Stars
A large model-based chatbot builder that can quickly integrate AI models (including ChatGPT, Claude, Gemini) into various software applications (such as Telegram, Gmail, Slack, and websites).
Using Autoencoder CNN and Stacked LSTM RNN to train an computer to generate it's own dance videos
LSTM network trained on dance videos using audio( songs ) as input and human pose estimated coordinates as output. Trained LSTM models are then used to generate dance videos using songs as input.
Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text frontend, Speaker Verification System, End-to-End Speech Translatio…
Python - 100天从新手到大师
Hikyuu Quant Framework 基于C++/Python的极速开源量化交易研究框架,同时可基于策略部件进行资产重用,快速累积策略资产。
MATLAB implementation of the paper "Image Denoising Via Sparse and Redundant Representations Over Learned Dictionaries"
Code and slides for the "Deep Learning (For Audio) With Python" course on TheSoundOfAI Youtube channel.
A pytorch reimplementation of liuwei16/CSP, their trained keras weights are loaded in pytorch.
CCNet: Criss-Cross Attention for Semantic Segmentation (TPAMI 2020 & ICCV 2019).
Pytorch implementation of "Adapted Center and Scale Prediction: More stable and More Accurate"
Dual Attention Network for Scene Segmentation (CVPR2019)
A paper list of object detection using deep learning.
CenterNet (Objects as Points) implementation in Keras and Tensorflow
Distribution-Aware Coordinate Representation for Human Pose Estimation
Part Segmentation for EANet
diffGrad: An Optimization Method for Convolutional Neural Networks
cvpr2024/cvpr2023/cvpr2022/cvpr2021/cvpr2020/cvpr2019/cvpr2018/cvpr2017 论文/代码/解读/直播合集,极市团队整理