teed / README.md
Flor's picture
card: update from fastforks 1cbf1671
d50a908 verified
|
Raw History Blame Contribute Delete
4.65 kB
metadata
library_name: fastforks
pipeline_tag: image-to-image
license: mit
tags:
  - edges
  - edge-detection
  - line-art
  - controlnet-preprocessor
  - cuda
  - pytorch
  - fastforks
  - fastforks-card

TEED edges (fastforks)

Tiny and efficient edge detector (Soria et al., ICCV 2023 workshops; controlnet_aux TEEDdetector, ComfyUI's "TEED Soft-Edge Lines"): a 58 k-parameter network whose four outputs are averaged into a soft edge map, quantized to a few levels by default.

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/controlnet_aux at b1aac318b15c.

Task: edges. Tier: experimental. Outputs: edges. Backends: portable.

Input: one RGB image. Output: a line / edge map [H, W] in [0, 1] at the input size (1 = line), the ControlNet preprocessors (line art, HED, PiDiNet, TEED / Anyline); M-LSD also returns straight line segments.

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
teed@1 teed_5_model.pth 0322caf70f58 MIT yes

Licence

Original-code strings, recorded as they are (research-use package; check them before any other use). Code: MIT. Licence files: LICENSE.

Training data: BIPED (Barcelona Images for Perceptual Edge Detection) (BIPED (the repository's checkpoints/BIPED folder and README); the dataset is for non-commercial use.).

Licence evidence: https://github.com/xavysp/TEED/blob/40fa4b1391dc6424f88989d0ca75d5b592c8681d/LICENSE ; https://github.com/xavysp/TEED/tree/40fa4b1391dc6424f88989d0ca75d5b592c8681d/checkpoints/BIPED/5

Input size

any H x W >= 32, padded to a multiple of 32 Tested up to (portable, fp16, RTX 5060 Ti 16 GB): teed 1080x1920 (0.1 GiB peak allocated, 0.1 reserved)

Speed and memory

Edges, synthetic, 1080x1920

model time (ms): original portable peak memory (MiB, allocated / reserved): original portable
teed 29.6 4.09 149 / 184 122 / 146

Startup and first call

model load (s): original portable kernels first call (s): original portable kernels
teed 0.13 0.16 – 0.08 0.01 –

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)
teed 1024x1024 2.54 ms 1.10 ms 0.799 ms – 9.06 s 12.5 s 68 / 88 71 / 104 – 106 / 120

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| <= 0.002 vs the original. GPU, float16 (the default), portable and kernels: mean |diff| <= 0.02 and p99 <= 0.25 (absolute error of the output edges).

Usage

from fastforks import edges

model = edges.load("teed")  # mode="auto": the preferred backend from recorded measurements
result = model("photo.jpg")
result.edges  # [H, W] float32 in [0, 1], 1 = line, input resolution
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: teed.

Kernels backend

No kernels backend: a 58 k-parameter CNN that runs in a few ms; no custom kernel measured to pay off.