UniFace: A Unified Face Analysis Library for Python | Detection, alignment, landmarks, face-mesh, recognition, parsing, gaze, attributes and anti-spoofing under one API.
Python computer-visiondeep-learningface-alignmentface-analysisface-anonymizationface-anti-spoofingface-attributesface-detectionface-meshface-parsingface-quality-assessmentface-recognitionface-segmentationface-trackingfacial-landmarksgaze-estimationhead-pose-estimationonnxruntimeportrait-mattingpython
docs: Add translation for README and dataset link (#149)
Yakhyokhuja Valikhujaev2fd4ab1e86dc
diff --git a/README.es.md b/README.es.mdnew file mode 100644index 0000000..15d7ddf--- /dev/null+++ b/README.es.md@@ -0,0 +1,190 @@+\[[English](README.md)\] | \[[Chinese](README.zh-CN.md)\] | \[[Korean](README.ko.md)\] | \[[Spanish](README.es.md)\] | \[[Uzbek](README.uz.md)\]++<h1 align="center">UniFace: Una biblioteca unificada de análisis facial para Python</h1>++Esta página es la traducción al español del [README en inglés](README.md). La documentación enlazada está principalmente en inglés. Al actualizar la traducción, mantén el contenido sincronizado con la versión inglesa.++<div align="center">++[](https://pypi.org/project/uniface/)+[](https://www.python.org/)+[](https://opensource.org/licenses/MIT)+[](https://github.com/yakhyo/uniface/actions)+[](https://pepy.tech/projects/uniface)+[](https://www.kaggle.com/yakhyokhuja/code)+[](https://huggingface.co/spaces/yakhyo/uniface)++</div>++<div align="center">+ <img src="https://raw.githubusercontent.com/yakhyo/uniface/main/.github/logos/uniface_rounded_q80.webp" width="90%" alt="UniFace — Una biblioteca unificada de análisis facial para Python">+</div>++<p align="center">+ UniFace es una biblioteca ligera de Python, lista para producción, para detección y reconocimiento facial,<br>+ seguimiento, análisis de puntos de referencia, segmentación de partes del rostro, estimación de la mirada y atributos faciales.+</p>++<p align="center">+ <a href="https://yakhyo.github.io/uniface/quickstart/"><img src="https://img.shields.io/badge/Primeros%20pasos-1f6feb?style=for-the-badge&logoColor=white" alt="Primeros pasos"></a>+ + <a href="https://yakhyo.github.io/uniface/models/"><img src="https://img.shields.io/badge/Cat%C3%A1logo%20de%20modelos-30363d?style=for-the-badge&logoColor=white" alt="Catálogo de modelos"></a>+ + <a href="https://yakhyo.github.io/uniface/notebooks/"><img src="https://img.shields.io/badge/Cuadernos-30363d?style=for-the-badge&logo=jupyter&logoColor=white" alt="Cuadernos"></a>+ + <a href="https://yakhyo.github.io/uniface/"><img src="https://img.shields.io/badge/Documentaci%C3%B3n%20completa-30363d?style=for-the-badge&logoColor=white" alt="Documentación completa"></a>+</p>++```bash+pip install "uniface[cpu]" # CPU y Apple Silicon+pip install "uniface[gpu]" # NVIDIA CUDA+pip install --pre "uniface[cpu]" # última versión preliminar+```++<details>+<summary><b>Un primer script</b></summary>++<br>++`FaceAnalyzer` ejecuta la detección, la alineación y el reconocimiento en una sola llamada. Los modelos de atributos se añaden de forma explícita.++```python+import cv2+from uniface import FaceAnalyzer, FairFace++analyzer = FaceAnalyzer(predictors=[FairFace()])++for face in analyzer.analyze(cv2.imread("photo.jpg")):+ print(face.bbox, face.sex, face.age_group, face.embedding.shape)+```++`bbox`, `confidence`, `landmarks` y `embedding` siempre tienen un valor. La edad, el sexo, la raza, la emoción, la calidad+y los estados del rostro permanecen en `None` hasta que se añade el predictor correspondiente.++</details>++<details>+<summary><b>Las quince tareas y sus modelos</b></summary>++<br>++| Tarea | Modelos |+| --- | --- |+| Detección facial | RetinaFace, SCRFD, CenterFace, YOLOv5-Face, YOLOv8-Face, BlazeFace |+| Reconocimiento facial | AdaFace, ArcFace, EdgeFace, MobileFace, SphereFace |+| Seguimiento facial | BYTETracker, identificadores persistentes entre fotogramas |+| Puntos de referencia faciales | 2d106det (106), PIPNet (98 / 68), Face Mesh (468 / 478, 3D) |+| Segmentación de partes del rostro | BiSeNet (19 clases), máscaras con XSeg |+| Recorte de retratos | MODNet, sin trimap |+| Estimación de la mirada | MobileGaze (ResNet-18 / 34 / 50, MobileNetV2) |+| Pose de la cabeza | representación de rotación 6D, cabeceo / guiñada / alabeo |+| Atributos demográficos | AgeGender, FairFace (grupo de edad, sexo, raza) |+| Emoción | AffectNet-7 y AffectNet-8 |+| Estados del rostro | FaceAttribNet: estado de los ojos, gafas, gafas de sol, mascarilla |+| Calidad facial | eDifFIQA (T / S / M / L) |+| Detección de suplantación facial | detección de vida con MiniFASNet |+| Anonimización | 5 métodos de desenfoque |+| Almacén de vectores | búsqueda de embeddings con FAISS |++Funciona en CPU, Apple Silicon y CUDA. Los pesos se descargan al usarlos por primera vez y se verifican con SHA-256.