Pinned Repositories
3DDFA
The PyTorch improved version of TPAMI 2017 paper: Face Alignment in Full Pose Range: A 3D Total Solution.
bark
🔊 Text-Prompted Generative Audio Model
cat-sam
The official implementation of "CAT-SAM: Conditional Tuning Network for Few-Shot Adaptation of Segmentation Anything Model".
CogVLM
a state-of-the-art-level open visual language model | 多模态预训练模型
czsc
缠中说禅技术分析工具；缠论；股票；期货；Quant；量化交易
donut
Official Implementation of OCR-free Document Understanding Transformer (Donut) and Synthetic Document Generator (SynthDoG), ECCV 2022
EagleEye
(ECCV'2020 Oral)EagleEye: Fast Sub-net Evaluation for Efficient Neural Network Pruning
ECCV20-STDN
Source code for ECCV 2020 paper: On Disentangling Spoof Trace for Generic Face Anti-Spoofing
EmotiVoice
EmotiVoice 😊: a Multi-Voice and Prompt-Controlled TTS Engine
face-alignment
:fire: 2D and 3D Face alignment library build using pytorch
leung-yaya's Repositories
leung-yaya/3DDFA
The PyTorch improved version of TPAMI 2017 paper: Face Alignment in Full Pose Range: A 3D Total Solution.
leung-yaya/bark
🔊 Text-Prompted Generative Audio Model
leung-yaya/cat-sam
The official implementation of "CAT-SAM: Conditional Tuning Network for Few-Shot Adaptation of Segmentation Anything Model".
leung-yaya/CogVLM
a state-of-the-art-level open visual language model | 多模态预训练模型
leung-yaya/donut
Official Implementation of OCR-free Document Understanding Transformer (Donut) and Synthetic Document Generator (SynthDoG), ECCV 2022
leung-yaya/EagleEye
(ECCV'2020 Oral)EagleEye: Fast Sub-net Evaluation for Efficient Neural Network Pruning
leung-yaya/ECCV20-STDN
Source code for ECCV 2020 paper: On Disentangling Spoof Trace for Generic Face Anti-Spoofing
leung-yaya/EmotiVoice
EmotiVoice 😊: a Multi-Voice and Prompt-Controlled TTS Engine
leung-yaya/face-alignment
:fire: 2D and 3D Face alignment library build using pytorch
leung-yaya/face_toolbox_keras
A collection of deep learning frameworks ported to Keras for face analysis.
leung-yaya/mediapipe
MediaPipe is the simplest way for researchers and developers to build world-class ML solutions and applications for mobile, edge, cloud and the web.
leung-yaya/stormljj
leung-yaya/whisper
Robust Speech Recognition via Large-Scale Weak Supervision
leung-yaya/MobileVLM
Strong and Open Vision Language Assistant for Mobile Devices
leung-yaya/open_clip
An open source implementation of CLIP.
leung-yaya/unilm
Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities