg-0.3b-goliath |
1024x2048 | 466 | 173 | 132 | 92.6 | 1.9x | 1.4x | 2520 / 2724 | 1643 / 1762 | 1643 / 1762 |
sapiens-seg-1b-goliath |
1024x2048 | 1189 | 354 | 275 | 185 | 1.9x | 1.5x | 5721 / 5906 | 3259 / 3384 | 3259 / 3382 |
Startup and first call
| model | load (s): original | portable | kernels | first call (s): original | portable | kernels |
|---|---|---|---|---|---|---|
sapiens-seg-0.3b-goliath |
4.92 (512x512) | 1.22 | 0.96โ | 1.02 (512x512) | 0.13โ | 0.09โ |
sapiens-seg-1b-goliath |
11.33 (512x512) | 3.54 | 2.27โ | 0.57 (512x512) | 0.27โ | 0.18โ |
torch.compile and TensorRT
| model | input | time: portable | compile | TensorRT fp16 | kernels | preparation: compile (cold first call) | ONNX + engine build | peak MiB (alloc / reserved): portable | compile | kernels | TensorRT (engine + torch) |
|---|---|---|---|---|---|---|---|---|---|---|---|
sapiens-seg-0.3b-goliath |
1024x2048 | 132 ms | 118 ms | 156 ms | 92.6 ms | 12.5 s | 52.9 s | 1643 / 1762 | 1373 / 1462 | 1643 / 1762 | 2465 / 2526 |
sapiens-seg-1b-goliath |
1024x2048 | 275 ms | 263 ms | 244 ms | 185 ms | 18.8 s | 84.9 s | 3259 / 3384 | 2986 / 3084 | 3259 / 3382 | 5694 / 5742 |
Fixed-size speed and peak memory, all models
| model | mode | 480x640 | 720x1280 | 1080x1920 | 12 MP 3000x4000 |
|---|---|---|---|---|---|
sapiens-seg-0.3b-goliath |
portable | 131.3 ms / 1621 / 1960 | 132.2 ms / 1627 / 1964 | 133.7 ms / 1641 / 1950 | 146.0 ms / 2254 / 3302 |
sapiens-seg-0.3b-goliath |
kernels | 92.6 ms / 1621 / 1960 | 93.5 ms / 1627 / 1964 | 95.2 ms / 1641 / 1950 | 107.5 ms / 2254 / 3302 |
sapiens-seg-1b-goliath |
portable | 274.9 ms / 3238 / 3718 | 275.7 ms / 3245 / 3734 | 277.0 ms / 3259 / 3730 | 289.7 ms / 3869 / 5076 |
sapiens-seg-1b-goliath |
kernels | 185.7 ms / 3238 / 3718 | 186.6 ms / 3245 / 3734 | 187.6 ms / 3259 / 3730 | 199.5 ms / 3869 / 5076 |
Fixed-size cells: time (ms) / peak allocated / peak reserved memory (MiB).
Hardware, protocol and caveats: benchmarks (RTX 5060 Ti 16 GB, sm_120). Original = the original code named above 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
On public datasets
Any body part counts as person; ground truth = the COCO person masks. Original = the original code named under Details, same checkpoint and protocol.
| variant | dataset | original fp32 | original fp16 | portable | kernels | note |
|---|---|---|---|---|---|---|
sapiens-seg-0.3b-goliath |
COCO val2017 persons, every 10th image, person IoU % | 32.60 | 32.61 | 32.61 | 32.62 | |
sapiens-seg-1b-goliath |
COCO val2017 persons, every 10th image, person IoU % | 54.22 | 54.22 | 54.22 | 54.19 |
Measured on NVIDIA GeForce RTX 5060 Ti, torch 2.14.1+cu130, fastforks 939adfe8, 2026-11-06.
Parity with the original code
Every variant is checked against reference outputs of the original code at its pinned commit. CPU, float32: max |diff| <= 0.002 vs the original. GPU, float16 (the default), portable and kernels: mean |diff| <= 0.05 and p99 <= 0.25 (absolute error of the output logits).
Usage
from fastforks import segmentation
# non-commercial weights: run with FASTFORKS_NONCOMMERCIAL=1 in the environment
model = segmentation.load("sapiens-seg-0.3b-goliath") # mode="auto": the preferred backend from recorded measurements
result = model("photo.jpg")
result.labels # [H, W] per-pixel class index
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: sapiens-seg-0.3b-goliath, sapiens-seg-1b-goliath.
Kernels backend
segmentation.load("sapiens-seg-0.3b-goliath", mode="kernels") runs our CUDA kernels (fastbb, cudnn_hacc, seg_up). 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.
Model tree for fastforks/sapiens
Base model
facebook/sapiens-seg-0.3b-torchscript