++</details>++<br>++### Detectar rostros y medir sus características++**Detección facial** · [documentación](https://yakhyo.github.io/uniface/modules/detection/)++<img src="https://raw.githubusercontent.com/yakhyo/uniface/main/assets/demo/detection.jpg" width="100%">++**Puntos de referencia faciales** · [documentación](https://yakhyo.github.io/uniface/modules/landmarks/)++<img src="https://raw.githubusercontent.com/yakhyo/uniface/main/assets/demo/landmarks.jpg" width="100%">++**Malla facial** · [documentación](https://yakhyo.github.io/uniface/modules/landmarks/#face-mesh-468-or-478-points-3d)++<img src="https://raw.githubusercontent.com/yakhyo/uniface/main/assets/demo/face_mesh.jpg" width="100%">++**Calidad facial** · [documentación](https://yakhyo.github.io/uniface/modules/quality/)++<img src="https://raw.githubusercontent.com/yakhyo/uniface/main/assets/demo/quality.jpg" width="100%">++### Separar rostros y retratos++**Segmentación de partes del rostro** · [documentación](https://yakhyo.github.io/uniface/modules/parsing/)++<img src="https://raw.githubusercontent.com/yakhyo/uniface/main/assets/demo/parsing.jpg" width="100%">++**Segmentación facial** · [documentación](https://yakhyo.github.io/uniface/modules/parsing/#xseg)++<img src="https://raw.githubusercontent.com/yakhyo/uniface/main/assets/demo/segmentation.jpg" width="100%">++<img src="https://raw.githubusercontent.com/yakhyo/uniface/main/assets/demo/segmentation_occluded.jpg" width="100%">++**Recorte de retratos** · [documentación](https://yakhyo.github.io/uniface/modules/matting/)++<img src="https://raw.githubusercontent.com/yakhyo/uniface/main/assets/demo/matting.jpg" width="100%">++<img src="https://raw.githubusercontent.com/yakhyo/uniface/main/assets/demo/matting_alt.jpg" width="100%">++### Estimar la orientación de la cabeza y la mirada++**Pose de la cabeza** · [documentación](https://yakhyo.github.io/uniface/modules/headpose/)++<img src="https://raw.githubusercontent.com/yakhyo/uniface/main/assets/demo/headpose.jpg" width="100%">++**Estimación de la mirada** · [documentación](https://yakhyo.github.io/uniface/modules/gaze/)++<img src="https://raw.githubusercontent.com/yakhyo/uniface/main/assets/demo/gaze.jpg" width="100%">++### Analizar atributos faciales++**Edad y sexo** · [documentación](https://yakhyo.github.io/uniface/modules/attributes/)++<img src="https://raw.githubusercontent.com/yakhyo/uniface/main/assets/demo/demography.jpg" width="100%">++**Emoción** · [documentación](https://yakhyo.github.io/uniface/modules/attributes/#emotion)++<img src="https://raw.githubusercontent.com/yakhyo/uniface/main/assets/demo/emotion.jpg" width="100%">++**Estados del rostro** · [documentación](https://yakhyo.github.io/uniface/modules/attributes/#faceattribnet)++<img src="https://raw.githubusercontent.com/yakhyo/uniface/main/assets/demo/face_states.jpg" width="100%">++<img src="https://raw.githubusercontent.com/yakhyo/uniface/main/assets/demo/face_states_alt.jpg" width="100%">++### Distinguir un rostro real de una reproducción++**Detección de suplantación facial** · [documentación](https://yakhyo.github.io/uniface/modules/spoofing/)++<img src="https://raw.githubusercontent.com/yakhyo/uniface/main/assets/demo/spoofing.jpg" width="100%">++### Comparar rostros o anonimizarlos++**Reconocimiento facial** · [documentación](https://yakhyo.github.io/uniface/modules/recognition/)++<img src="https://raw.githubusercontent.com/yakhyo/uniface/main/assets/demo/verification.jpg" width="100%">++**Anonimización facial** · [documentación](https://yakhyo.github.io/uniface/modules/privacy/)++<img src="https://raw.githubusercontent.com/yakhyo/uniface/main/assets/demo/anonymization.jpg" width="100%">++<br>++<div align="center">++**[Primeros pasos](https://yakhyo.github.io/uniface/quickstart/)** · +[Catálogo de modelos](https://yakhyo.github.io/uniface/models/) · +[Cuadernos](https://yakhyo.github.io/uniface/notebooks/) · +[Licencias de los modelos](https://yakhyo.github.io/uniface/license-attribution/) · +[Contribuir](CONTRIBUTING.md) · +[Discord](https://discord.gg/wdzrjr7R5j) · +[Incidencias](https://github.com/yakhyo/uniface/issues)++Funciona en CPU, Apple Silicon y CUDA. Los pesos se descargan al usarlos por primera vez y se verifican con SHA-256.<br>+UniFace se distribuye bajo la licencia [MIT](LICENSE); algunos pesos preentrenados tienen otras licencias, así que consulta las+[licencias](https://yakhyo.github.io/uniface/license-attribution/) antes de distribuirlo comercialmente.<br>+Este proyecto no está afiliado a [Uniface](https://uniface.com/) de Rocket Software.++</div>diff --git a/README.ko.md b/README.ko.mdnew file mode 100644index 0000000..d0e0411--- /dev/null+++ b/README.ko.md@@ -0,0 +1,190 @@+\[[English](README.md)\] | \[[Chinese](README.zh-CN.md)\] | \[[Korean](README.ko.md)\] | \[[Spanish](README.es.md)\] | \[[Uzbek](README.uz.md)\]++<h1 align="center">UniFace: Python용 통합 얼굴 분석 라이브러리</h1>++이 페이지는 [영문 README](README.md)의 한국어 번역입니다. 링크된 문서는 주로 영어로 제공됩니다. 번역을 수정할 때는 영문 버전과 내용을 맞춰 주세요.++<div align="center">++[](https://pypi.org/project/uniface/)+[](https://www.python.org/)+[](https://opensource.org/licenses/MIT)+[](https://github.com/yakhyo/uniface/actions)+[](https://pepy.tech/projects/uniface)+[](https://www.kaggle.com/yakhyokhuja/code)+[](https://huggingface.co/spaces/yakhyo/uniface)++</div>++<div align="center">+ <img src="https://raw.githubusercontent.com/yakhyo/uniface/main/.github/logos/uniface_rounded_q80.webp" width="90%" alt="UniFace — Python용 통합 얼굴 분석 라이브러리">+</div>++<p align="center">+ UniFace는 가볍고 프로덕션 환경에서 사용할 수 있는 Python 라이브러리로, 얼굴 검출, 인식,<br>+ 추적, 랜드마크 분석, 얼굴 파싱, 시선 추정 및 얼굴 속성 분석을 지원합니다.