郑启航's repositories
Circle-Loss
Tensorflow2 implementation of CircleLoss. Support class-level, sparse class-level, pair-wise labels
ai-matting-tool
Batch auto matting tool base on PoolNet
AnimeFaceBoxes
Fast anime face detection
atl
A Tensor Language
AutoKernel
AutoKernel 是一个简单易用，低门槛的自动算子优化工具，提高深度学习算法部署效率。
EyerissF
An Eyeriss Chip (researched by MIT, a CNN accelerator) simulator and New DNN framework "Hive"
FSRCNN-pytorch
PyTorch implementation of Accelerating the Super-Resolution Convolutional Neural Network (ECCV 2016)
jittor
Jittor is a high-performance deep learning framework based on JIT compiling and meta-operators.
libonnx
A lightweight, portable pure C99 onnx inference engine for embedded devices with hardware acceleration support.
MNN
MNN is a blazing fast, lightweight deep learning framework, battle-tested by business-critical use cases in Alibaba
ncnn
ncnn is a high-performance neural network inference framework optimized for the mobile platform
oneDNN
oneAPI Deep Neural Network Library (oneDNN)
PaddleGAN
PaddlePaddle GAN library and applications.
PatternSourceGenerator
Generator Pattern from nncase expr syntax
ppl.nn
A primitive library for neural network
pylance-bug-report
pylance issue with #1751
synergy-core
Open source core of Synergy, the keyboard and mouse sharing tool
tvm
Open deep learning compiler stack for cpu, gpu and specialized accelerators
vod-converter
Convert between visual object detection datasets
White-box-Cartoonization
Official tensorflow implementation for CVPR2020 paper “Learning to Cartoonize Using White-box Cartoon Representations”
YOLOX
YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with ONNX, TensorRT, ncnn, and OpenVINO supported.