머신러닝 · GitHub

Coursera Machine Learning By Prof. Andrew Ng

The V Tensor Library

• Tensors — create, slice, indexed take/take_nd/take_flat/put, choose/select, round_decimals, nan_to_num, compress, indices, pad, set membership, reshape, transpose, move/roll axes, N-D diagonal views, NumPy-style Kronecker products, broadcast, map/reduce, einsum, and complex128 storage with elementwise and matrix products
• Autograd — reverse-mode AD; arbitrary computational graphs

🔥DM-NeRF in PyTorch (ICLR 2023)

List of DL topics and resources essential for cracking interviews

State-of-the-art, lightweight NLP tools for Turkish language. Developed by VNGRS.

A Python/Pytorch app for easily synthesising human voices

• Automatic dataset generation (with support for subtitles and audiobooks)
• Additional language support

⚡VoltaML is a lightweight library to convert and run your ML/DL deep learning models in high performance inference runtimes like TensorRT, TorchScript, ONNX and TVM.

Beautiful and Easy to use Stable Diffusion WebUI

• Easy install with Docker
• Clean and simple Web UI

Panoptic segmentation algorithms for 2D and 3D electron microscopy in napari

A Streaming-Native Serving Engine for TTS/STS Models

ETA: Extensible Toolkit for Analytics

Built a sentiment analysis model to predict the sentiment of a Financial News article. A comparative study of different optimizers used for training was done.

DMKaraoke is a lightweight web application for home karaoke. It uses machine learning to separate vocals and create word-by-word synced lyrics. The application is completely free, with no advertisements and zero cloud subscription fees. It creates karaoke on your own device.

• User queues: A mobile-friendly page for searching and adding songs with real-time updates.
• Video and lyrics downloads: Powered by YouTube, Musixmatch, and more; choose any karaoke style.

Papers, code and datasets about deep learning for 3D Object Detection.