+</p>++<p align="center">+ <a href="https://yakhyo.github.io/uniface/quickstart/"><img src="https://img.shields.io/badge/%EC%8B%9C%EC%9E%91%ED%95%98%EA%B8%B0-1f6feb?style=for-the-badge&logoColor=white" alt="시작하기"></a>+ + <a href="https://yakhyo.github.io/uniface/models/"><img src="https://img.shields.io/badge/%EB%AA%A8%EB%8D%B8%20%EB%AA%A8%EC%9D%8C-30363d?style=for-the-badge&logoColor=white" alt="모델 모음"></a>+ + <a href="https://yakhyo.github.io/uniface/notebooks/"><img src="https://img.shields.io/badge/%EB%85%B8%ED%8A%B8%EB%B6%81-30363d?style=for-the-badge&logo=jupyter&logoColor=white" alt="노트북"></a>+ + <a href="https://yakhyo.github.io/uniface/"><img src="https://img.shields.io/badge/%EC%A0%84%EC%B2%B4%20%EB%AC%B8%EC%84%9C-30363d?style=for-the-badge&logoColor=white" alt="전체 문서"></a>+</p>++```bash+pip install "uniface[cpu]" # CPU 및 Apple Silicon+pip install "uniface[gpu]" # NVIDIA CUDA+pip install --pre "uniface[cpu]" # 최신 사전 릴리스+```++<details>+<summary><b>첫 번째 예제</b></summary>++<br>++`FaceAnalyzer`는 한 번의 호출로 검출, 정렬 및 인식을 수행합니다. 속성 모델은 필요할 때 명시적으로 추가합니다.++```python+import cv2+from uniface import FaceAnalyzer, FairFace++analyzer = FaceAnalyzer(predictors=[FairFace()])++for face in analyzer.analyze(cv2.imread("photo.jpg")):+ print(face.bbox, face.sex, face.age_group, face.embedding.shape)+```++`bbox`, `confidence`, `landmarks`, `embedding`은 항상 설정됩니다. 나이, 성별, 인종, 감정, 품질+및 얼굴 상태는 해당 값을 채우는 예측 모델을 전달하기 전까지 `None`으로 유지됩니다.++</details>++<details>+<summary><b>15가지 작업과 각 작업에 사용되는 모델</b></summary>++<br>++| 작업 | 모델 |+| --- | --- |+| 얼굴 검출 | RetinaFace, SCRFD, CenterFace, YOLOv5-Face, YOLOv8-Face, BlazeFace |+| 얼굴 인식 | AdaFace, ArcFace, EdgeFace, MobileFace, SphereFace |+| 얼굴 추적 | BYTETracker, 동영상 프레임 간 ID 유지 |+| 얼굴 랜드마크 | 2d106det (106), PIPNet (98 / 68), Face Mesh (468 / 478, 3D) |+| 얼굴 파싱 | BiSeNet (19개 클래스), XSeg 마스크 생성 |+| 인물 매팅 | MODNet, 트라이맵 불필요 |+| 시선 추정 | MobileGaze (ResNet-18 / 34 / 50, MobileNetV2) |+| 머리 자세 | 6D 회전 표현, 피치 / 요 / 롤 |+| 인구통계학적 속성 | AgeGender, FairFace (연령대, 성별, 인종) |+| 감정 | AffectNet-7 및 AffectNet-8 |+| 얼굴 상태 | FaceAttribNet: 눈 상태, 안경, 선글라스, 마스크 |+| 얼굴 품질 | eDifFIQA (T / S / M / L) |+| 얼굴 위조 방지 | MiniFASNet 생체 감지 |+| 익명화 | 5가지 블러 방식 |+| 벡터 저장소 | FAISS 기반 임베딩 검색 |++CPU, Apple Silicon 및 CUDA에서 실행됩니다. 모델 가중치는 처음 사용할 때 다운로드되며 SHA-256으로 검증됩니다.++</details>++<br>++### 얼굴 검출과 특징 측정++**얼굴 검출** · [문서](https://yakhyo.github.io/uniface/modules/detection/)++<img src="https://raw.githubusercontent.com/yakhyo/uniface/main/assets/demo/detection.jpg" width="100%">++**얼굴 랜드마크** · [문서](https://yakhyo.github.io/uniface/modules/landmarks/)++<img src="https://raw.githubusercontent.com/yakhyo/uniface/main/assets/demo/landmarks.jpg" width="100%">++**얼굴 메시** · [문서](https://yakhyo.github.io/uniface/modules/landmarks/#face-mesh-468-or-478-points-3d)++<img src="https://raw.githubusercontent.com/yakhyo/uniface/main/assets/demo/face_mesh.jpg" width="100%">++**얼굴 품질** · [문서](https://yakhyo.github.io/uniface/modules/quality/)++<img src="https://raw.githubusercontent.com/yakhyo/uniface/main/assets/demo/quality.jpg" width="100%">++### 얼굴과 인물 영역 분리++**얼굴 파싱** · [문서](https://yakhyo.github.io/uniface/modules/parsing/)++<img src="https://raw.githubusercontent.com/yakhyo/uniface/main/assets/demo/parsing.jpg" width="100%">++**얼굴 세그멘테이션** · [문서](https://yakhyo.github.io/uniface/modules/parsing/#xseg)++<img src="https://raw.githubusercontent.com/yakhyo/uniface/main/assets/demo/segmentation.jpg" width="100%">++<img src="https://raw.githubusercontent.com/yakhyo/uniface/main/assets/demo/segmentation_occluded.jpg" width="100%">++**인물 매팅** · [문서](https://yakhyo.github.io/uniface/modules/matting/)++<img src="https://raw.githubusercontent.com/yakhyo/uniface/main/assets/demo/matting.jpg" width="100%">++<img src="https://raw.githubusercontent.com/yakhyo/uniface/main/assets/demo/matting_alt.jpg" width="100%">++### 머리 방향과 시선 추정++**머리 자세** · [문서](https://yakhyo.github.io/uniface/modules/headpose/)++<img src="https://raw.githubusercontent.com/yakhyo/uniface/main/assets/demo/headpose.jpg" width="100%">++**시선 추정** · [문서](https://yakhyo.github.io/uniface/modules/gaze/)++<img src="https://raw.githubusercontent.com/yakhyo/uniface/main/assets/demo/gaze.jpg" width="100%">++### 얼굴 속성 분석++**나이와 성별** · [문서](https://yakhyo.github.io/uniface/modules/attributes/)++<img src="https://raw.githubusercontent.com/yakhyo/uniface/main/assets/demo/demography.jpg" width="100%">++**감정** · [문서](https://yakhyo.github.io/uniface/modules/attributes/#emotion)++<img src="https://raw.githubusercontent.com/yakhyo/uniface/main/assets/demo/emotion.jpg" width="100%">++**얼굴 상태** · [문서](https://yakhyo.github.io/uniface/modules/attributes/#faceattribnet)++<img src="https://raw.githubusercontent.com/yakhyo/uniface/main/assets/demo/face_states.jpg" width="100%">++<img src="https://raw.githubusercontent.com/yakhyo/uniface/main/assets/demo/face_states_alt.jpg" width="100%">++### 