qingswu's repositories
adamw_bfloat16
AdamW optimizer for bfloat16 models in pytorch 🔥.
bertviz
BertViz: Visualize Attention in NLP Models (BERT, GPT2, BART, etc.)
ByteTrack
ByteTrack: Multi-Object Tracking by Associating Every Detection Box
codegeex-vscode-extension
VS Code extension for CodeGeeX
codetiming
A flexible, customizable timer for your Python code
efficient-descriptors
:rocket::rocket: Revisiting Binary Local Image Description for Resource Limited Devices
extract-video-ppt
extract the ppt in the video
llm-analysis
Latency and Memory Analysis of Transformer Models for Training and Inference
lycon2
A minimal and fast image library for Python and C++
Megatron-LM
Ongoing research training transformer models at scale
mmdetection
OpenMMLab Detection Toolbox and Benchmark
OneNet
What Makes for End-to-End Object Detection, ICML2021
onnx-simplifier
Simplify your onnx model
opencv
Open Source Computer Vision Library
parler-tts
Inference and training library for high-quality TTS models.
PFLD-pytorch
PFLD pytorch Implementation
SLidR
Official PyTorch implementation of "Image-to-Lidar Self-Supervised Distillation for Autonomous Driving Data"
stable-diffusion
A latent text-to-image diffusion model
torch2trt_dynamic
A pytorch to tensorrt convert with dynamic shape support
UltraEval
An open source framework for evaluating foundation models.
UNPG
Unified Negative Pair Generation toward Well-discriminative Feature Space for Face Recognition
VideoProcessingFramework
Set of Python bindings to C++ libraries which provides full HW acceleration for video decoding, encoding and GPU-accelerated color space and pixel format conversions
warp-transducer
fixing warp-transducer building issues with latest cuda11.0+ and pytorch 1.12 in https://github.com/HawkAaron/warp-transducer