yibin-chn Goto Github PK

attention-bilstm

baby-llama2-chinese

用于从头预训练+SFT一个小参数量的中文LLaMa2的仓库；24G单卡即可运行得到一个具备简单中文问答能力的chat-llama2.

cmcm

Codes for our paper "Non-Autoregressive Cross-Modal Coherence Modelling" in ACM MM 2022

cnn-svm

An Architecture Combining Convolutional Neural Network (CNN) and Linear Support Vector Machine (SVM) for Image Classification

cool-fashion-papers

👔👗🕶️🎩 Cool resources about Fashion + AI! (papers, datasets, workshops, companies, ...) (constantly updating)

ctcdecode

PyTorch CTC Decoder bindings

ctcdecoder

Connectionist Temporal Classification (CTC) decoding algorithms: best path, prefix search, beam search and token passing. Implemented in Python and OpenCL.

deep-learning-for-bci

Resources for Book: Deep Learning for EEG-based Brain-Computer Interface: Representations, Algorithms and Applications

deep-painterly-harmonization

Code and data for paper "Deep Painterly Harmonization": https://arxiv.org/abs/1804.03189

dl-seq2seq

Implementation of papers on Deep Seq2seq learning using Pytorch.

drnet_cvpr2017

Detecting Visual Relationships with Deep Relational Networks

faster-rcnn.pytorch

A faster pytorch implementation of faster r-cnn

fund

天天基金数据处理

generative_inpainting

DeepFill v1/v2 with Contextual Attention and Gated Convolution, CVPR 2018, and ICCV 2019 Oral

icnn

Input Convex Neural Networks

im2pencil

The source code of CVPR19 'Im2Pencil: Controllable Pencil Illustration from Photographs'.

kcfpy

Python implementation of KCF tracking algorithm

ml-tutorial

machine learning algorithms and implementations

pairwise

Code for "Enhance Pointer Network with Pairwise Ordering Predictions"AAAI2020

partialconv

A New Padding Scheme: Partial Convolution based Padding

reinforcement-learning-an-introduction

Python implementation of Reinforcement Learning: An Introduction

scene-text-understanding

OCR, Scene-Text-Understanding, Text Recognition

spellchecker

Spell correct entire sentences using nltk freqdist and symspell

swapnet

Implemented SwapNet Architecture by training two input images and one output image in a single model