실제 얼굴과 재생 공격 구분++**얼굴 위조 방지** · [문서](https://yakhyo.github.io/uniface/modules/spoofing/)++<img src="https://raw.githubusercontent.com/yakhyo/uniface/main/assets/demo/spoofing.jpg" width="100%">++### 얼굴 매칭과 익명화++**얼굴 인식** · [문서](https://yakhyo.github.io/uniface/modules/recognition/)++<img src="https://raw.githubusercontent.com/yakhyo/uniface/main/assets/demo/verification.jpg" width="100%">++**얼굴 익명화** · [문서](https://yakhyo.github.io/uniface/modules/privacy/)++<img src="https://raw.githubusercontent.com/yakhyo/uniface/main/assets/demo/anonymization.jpg" width="100%">++<br>++<div align="center">++**[시작하기](https://yakhyo.github.io/uniface/quickstart/)** · +[모델 모음](https://yakhyo.github.io/uniface/models/) · +[노트북](https://yakhyo.github.io/uniface/notebooks/) · +[모델 라이선스](https://yakhyo.github.io/uniface/license-attribution/) · +[기여하기](CONTRIBUTING.md) · +[Discord](https://discord.gg/wdzrjr7R5j) · +[이슈](https://github.com/yakhyo/uniface/issues)++CPU, Apple Silicon 및 CUDA에서 실행됩니다. 모델 가중치는 처음 사용할 때 다운로드되며 SHA-256으로 검증됩니다.<br>+UniFace는 [MIT](LICENSE) 라이선스를 사용합니다. 일부 사전 학습 가중치에는 다른 라이선스가 적용되므로 상업적으로 배포하기 전에+[라이선스 안내](https://yakhyo.github.io/uniface/license-attribution/)를 확인하세요.<br>+이 프로젝트는 Rocket Software의 [Uniface](https://uniface.com/)와 관련이 없습니다.++</div>diff --git a/README.md b/README.mdindex 04dbcc8..435902d 100644--- a/README.md+++ b/README.md@@ -1,3 +1,5 @@+\[[English](README.md)\] | \[[Chinese](README.zh-CN.md)\] | \[[Korean](README.ko.md)\] | \[[Spanish](README.es.md)\] | \[[Uzbek](README.uz.md)\]+<h1 align="center">UniFace: A Unified Face Analysis Library for Python</h1><div align="center">diff --git a/README.uz.md b/README.uz.mdnew file mode 100644index 0000000..a4479b8--- /dev/null+++ b/README.uz.md@@ -0,0 +1,190 @@+\[[English](README.md)\] | \[[Chinese](README.zh-CN.md)\] | \[[Korean](README.ko.md)\] | \[[Spanish](README.es.md)\] | \[[Uzbek](README.uz.md)\]++<h1 align="center">UniFace: Python uchun yagona yuz tahlili kutubxonasi</h1>++Bu sahifa [inglizcha README](README.md) faylining oʻzbekcha tarjimasidir. Havolalardagi hujjatlar asosan ingliz tilida. Tarjimani yangilashda inglizcha nusxa bilan mosligini saqlang.++<div align="center">++[](https://pypi.org/project/uniface/)+[](https://www.python.org/)+[](https://opensource.org/licenses/MIT)+[](https://github.com/yakhyo/uniface/actions)+[](https://pepy.tech/projects/uniface)+[](https://www.kaggle.com/yakhyokhuja/code)+[](https://huggingface.co/spaces/yakhyo/uniface)++</div>++<div align="center">+ <img src="https://raw.githubusercontent.com/yakhyo/uniface/main/.github/logos/uniface_rounded_q80.webp" width="90%" alt="UniFace — Python uchun yagona yuz tahlili kutubxonasi">+</div>++<p align="center">+ UniFace — ishlab chiqarish muhitida foydalanishga tayyor, yengil Python kutubxonasi. U yuzlarni aniqlash, tanib olish,<br>+ kuzatish, tayanch nuqtalarni tahlil qilish, yuz qismlarini segmentlash, nigoh yoʻnalishini baholash va yuz atributlarini tahlil qilishni qoʻllab-quvvatlaydi.+</p>++<p align="center">+ <a href="https://yakhyo.github.io/uniface/quickstart/"><img src="https://img.shields.io/badge/Boshlash-1f6feb?style=for-the-badge&logoColor=white" alt="Boshlash"></a>+ + <a href="https://yakhyo.github.io/uniface/models/"><img src="https://img.shields.io/badge/Modellar%20to%CA%BBplami-30363d?style=for-the-badge&logoColor=white" alt="Modellar toʻplami"></a>+ + <a href="https://yakhyo.github.io/uniface/notebooks/"><img src="https://img.shields.io/badge/Notebooklar-30363d?style=for-the-badge&logo=jupyter&logoColor=white" alt="Notebooklar"></a>+ + <a href="https://yakhyo.github.io/uniface/"><img src="https://img.shields.io/badge/To%CA%BBliq%20hujjatlar-30363d?style=for-the-badge&logoColor=white" alt="Toʻliq hujjatlar"></a>+</p>++```bash+pip install "uniface[cpu]" # CPU va Apple Silicon+pip install "uniface[gpu]" # NVIDIA CUDA+pip install --pre "uniface[cpu]" # eng soʻnggi dastlabki reliz+```++<details>+<summary><b>Birinchi skript</b></summary>++<br>++`FaceAnalyzer` bitta chaqiruvda yuzni aniqlash, tekislash va tanib olishni bajaradi. Atribut modellarini alohida qoʻshish kerak.++```python+import cv2+from uniface import FaceAnalyzer, FairFace++analyzer = FaceAnalyzer(predictors=[FairFace()])++for face in analyzer.analyze(cv2.imread("photo.jpg")):+ print(face.bbox, face.sex, face.age_group, face.embedding.shape)+```++`bbox`, `confidence`, `landmarks` va `embedding` har doim toʻldiriladi. Yosh, jins, irq, hissiyot, sifat+va yuz holatlari tegishli bashorat modelini uzatmaguningizcha `None` boʻlib qoladi.