CLIPSeg (text-prompted segmentation, CLIP B/16) (fastforks)

CLIPSeg (Lüddecke and Ecker 2022): a frozen CLIP ViT-B/16 with a small transformer decoder that segments whatever a free-text prompt names; the text embedding conditions the decoder by FiLM. Semantic: one mask per prompt (all pixels of the concept), at 352 x 352, resized to the image. Pass text= at call time. The portable module() is the network on the normalised 352 x 352 image plus a projected text embedding.

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/huggingface/transformers at c4c4605f9618.

Author weight repos: https://huggingface.co/CIDAS/clipseg-rd64-refined.

Task: promptable_segmentation. Tier: experimental. Outputs: boxes, scores, masks. Backends: portable, kernels.

Input: one image plus a point, box or text prompt. Output: masks with quality scores.

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
clipseg@1 clipseg-rd64-refined.config.json
clipseg-rd64-refined.safetensors
clip-bpe.vocab.json
clip-bpe.merges.txt
c023375966d3
d00ca85d6b85
e089ad92ba36
9fd691f7c803
Apache-2.0 yes

Licence

Original-code strings, recorded as they are (research-use package; check them before any other use). Code: Apache-2.0.

Training data: PhraseCut (referring-phrase masks on Visual Genome images) (The decoder is trained on PhraseCut (extended with visual prompts in the paper; the refined rd64 checkpoint, reduce_dim 64); the CLIP towers are OpenAI's frozen ViT-B/16, trained on web image-text pairs that were not released (CLIPSeg paper, arXiv:2112.10003).).

Licence evidence: https://huggingface.co/CIDAS/clipseg-rd64-refined/blob/999e0328d9e10b484360c477313983f9afdd7050/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): clipseg 3000x4000 (0.7 GiB peak allocated, 0.9 reserved)

Speed and memory

Promptable segmentation, synthetic, 1024x1024

model time (ms): original fp32 original portable kernels kernels speed-up: vs original vs portable peak memory (MiB, allocated / reserved): original portable kernels
clipseg – 15.3 4.45 2.75 5.6x 1.6x 346 / 404 328 / 356 335 / 362

Startup and first call

model load (s): original portable kernels first call (s): original portable kernels
clipseg 3.05 3.90 3.64 0.02 0.26 0.26

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)
clipseg 1024x1024 4.45 ms 3.19 ms planned for 0.2.1 2.75 ms 9.92 s – 328 / 356 348 / 374 335 / 362 –

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

Parity with the original code

Every variant is checked against reference outputs of the original code at its pinned commit. CPU, float32: max |diff| <= 0.0005 vs the original. GPU, float16 (the default), portable and kernels: mean |diff| <= 0.1 and p99 <= 0.5 (absolute error of the output boxes).

Limitations

  • Requires the optional transformers library (the network is its CLIPSegForImageSegmentation).
  • The original in the benchmarks and goldens is the Hugging Face transformers 5.19.0 port with the authors' weights (CIDAS/clipseg-rd64-refined); the authors' timojl/clipseg code was not run.
  • Text prompts only (no box exemplars or visual prompts); one instance per prompt: its mask is every pixel above probability 0.5, its score the highest pixel probability, its box the mask's bounding box.
  • The image is resized to 352 x 352 without keeping the aspect ratio, as the original processor; masks are coarse (22 x 22 patch tokens).

Usage

from fastforks import promptable_segmentation

model = promptable_segmentation.load("clipseg")  # mode="auto": the preferred backend from recorded measurements
result = model("photo.jpg", input_points=[[x, y]], input_labels=[1])
result.masks  # [M, H, W] bool
# SAM 3 (text prompts): model("photo.jpg", text="coin") -> boxes, scores, masks
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: clipseg.

Kernels backend

promptable_segmentation.load("clipseg", mode="kernels") runs our CUDA kernels (fvm_conv). 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.

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for fastforks/clipseg

Finetuned
(8)
this model

Collection including fastforks/clipseg

Paper for fastforks/clipseg