Sign in

Repository Index

132,241 visible repositories in the index

Tags: All Tags
Tags

A repository shows when it has any selected Tag.

Filters (1)

Filters

Clear all filters

1,849–1,872 of 2,460 · Most stars

This repository contains the source codes for the paper "AtlasNet: A Papier-Mâché Approach to Learning 3D Surface Generation ". The network is able to synthesize a mesh (point cloud + connectivity) from a low-resolution point cloud, or from an image.

Support PointRend, Fast_SCNN, HRNet, Deeplabv3_plus(xception, resnet, mobilenet), ContextNet, FPENet, DABNet, EdaNet, ENet, Espnetv2, RefineNet, UNet, DANet, HRNet, DFANet, HardNet, LedNet, OCNet, EncNet, DuNet, CGNet, CCNet, BiSeNet, PSPNet, ICNet, FCN, deeplab)

  • deeplab-v3-plus
  • deeplabv3plus
  • xception
  • fast-scnn

Training-free Spectrum acceleration for ComfyUI’s native MiniMax H3 audio-video model. Uses Chebyshev ridge feature forecasting to skip selected H3 transformer evaluations, with adaptive scheduling, sampler-aware support for Euler, ER-SDE, RES, SEEDS and SA-Solver, CPU/VRAM history storage, and fail-closed native fallbacks.

This project isn't finished yet. Goal is to create a SickBeard, CouchPotato, Headphones-like application for ebooks. Headphones is used as a base, so there are still a lot of references to it.

Paddle Multimodal Integration and eXploration, supporting mainstream multi-modal tasks, including end-to-end large-scale multi-modal pretrain models and diffusion model toolbox. Equipped with high performance and flexibility.

The last Micro Web Server for IoTs (MicroPython) or large servers (CPython), that supports WebSockets, routes, template engine and with really optimized architecture (mem allocations, async I/Os). Ready for ESP32, STM32 on Pyboard, Pycom's chipsets (WiPy, LoPy, ...). Robust, efficient and documented!

Temporian is an open-source Python library for preprocessing ⚡ and feature engineering 🛠 temporal data 📈 for machine learning applications 🤖

  • python
  • cpp
  • feature-engineering
  • temporal-data

Inspect, visualize and intervene on any operation in any neural network. Capture every activation and gradient, the full computational graph and 800+ metadata fields without changing model code. Supports PyTorch, JAX, TensorFlow, MLX, PaddlePaddle and tinygrad. Validated on 6400+ models. Built for researchers and their AI agents.