++</details>++<details>+<summary><b>Barcha oʻn beshta vazifa va ularni bajaradigan modellar</b></summary>++<br>++| Vazifa | Modellar |+| --- | --- |+| Yuzni aniqlash | RetinaFace, SCRFD, CenterFace, YOLOv5-Face, YOLOv8-Face, BlazeFace |+| Yuzni tanib olish | AdaFace, ArcFace, EdgeFace, MobileFace, SphereFace |+| Yuzni kuzatish | BYTETracker, video kadrlari orasida saqlanadigan ID lar |+| Yuz tayanch nuqtalari | 2d106det (106), PIPNet (98 / 68), Face Mesh (468 / 478, 3D) |+| Yuz qismlarini segmentlash | BiSeNet (19 ta sinf), XSeg yordamida niqob yaratish |+| Odam tasvirini fondan ajratish | MODNet, trimap talab qilmaydi |+| Nigoh yoʻnalishini baholash | MobileGaze (ResNet-18 / 34 / 50, MobileNetV2) |+| Bosh holati | 6D aylanish ifodasi, pitch / yaw / roll |+| Demografik atributlar | AgeGender, FairFace (yosh guruhi, jins, irq) |+| Hissiyot | AffectNet-7 va AffectNet-8 |+| Yuz holatlari | FaceAttribNet: koʻz holati, koʻzoynak, quyosh koʻzoynagi, niqob |+| Yuz tasviri sifati | eDifFIQA (T / S / M / L) |+| Soxta yuzlardan himoya | MiniFASNet yordamida tiriklikni tekshirish |+| Anonimlashtirish | 5 xil xiralashtirish usuli |+| Vektorlar ombori | FAISS asosida embedding vektorlarini qidirish |++CPU, Apple Silicon va CUDA da ishlaydi. Model vaznlari birinchi foydalanishda yuklab olinadi va SHA-256 orqali tekshiriladi.++</details>++<br>++### Yuzlarni topish va xususiyatlarini oʻlchash++**Yuzni aniqlash** · [hujjatlar](https://yakhyo.github.io/uniface/modules/detection/)++<img src="https://raw.githubusercontent.com/yakhyo/uniface/main/assets/demo/detection.jpg" width="100%">++**Yuz tayanch nuqtalari** · [hujjatlar](https://yakhyo.github.io/uniface/modules/landmarks/)++<img src="https://raw.githubusercontent.com/yakhyo/uniface/main/assets/demo/landmarks.jpg" width="100%">++**Yuz toʻri** · [hujjatlar](https://yakhyo.github.io/uniface/modules/landmarks/#face-mesh-468-or-478-points-3d)++<img src="https://raw.githubusercontent.com/yakhyo/uniface/main/assets/demo/face_mesh.jpg" width="100%">++**Yuz tasviri sifati** · [hujjatlar](https://yakhyo.github.io/uniface/modules/quality/)++<img src="https://raw.githubusercontent.com/yakhyo/uniface/main/assets/demo/quality.jpg" width="100%">++### Yuz va odam tasvirini ajratib olish++**Yuz qismlarini segmentlash** · [hujjatlar](https://yakhyo.github.io/uniface/modules/parsing/)++<img src="https://raw.githubusercontent.com/yakhyo/uniface/main/assets/demo/parsing.jpg" width="100%">++**Yuzni segmentlash** · [hujjatlar](https://yakhyo.github.io/uniface/modules/parsing/#xseg)++<img src="https://raw.githubusercontent.com/yakhyo/uniface/main/assets/demo/segmentation.jpg" width="100%">++<img src="https://raw.githubusercontent.com/yakhyo/uniface/main/assets/demo/segmentation_occluded.jpg" width="100%">++**Odam tasvirini fondan ajratish** · [hujjatlar](https://yakhyo.github.io/uniface/modules/matting/)++<img src="https://raw.githubusercontent.com/yakhyo/uniface/main/assets/demo/matting.jpg" width="100%">++<img src="https://raw.githubusercontent.com/yakhyo/uniface/main/assets/demo/matting_alt.jpg" width="100%">++### Bosh va nigoh yoʻnalishini baholash++**Bosh holati** · [hujjatlar](https://yakhyo.github.io/uniface/modules/headpose/)++<img src="https://raw.githubusercontent.com/yakhyo/uniface/main/assets/demo/headpose.jpg" width="100%">++**Nigoh yoʻnalishini baholash** · [hujjatlar](https://yakhyo.github.io/uniface/modules/gaze/)++<img src="https://raw.githubusercontent.com/yakhyo/uniface/main/assets/demo/gaze.jpg" width="100%">++### Yuz atributlarini tahlil qilish++**Yosh va jins** · [hujjatlar](https://yakhyo.github.io/uniface/modules/attributes/)++<img src="https://raw.githubusercontent.com/yakhyo/uniface/main/assets/demo/demography.jpg" width="100%">++**Hissiyot** · [hujjatlar](https://yakhyo.github.io/uniface/modules/attributes/#emotion)++<img src="https://raw.githubusercontent.com/yakhyo/uniface/main/assets/demo/emotion.jpg" width="100%">++**Yuz holatlari** · [hujjatlar](https://yakhyo.github.io/uniface/modules/attributes/#faceattribnet)++<img src="https://raw.githubusercontent.com/yakhyo/uniface/main/assets/demo/face_states.jpg" width="100%">++<img src="https://raw.githubusercontent.com/yakhyo/uniface/main/assets/demo/face_states_alt.jpg" width="100%">++### Haqiqiy yuzni qayta namoyish etilgan tasvirdan farqlash++**Soxta yuzlardan himoya** · [hujjatlar](https://yakhyo.github.io/uniface/modules/spoofing/)++<img src="https://raw.githubusercontent.com/yakhyo/uniface/main/assets/demo/spoofing.jpg" width="100%">++### Yuzlarni solishtirish yoki anonimlashtirish++**Yuzni tanib olish** · [hujjatlar](https://yakhyo.github.io/uniface/modules/recognition/)++<img src="https://raw.githubusercontent.com/yakhyo/uniface/main/assets/demo/verification.jpg" width="100%">++**Yuzni anonimlashtirish** · [hujjatlar](https://yakhyo.github.io/uniface/modules/privacy/)++<img src="https://raw.githubusercontent.com/yakhyo/uniface/main/assets/demo/anonymization.jpg" width="100%">++<br>++<div align="center">++**[Boshlash](https://yakhyo.github.io/uniface/quickstart/)** · +[Modellar toʻplami](https://yakhyo.github.io/uniface/models/) · +[Notebooklar](https://yakhyo.github.io/uniface/notebooks/) · +[Model litsenziyalari](https://yakhyo.github.io/uniface/license-attribution/) · +[Hissa qoʻshish](CONTRIBUTING.md) · +[Discord](https://discord.gg/wdzrjr7R5j) · +[Muammolar](https://github.com/yakhyo/uniface/issues)++CPU, Apple Silicon va CUDA da ishlaydi. Model vaznlari birinchi foydalanishda yuklab olinadi va SHA-256 orqali tekshiriladi.<br>+UniFace [MIT](LICENSE) litsenziyasi asosida tarqatiladi; ayrim oldindan oʻqitilgan model vaznlari boshqa litsenziyalarga ega. Tijoriy tarqatishdan oldin+[litsenziyalarni](https://yakhyo.github.io/uniface/license-attribution/) tekshiring.