機械学習 · GitHub

C#/F# bindings for NumPy - a fundamental library for scientific computing, machine learning and AI

Pytorch Bindings for warp-ctc

Data and code of my Medium story on stock prediction with TensorFlow

Syllable-aware BPE tokenizer for the Amharic language (አማርኛ) – fast, accurate, trainable.

SSSegmentation: An Open Source Supervised Semantic Segmentation Toolbox Based on PyTorch.

Peer-to-peer machine learning

Data science for beginners involves learning to extract insights from data using statistics, programming (Python/R), and visualization. Key steps include data collection, cleaning, analysis, modeling, and communicating findings. Beginners should start with Python, basic math (linear algebra/calculus), and build projects to create a portfolio.

V2E: From video frames to DVS events

A browser-based tool for image annotation

Implementation of a hierarchical CNN based model to detect Big Five personality traits

A TensorFlow-inspired neural network library built from scratch in C# 7.3 for .NET Standard 2.0, with GPU support through cuDNN

Run TensorFlow models in C++ without installation and without Bazel

Serverless LLM Serving for Everyone.

Code for YouTube series: Deep Learning for Audio Classification

Code for the book Deep Learning From Scratch, from O'Reilly September 2019

MelGAN vocoder (compatible with NVIDIA/tacotron2)

Implementation of: "Exploring Randomly Wired Neural Networks for Image Recognition"

A Pytorch Knowledge Distillation library for benchmarking and extending works in the domains of Knowledge Distillation, Pruning, and Quantization.