quziyan's repositories
Post-Processing-for-Matting
We often change background after matting. But due to the matting precision, the edge of body, especially hair, often leak pixels contain background, so we need some post-processing like this.
MultiClassDataLayer
These code follow the data providers in papers: [Learning a Metric Embedding for Face Recognition using the Multibatch Method] and [Improved Deep Metric Learning with Multi-class N-pair Loss Objective]
AI-Chip
A list of ICs and IPs for AI, Machine Learning and Deep Learning.
aimet
AIMET is a library that provides advanced quantization and compression techniques for trained neural network models.
awesome-chatgpt-prompts-zh
ChatGPT 中文调教指南。各种场景使用指南。学习怎么让它听你的话。
caffe
Caffe: a fast open framework for deep learning.
Chain-of-ThoughtsPapers
A trend starts from "Chain of Thought Prompting Elicits Reasoning in Large Language Models".
chatgpt-api
Node.js client for the unofficial ChatGPT API. 🔥
ChatGPTPapers
Must-read papers, related blogs and API tools on the pre-training and tuning methods for ChatGPT.
corex_topic
Hierarchical unsupervised and semi-supervised topic models for sparse count data with CorEx
DataTransformerLayer
cuda version data augumentation layer in caffe
EmoBank
This repository contains EmoBank, a large-scale text corpus manually annotated with emotion according to the psychological Valence-Arousal-Dominance scheme.
Focal-Loss
The implementation of Focal-Loss Using Caffe
Chinese-ChatLLaMA
中文LLaMA基础模型;中文ChatLLaMA对话模型;NLP预训练/指令微调数据集
horovod
Distributed training framework for TensorFlow, Keras, PyTorch, and MXNet.
literature-books
书籍txt
lsoftmax-pytorch
PyTorch implementation Large-Margin Softmax (L-Softmax) loss
Luotuo-Chinese-LLM
骆驼(Luotuo): Open Sourced Chinese Language Models. Developed by 陈启源 @ 华中师范大学 & 李鲁鲁 @ 商汤科技 & 冷子昂 @ 商汤科技
networkx
Network Analysis in Python
pyblur
blurring routines
pytorch-histogram-loss
PyTorch implementation for Histogram Loss
SynthTabNet
Dataset of PNG images from synthetically generated table layouts with annotations in JSONL files
Top2Vec
Top2Vec learns jointly embedded topic, document and word vectors.