<br>+Loyiha Rocket Software kompaniyasining [Uniface](https://uniface.com/) mahsulotiga aloqador emas.++</div>diff --git a/README.zh-CN.md b/README.zh-CN.mdnew file mode 100644index 0000000..0392aff--- /dev/null+++ b/README.zh-CN.md@@ -0,0 +1,190 @@+\[[English](README.md)\] | \[[Chinese](README.zh-CN.md)\] | \[[Korean](README.ko.md)\] | \[[Spanish](README.es.md)\] | \[[Uzbek](README.uz.md)\]++<h1 align="center">UniFace:统一的 Python 人脸分析库</h1>++本页是 [英文 README](README.md) 的简体中文翻译。链接指向的文档主要使用英文;更新翻译时请与英文版本保持同步。++<div align="center">++[](https://pypi.org/project/uniface/)+[](https://www.python.org/)+[](https://opensource.org/licenses/MIT)+[](https://github.com/yakhyo/uniface/actions)+[](https://pepy.tech/projects/uniface)+[](https://www.kaggle.com/yakhyokhuja/code)+[](https://huggingface.co/spaces/yakhyo/uniface)++</div>++<div align="center">+ <img src="https://raw.githubusercontent.com/yakhyo/uniface/main/.github/logos/uniface_rounded_q80.webp" width="90%" alt="UniFace — 统一的 Python 人脸分析库">+</div>++<p align="center">+ UniFace 是一个轻量级、可用于生产环境的 Python 库,支持人脸检测、识别、<br>+ 跟踪、关键点分析、人脸解析、视线估计和人脸属性分析。+</p>++<p align="center">+ <a href="https://yakhyo.github.io/uniface/quickstart/"><img src="https://img.shields.io/badge/%E5%BF%AB%E9%80%9F%E5%BC%80%E5%A7%8B-1f6feb?style=for-the-badge&logoColor=white" alt="快速开始"></a>+ + <a href="https://yakhyo.github.io/uniface/models/"><img src="https://img.shields.io/badge/%E6%A8%A1%E5%9E%8B%E5%BA%93-30363d?style=for-the-badge&logoColor=white" alt="模型库"></a>+ + <a href="https://yakhyo.github.io/uniface/notebooks/"><img src="https://img.shields.io/badge/%E4%BA%A4%E4%BA%92%E5%BC%8F%E7%AC%94%E8%AE%B0%E6%9C%AC-30363d?style=for-the-badge&logo=jupyter&logoColor=white" alt="交互式笔记本"></a>+ + <a href="https://yakhyo.github.io/uniface/"><img src="https://img.shields.io/badge/%E5%AE%8C%E6%95%B4%E6%96%87%E6%A1%A3-30363d?style=for-the-badge&logoColor=white" alt="完整文档"></a>+</p>++```bash+pip install "uniface[cpu]" # CPU 和 Apple Silicon+pip install "uniface[gpu]" # NVIDIA CUDA+pip install --pre "uniface[cpu]" # 最新预发布版本+```++<details>+<summary><b>第一个示例脚本</b></summary>++<br>++`FaceAnalyzer` 通过一次调用完成检测、对齐和识别。属性模型需要显式启用。++```python+import cv2+from uniface import FaceAnalyzer, FairFace++analyzer = FaceAnalyzer(predictors=[FairFace()])++for face in analyzer.analyze(cv2.imread("photo.jpg")):+ print(face.bbox, face.sex, face.age_group, face.embedding.shape)+```++`bbox`、`confidence`、`landmarks` 和 `embedding` 始终会被赋值。年龄、性别、种族、情绪、质量+和人脸状态保持为 `None`,直到你传入相应的预测模型。++</details>++<details>+<summary><b>全部十五项任务及其对应模型</b></summary>++<br>++| 任务 | 模型 |+| --- | --- |+| 人脸检测 | RetinaFace, SCRFD, CenterFace, YOLOv5-Face, YOLOv8-Face, BlazeFace |+| 人脸识别 | AdaFace, ArcFace, EdgeFace, MobileFace, SphereFace |+| 人脸跟踪 | BYTETracker, 视频帧之间保持一致的 ID |+| 人脸关键点 | 2d106det (106), PIPNet (98 / 68), Face Mesh (468 / 478, 3D) |+| 人脸解析 | BiSeNet (19 个类别), XSeg 掩码生成 |+| 人像抠图 | MODNet, 无需三分图 |+| 视线估计 | MobileGaze (ResNet-18 / 34 / 50, MobileNetV2) |+| 头部姿态 | 6D 旋转表示,俯仰 / 偏航 / 翻滚 |+| 人口统计属性 | AgeGender, FairFace (年龄组、性别、种族) |+| 情绪 | AffectNet-7 和 AffectNet-8 |+| 人脸状态 | FaceAttribNet: 眼部状态、眼镜、太阳镜、口罩 |+| 人脸质量 | eDifFIQA (T / S / M / L) |+| 人脸防伪 | MiniFASNet 活体检测 |+| 匿名化 | 5 种模糊方法 |+| 向量存储 | 基于 FAISS 的嵌入向量搜索 |++支持 CPU、Apple Silicon 和 CUDA。模型权重在首次使用时下载,并通过 SHA-256 校验。++</details>++<br>++### 检测人脸并测量特征++**人脸检测** · [文档](https://yakhyo.github.io/uniface/modules/detection/)++<img src="https://raw.githubusercontent.com/yakhyo/uniface/main/assets/demo/detection.jpg" width="100%">++**人脸关键点** · [文档](https://yakhyo.github.io/uniface/modules/landmarks/)++<img src="https://raw.githubusercontent.com/yakhyo/uniface/main/assets/demo/landmarks.jpg" width="100%">++**人脸网格** · [文档](https://yakhyo.github.io/uniface/modules/landmarks/#face-mesh-468-or-478-points-3d)++<img src="https://raw.githubusercontent.com/yakhyo/uniface/main/assets/demo/face_mesh.jpg" width="100%">++**人脸质量** · [文档](https://yakhyo.github.io/uniface/modules/quality/)++<img src="https://raw.githubusercontent.com/yakhyo/uniface/main/assets/demo/quality.jpg" width="100%">++### 分割人脸与人像++**人脸解析** · [文档](https://yakhyo.github.io/uniface/modules/parsing/)++<img src="https://raw.githubusercontent.com/yakhyo/uniface/main/assets/demo/parsing.jpg" width="100%">++**人脸分割** · [文档](https://yakhyo.github.io/uniface/modules/parsing/#xseg)++<img src="https://raw.githubusercontent.com/yakhyo/uniface/main/assets/demo/segmentation.jpg" width="100%">++<img src="https://raw.githubusercontent.com/yakhyo/uniface/main/assets/demo/segmentation_occluded.jpg" width="100%">++**人像抠图** · [文档](https://yakhyo.github.io/uniface/modules/matting/)++<img src="https://raw.githubusercontent.com/yakhyo/uniface/main/assets/demo/matting.jpg" width="100%">++<img src="https://raw.githubusercontent.com/yakhyo/uniface/main/assets/demo/matting_alt.jpg" width="100%">++### 估计头部朝向与视线方向++**头部姿态** · [文档](https://yakhyo.github.io/uniface/modules/headpose/)++<img src="https://raw.githubusercontent.com/yakhyo/uniface/main/assets/demo/headpose.jpg" width="100%">++**视线估计** · [文档](https://yakhyo.github.io/uniface/modules/gaze/)++<img