cheng xu's starred repositories
PaddleOCR
Awesome multilingual OCR toolkits based on PaddlePaddle (practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and deployment among server, mobile, embedded and IoT devices)
instant-ngp
Instant neural graphics primitives: lightning fast NeRF and more
AnimateAnyone
Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation
flash-attention
Fast and memory-efficient exact attention
StreamDiffusion
StreamDiffusion: A Pipeline-Level Solution for Real-Time Interactive Generation
nerfstudio
A collaboration friendly studio for NeRFs
py-faster-rcnn
Faster R-CNN (Python implementation) -- see https://github.com/ShaoqingRen/faster_rcnn for the official MATLAB version
async-profiler
Sampling CPU and HEAP profiler for Java featuring AsyncGetCallTrace + perf_events
awesome-NeRF
A curated list of awesome neural radiance fields papers
OutfitAnyone
Outfit Anyone: Ultra-high quality virtual try-on for Any Clothing and Any Person
annotated-transformer
An annotated implementation of the Transformer paper.
OpenPDF
OpenPDF is a free Java library for creating and editing PDF files, with a LGPL and MPL open source license. OpenPDF is based on a fork of iText. We welcome contributions from other developers. Please feel free to submit pull-requests and bugreports to this GitHub repository.
MobileNet-SSD
Caffe implementation of Google MobileNet SSD detection network, with pretrained weights on VOC0712 and mAP=0.727.
DeepSpeed-MII
MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.
pytorch-ssd
MobileNetV1, MobileNetV2, VGG based SSD/SSD-lite implementation in Pytorch 1.0 / Pytorch 0.4. Out-of-box support for retraining on Open Images dataset. ONNX and Caffe2 support. Experiment Ideas like CoordConv.
long-range-arena
Long Range Arena for Benchmarking Efficient Transformers
multi-lora-fine-tune
Provide Efficient LLM Fine-Tune via Multi-LoRA Optimization
Computer_Vision-Object_Detection-Scoliosis_demo
Given as an input either a frontal or a sagittal x-ray image, detect the spinal vertebrae and estimate the Cobb angle, and the shape of the scoliosis.