RAFT
RAFT is the recurrent all-pairs optical flow network by Teed and Deng (ECCV 2020). It takes two frames and returns, for every pixel of the first, its displacement to the second. LibreYOLO ports the upstream inference code and mirrors the four published checkpoints for the flow task.
- 작업
- optical flow
- 설치
pip install libreyolo- 지원 티어
- 추론 전용, v1.8.0부터 지원. 예측, 검증, 내보내기만 지원합니다. 학습 기능은 적용되지 않습니다.
- 라이선스
- 코드 MIT, 가중치 BSD-3-Clause. 상업적 사용
RAFT builds a 4D correlation volume between all pixel pairs of the two frames and refines one flow field with a recurrent update block. It is the reference most later flow networks start from, SEA-RAFT, FlowSeek and MEMFOF among them. Pick it when you want the well-known baseline, or the KITTI or Sintel fine-tune for footage close to those benchmarks.
Install
RAFT needs no optional extra. Everything it imports is in the base install.
pip install libreyoloPredict
Weights download from the LibreYOLO Hugging Face organization on first use.
The class LibreRAFT is also exported from libreyolo if you prefer to build the
model directly.
from libreyolo import LibreYOLO model = LibreYOLO("LibreRAFTl-flow.pt") # weights download on first useresults = model(["frame_0001.jpg", "frame_0002.jpg"]) flow = results[0].flowprint(flow.data.shape) # (H, W, 2) float32, (dx, dy) in pixelsprint(flow.mean_magnitude) # mean displacement in pixelsfrom libreyolo import LibreYOLO model = LibreYOLO("LibreRAFTl-flow.pt") # N frames give N - 1 results; result i is the flow from frame i to i + 1.for result in model("video.mp4", stream=True, save=True, save_flow=True): print(result.flow.max_magnitude)libreyolo predict model=LibreRAFTl-flow.pt source=frame_0001.jpg,frame_0002.jpg save=truelibreyolo predict model=LibreRAFTl-flow.pt source=video.mp4 save=true arrows=true save_flow=trueFlow needs at least two frames: a single image raises. A list of images, a
directory sorted by name, a video or a stream is one sequence, and N frames
give N - 1 results. result.flow is a FlowField with an (H, W, 2) float32
array on the original canvas of the first frame; flow.data[y, x] is
(dx, dy) in pixels, +x right and +y down. RAFT fills no confidence map, so flow.confidence is None. result.boxes is
None. save=True writes the Middlebury colour wheel, arrows=True or
warp=True pick the other views, and save_flow=True also writes each pair's
raw field as a .flo file. The optical flow task
page describes the payload and views in full.
Variants
| Size | Upstream checkpoint | File |
|---|---|---|
s | raft-small | LibreRAFTs-flow.pt |
l | raft-things (canonical) | LibreRAFTl-flow.pt |
l | raft-sintel fine-tune | LibreRAFTl-flow-sintel.pt |
l | raft-kitti fine-tune | LibreRAFTl-flow-kitti.pt |
LibreRAFT defaults to size l. Inference runs at the native frame
resolution, padded to a multiple of 8 as upstream's InputPadder does, with a
fixed 20 refinement iterations (upstream demo.py). imgsz caps the long
side: larger frames are downscaled and the field is scaled back to the
original canvas.
Training is not offered: train() raises NotImplementedError.
Validate
val() runs the shared flow validator on a flow dataset (frames per sequence
folder, Middlebury .flo, KITTI 16-bit PNG or .npy ground truth; see the
dataset format). It reports the mean
end-point error metrics/epe, metrics/px1 and metrics/px3 (share of valid
pixels under 1 and 3 px of error) and the KITTI outlier rate
metrics/fl_all.