src="https://raw.githubusercontent.com/yakhyo/uniface/main/assets/demo/gaze.jpg" width="100%">++### 分析人脸属性++**年龄与性别** · [文档](https://yakhyo.github.io/uniface/modules/attributes/)++<img src="https://raw.githubusercontent.com/yakhyo/uniface/main/assets/demo/demography.jpg" width="100%">++**情绪** · [文档](https://yakhyo.github.io/uniface/modules/attributes/#emotion)++<img src="https://raw.githubusercontent.com/yakhyo/uniface/main/assets/demo/emotion.jpg" width="100%">++**人脸状态** · [文档](https://yakhyo.github.io/uniface/modules/attributes/#faceattribnet)++<img src="https://raw.githubusercontent.com/yakhyo/uniface/main/assets/demo/face_states.jpg" width="100%">++<img src="https://raw.githubusercontent.com/yakhyo/uniface/main/assets/demo/face_states_alt.jpg" width="100%">++### 区分真实人脸与回放攻击++**人脸防伪** · [文档](https://yakhyo.github.io/uniface/modules/spoofing/)++<img src="https://raw.githubusercontent.com/yakhyo/uniface/main/assets/demo/spoofing.jpg" width="100%">++### 匹配人脸或进行匿名化处理++**人脸识别** · [文档](https://yakhyo.github.io/uniface/modules/recognition/)++<img src="https://raw.githubusercontent.com/yakhyo/uniface/main/assets/demo/verification.jpg" width="100%">++**人脸匿名化** · [文档](https://yakhyo.github.io/uniface/modules/privacy/)++<img src="https://raw.githubusercontent.com/yakhyo/uniface/main/assets/demo/anonymization.jpg" width="100%">++<br>++<div align="center">++**[快速开始](https://yakhyo.github.io/uniface/quickstart/)** · +[模型库](https://yakhyo.github.io/uniface/models/) · +[交互式笔记本](https://yakhyo.github.io/uniface/notebooks/) · +[模型许可证](https://yakhyo.github.io/uniface/license-attribution/) · +[参与贡献](CONTRIBUTING.md) · +[Discord](https://discord.gg/wdzrjr7R5j) · +[问题反馈](https://github.com/yakhyo/uniface/issues)++支持 CPU、Apple Silicon 和 CUDA。模型权重在首次使用时下载,并通过 SHA-256 校验。<br>+UniFace 使用 [MIT](LICENSE) 许可证;部分预训练权重采用其他许可证,因此在商业发布前请查看+[许可证说明](https://yakhyo.github.io/uniface/license-attribution/)。<br>+本项目与 Rocket Software 的 [Uniface](https://uniface.com/) 无关。++</div>diff --git a/docs/datasets.md b/docs/datasets.mdindex 2eefc58..7f86391 100644--- a/docs/datasets.md+++ b/docs/datasets.md@@ -6,21 +6,21 @@ Overview of all training datasets and evaluation benchmarks used by UniFace mode## Quick Reference-| Task | Dataset | Scale | Models |-| ----------- | ------------------------------------------------ | ---------------------- | ------------------------------------------- |-| Detection | [WIDER FACE](#wider-face) | 32K images | RetinaFace, SCRFD, CenterFace, YOLOv5-Face, YOLOv8-Face |-| Detection | Proprietary (Google) | - | BlazeFace |-| Recognition | [MS1MV2](#ms1mv2) | 5.8M images, 85.7K IDs | MobileFace, SphereFace |-| Recognition | [WebFace600K](#webface600k) | 600K images | ArcFace |-| Recognition | [WebFace4M / WebFace12M](#webface4m-webface12m) | 4M / 12M images | AdaFace, EdgeFace |-| Landmarks | [WFLW](#wflw) / [300W+CelebA](#300w-celeba) | 10K / 3.8K labeled + 202.6K unlabeled | PIPNet (98 / 68 pts) |-| Landmarks | Proprietary (Google) | - | Face Mesh (468 / 478 pts) |-| Attributes | Proprietary (Qualcomm) | - | FaceAttribNet |-| Gaze | [Gaze360](#gaze360) | 238 subjects | MobileGaze |-| Parsing | [CelebAMask-HQ](#celebamask-hq) | 30K images | BiSeNet |-| Attributes | [CelebA](#celeba) | 200K images | AgeGender |-| Attributes | [FairFace](#fairface) | Balanced demographics | FairFace |-| Attributes | [AffectNet](#affectnet) | Emotion labels | Emotion |+| Task | Dataset | Scale | Models |+| ----------- | ---------------------------------------------- | ------------------------------------- | ------------------------------------------------------- |+| Detection | [WIDER FACE](#wider-face) | 32K images | RetinaFace, SCRFD, CenterFace, YOLOv5-Face, YOLOv8-Face |+| Detection | Proprietary (Google) | - | BlazeFace |+| Recognition | [MS1MV2](#ms1mv2) | 5.8M images, 85.7K IDs | MobileFace, SphereFace |+| Recognition | [WebFace600K](#webface600k) | 600K images | ArcFace |+| Recognition | [WebFace4M / WebFace12M](#webface4m-webface12m) | 4M / 12M images | AdaFace, EdgeFace |+| Landmarks | [WFLW](#wflw) / [300W+CelebA](#300w-celeba) | 10K / 3.8K labeled + 202.6K unlabeled | PIPNet (98 / 68 pts) |+| Landmarks | Proprietary (Google) | - | Face Mesh (468 / 478 pts) |+| Attributes | Proprietary (Qualcomm) | - | FaceAttribNet |+| Gaze | [Gaze360](#gaze360) | 238 subjects | MobileGaze |+| Parsing | [CelebAMask-HQ](#celebamask-hq) | 30K images | BiSeNet |+| Attributes | [CelebA](#celeba) | 200K images | AgeGender |+| Attributes | [FairFace](#fairface) | Balanced demographics | FairFace |+| Attributes | [AffectNet](#affectnet) | Emotion labels | Emotion |---@@ -40,10 +40,15 @@ Large-scale face detection benchmark with images across 61 event categories. Con| Used by | RetinaFace, SCRFD, YOLOv5-Face, YOLOv8-Face |!!! info "Download & References"-**Paper**: [WIDER FACE: A Face Detection Benchmark](https://arxiv.org/abs/1511.06523)+ **Paper**: [WIDER FACE: A Face Detection Benchmark](https://arxiv.org/abs/1511.06523)**Download**: [http://shuoyang1213.me/WIDERFACE/](http://shuoyang1213.me/WIDERFACE/)+!!! tip "Prepared dataset for RetinaFace training"+ Organized WIDER FACE dataset with five-point landmark annotations:+ [Google Drive](https://drive.google.com/open?id=11UGV3nbVv1x9IC--_tK3Uxf7hA6rlbsS) or [Baidu Cloud](https://pan.baidu.com/s/1jIp9t30oYivrAvrgUgIoLQ) (password: `ruck`).