raykali Goto Github PK

bilibili

source code

cudnn_conv_int8

Testing INT8 convolution on cuDNN v6

cv-papers

计算机视觉相关论文整理、记录、分享; 包括图像分类、目标检测、视觉跟踪/目标跟踪、人脸识别/人脸验证、OCR/场景文本检测及识别等领域。欢迎加星,欢迎指正错误,同时也期待能够共同参与！！! 持续更新中... ...

detector

Detector by pytorch

distro

Unofficial maintenance repository of Torch7. It supports CUDA10.1, Volta, Turing, Docker https://hub.docker.com/r/nagadomi/torch7

eeover

Ellipse-Ellipse overlap area

ellipseoverlaps

Given two arbitrary ellipses calculate their overlap area or their overlap distance.

layoutgan

A reproducing for article LayoutGAN: Generating Graphic Layouts with Wireframe Discriminators.

layoutgan-1

LayoutGAN implementation, (incomplete)

m3u8-downloader

m3u8 视频在线提取工具

models

A collection of pre-trained, state-of-the-art models in the ONNX format

netron

Visualizer for deep learning and machine learning models

numpy-ml

Machine learning, in numpy

numpy_neural_network

仅使用numpy从头开始实现神经网络,包括反向传播公式推导过程; numpy构建全连接层、卷积层、池化层、Flatten层；以及图像分类案例及精调网络案例等,持续更新中... ...

nvidia

onnx

Open Neural Network Exchange

open-bilibili

Source code backup for open-biliili. Only for learning purpose!!

pure_prng

Generate professional pseudo-random number package in python.

pwc

Papers with code. Sorted by stars. Updated weekly.

python

All Algorithms implemented in Python

pytorch-cyclegan-and-pix2pix

Image-to-image translation in PyTorch (e.g., horse2zebra, edges2cats, and more)

random-seedable

Fully-fledged random number generator library with high quality implementations of Xorshift, Xorwow, Mersenne Twister, PCG and LCG. Each implements a standard API producing number distributions that exactly match the original implementations.

simple-faster-rcnn-pytorch

A simplified implemention of Faster R-CNN that replicate performance from origin paper

simple-int8-pytorch-implement

int8 calibration implement and inference (help you understand int8 Q)

ssr_ubuntu

Linux下科学上网工具

tutorials

Tutorials for using ONNX

videosuperresolution

A collection of state-of-the-art video or single-image super-resolution architectures, reimplemented in tensorflow.