from libreyolo import LibreYOLO model = LibreYOLO("LibreRAFTl-flow.pt")metrics = model.val(data="my_flow.yaml") print(metrics["metrics/epe"]) # mean end-point error, pixelsprint(metrics["metrics/px1"]) # share of pixels under 1 px errorprint(metrics["metrics/fl_all"]) # KITTI outlier ratelibreyolo val model=LibreRAFTl-flow.pt data=my_flow.yamlExport
| 작업 | ONNX | TorchScript | ExecuTorch | TensorRT | OpenVINO | Paddle | MNN | RKNN | Axelera | ncnn | TFLite | CoreML | Core AI |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Optical flow | Optical flow to ONNX: 지원하지 않음 | Optical flow to TorchScript: 지원하지 않음 | Optical flow to ExecuTorch: 지원하지 않음 | Optical flow to TensorRT: 지원하지 않음 | Optical flow to OpenVINO: 지원하지 않음 | Optical flow to Paddle: 지원하지 않음 | Optical flow to MNN: 지원하지 않음 | Optical flow to RKNN: 지원하지 않음 | Optical flow to Axelera: 지원하지 않음 | Optical flow to ncnn: 지원하지 않음 | Optical flow to TFLite: 지원하지 않음 | Optical flow to CoreML: 지원하지 않음 | Optical flow to Core AI: 지원하지 않음 |
Export is not available yet for any format. Optical flow export is blocked
until the two-input graph (image1, image2) and the backend vector-rescale
contract of the flow task are implemented for a family.
Checkpoints
Every published weight file for this family.
| 파일 | 가중치 라이선스 |
|---|---|
| Optical flow | |
| LibreRAFTl-flow.pt | bsd-3-clause |
| LibreRAFTs-flow.pt | bsd-3-clause |
| LibreRAFTl-flow-sintel.pt | bsd-3-clause |
| LibreRAFTl-flow-kitti.pt | bsd-3-clause |
위의 모든 파일은 현재 LibreYOLO 조직에 있으며 처음 사용할 때 내려받습니다.
Licensing
내려받는 특정 가중치의 Hugging Face 저장소에서 라이선스를 확인하십시오. LibreYOLO 조직의 모든 체크포인트에는 라이선스가 있으며 한 계열 안에서도 항상 같지는 않습니다. 해당 저장소가 신뢰할 수 있는 기준입니다. 아래 요약은 이 페이지를 마지막으로 검증했을 때 적용된 내용을 설명합니다.
관련 라이선스에 관한 설명이며 법률 자문이 아닙니다. 상업적으로 중요한 사안이라면 라이선스를 직접 읽고 별도의 법률 자문을 받으십시오.
- 원작
- RAFT, Princeton Vision & Learning Lab
- 업스트림 라이선스
- BSD-3-Clause
- 업스트림 소스
- github.com/princeton-vl/RAFT
- LibreYOLO 코드
- MIT
- 가중치
- BSD-3-Clause, huggingface.co/LibreYOLO에 다시 게시됨
- 해석
- BSD-3-Clause is a permissive license: the code and weights can be used in commercial and closed-source products. Redistributions must keep the copyright notice, the license conditions and the disclaimer, and the authors' names may not be used to endorse derived products without permission. The upstream inference code from princeton-vl/RAFT at commit 2888e15 is vendored under libreyolo/models/raft/_vendor/ with its BSD-3-Clause LICENSE; LibreYOLO's own wrapper code is MIT. The four checkpoints (raft-things as l, raft-small as s, and the raft-sintel and raft-kitti fine-tunes of l) come from the upstream download script and are mirrored on the LibreYOLO Hugging Face org under the same BSD-3-Clause license, without gating. Only the tensors' wrapping changes; training is not offered for this family.
RAFT is the work of Teed and Deng at the Princeton Vision & Learning Lab. The upstream inference code is vendored under its BSD-3-Clause licence, and the four checkpoints from the upstream download script are mirrored on the LibreYOLO Hugging Face organization under the same licence, without gating. BSD-3-Clause allows commercial and closed-source use as long as the copyright notice, conditions and disclaimer are kept.
Citation
@misc{teed2020raftrecurrentallpairsfield,
title={RAFT: Recurrent All-Pairs Field Transforms for Optical Flow},
author={Zachary Teed and Jia Deng},
year={2020},
eprint={2003.12039},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2003.12039},
}arxiv.org/abs/2003.12039에 있는 저자의 인용 블록에서 복사했습니다.