+ Prepared by [biubug6](https://github.com/biubug6).+---### Face Recognition@@ -86,9 +91,9 @@ Medium-scale face recognition dataset from the WebFace series.Large-scale face recognition datasets from the WebFace260M collection. Used for training AdaFace models with adaptive quality-aware margin, and EdgeFace models for edge devices.-| Property | WebFace4M | WebFace12M |-| -------- | ------------- | -------------- |-| Images | ~4M | ~12M |+| Property | WebFace4M | WebFace12M |+| -------- | -------------------- | -------------- |+| Images | ~4M | ~12M || Used by | AdaFace IR_18, IR_50 | AdaFace IR_101 |!!! info "Source"@@ -153,12 +158,12 @@ WIDER FACE. Used to train the supervised PIPNet 98-point variant shipped with UnThe 68-point PIPNet variant is trained in a generalizable semi-supervised setting (GSSL):labeled images come from 300W and unlabeled images come from CelebA.-| Property | Value |-| --------------- | -------------------------------------------------------------------------------- |-| Labeled images | 3,837 (3,148 train: LFPW train + HELEN train + AFW; 689 test: LFPW test + HELEN test + iBUG) |-| Unlabeled | 202,599 (full CelebA; bounding boxes from RetinaFace per the PIPNet paper) |-| Annotation | 68-point iBUG layout |-| Used by | PIPNet 300W+CelebA-68 |+| Property | Value |+| -------------- | -------------------------------------------------------------------------------------------- |+| Labeled images | 3,837 (3,148 train: LFPW train + HELEN train + AFW; 689 test: LFPW test + HELEN test + iBUG) |+| Unlabeled | 202,599 (full CelebA; bounding boxes from RetinaFace per the PIPNet paper) |+| Annotation | 68-point iBUG layout |+| Used by | PIPNet 300W+CelebA-68 |!!! info "Reference"**Paper**: [PIPNet (Pixel-in-Pixel Net)](https://arxiv.org/abs/2003.03771) (IJCV 2021)@@ -228,13 +233,13 @@ data/Large-scale synthesized face dataset with large pose variations, generated from 300W by face profiling. Used for training head pose estimation models.-| Property | Value |-| ----------- | ----------------------------- |-| Images | ~122,000 (synthesized) |-| Source | 300W (profiled) |-| Pose range | ±90° yaw |-| Evaluation | AFLW2000 |-| Used by | All HeadPose models |+| Property | Value |+| ---------- | ---------------------- |+| Images | ~122,000 (synthesized) |+| Source | 300W (profiled) |+| Pose range | ±90° yaw |+| Evaluation | AFLW2000 |+| Used by | All HeadPose models |!!! info "Download & Reference"**Paper**: [Face Alignment Across Large Poses: A 3D Solution](https://arxiv.org/abs/1511.07212)@@ -351,8 +356,8 @@ Recognition models are evaluated across multiple benchmarks. Aligned 112x112 val!!! info "Download"**Kaggle**: [agedb-30-calfw-cplfw-lfw-aligned-112x112](https://www.kaggle.com/datasets/yakhyokhuja/agedb-30-calfw-cplfw-lfw-aligned-112x112)-| Benchmark | Description | Used by |-| ------------ | ----------------------------------------------------------------- | ------------------------------- |+| Benchmark | Description | Used by |+| ------------------ | ----------------------------------------------------------------- | ------------------------------- || **LFW** | Labeled Faces in the Wild - standard face verification benchmark | ArcFace, MobileFace, SphereFace || **CALFW** | Cross-Age LFW - face verification across age gaps | MobileFace, SphereFace || **CPLFW** | Cross-Pose LFW - face verification across pose variations | MobileFace, SphereFace |@@ -367,8 +372,8 @@ See [Model Zoo - Recognition](models.md#face-recognition-models) for per-model a### Gaze Estimation-| Benchmark | Metric | Description |-| -------------------- | ------------- | -------------------------------------------- |+| Benchmark | Metric | Description |+| -------------------------- | ------------- | -------------------------------------------- || **Gaze360 test set** | MAE (degrees) | Mean Absolute Error in gaze angle prediction |See [Model Zoo - Gaze](models.md#gaze-estimation-models) for per-model MAE scores.@@ -379,8 +384,8 @@ See [Model Zoo - Gaze](models.md#gaze-estimation-models) for per-model MAE scoreFor training your own models or reproducing results, see the following repositories:-| Task | Repository | Datasets Supported |-| ----------- | ------------------------------------------------------------------------- | ------------------------------- |+| Task | Repository | Datasets Supported |+| ----------- | ------------------------------------------------------------------------ | ------------------------------- || Detection | [yakhyo/retinaface-pytorch](https://github.com/yakhyo/retinaface-pytorch) | WIDER FACE || Recognition | [yakhyo/face-recognition](https://github.com/yakhyo/face-recognition) | MS1MV2, CASIA-WebFace, VGGFace2 || Gaze | [yakhyo/gaze-estimation](https://github.com/yakhyo/gaze-estimation) | Gaze360, MPIIFaceGaze |