Repository Index

Pretrained model hub for Keras 3.

• deep-learning
• keras
• machine-learning
• nlp

High level network definitions with pre-trained weights in TensorFlow

• tensorflow
• model
• zoo
• deep-learning

Angora is a mutation-based fuzzer. The main goal of Angora is to increase branch coverage by solving path constraints without symbolic execution.

• fuzzing
• security
• fuzzer
• afl

:bullettrain_front: Lazyload images, iframes, widgets with a standalone JavaScript lazyloader

onnx-go gives the ability to import a pre-trained neural network within Go without being linked to a framework or library.

• go
• onnx
• neural-network
• open-source

Flexible type system for Ruby with coercions and constraints

• dry-rb
• types
• coercion
• constraints

Train and Deploy an ML REST API to predict crypto prices, in 10 steps

• deployment
• ml
• mlops
• crypto

🚀 Catalyst is a C# Natural Language Processing library built for speed. Inspired by spaCy's design, it brings pre-trained models, out-of-the box support for training word and document embeddings, and flexible entity recognition models.

• nlp
• natural-language-processing
• artificial-intelligence
• embeddings

vibe coded supermimic within 1h, LAFAN passed within 1.5 gpuh training

A lightweight, accurate and robust monocular visual inertial odometry based on Multi-State Constraint Kalman Filter.

• visual-inertial-odometry
• msckf
• localization
• ekf-mono-slam

A lightweight, secure, easy-to-use crypto library suitable for constrained environments.

• crypto
• embedded-systems
• cryptography
• embedded

DNABERT: pre-trained Bidirectional Encoder Representations from Transformers model for DNA-language in genome

• kmer
• dnabert-model
• kmer-format
• gpu

[iOS] Animated analog flip numbers like airport/train-station displays (Swift/SwiftUI ready)

• ios
• animation
• cocoapod
• customizable

ROS package for dynamic obstacle avoidance for ground robots trained with deep RL

• tensorflow
• ros
• deep-reinforcement-learning
• collision-avoidance

BioBERT: a pre-trained biomedical language representation model for biomedical text mining

RBDL is a C++ library that contains some essential and efficient rigid body dynamics algorithms such as the Articulated Body Algorithm (ABA) for forward dynamics, Recursive Newton-Euler Algorithm (RNEA) for inverse dynamics, the Composite Rigid Body Algorithm (CRBA) for the efficient computation of the joint space inertia matrix and is also able to compute forward dynamics with external contact constraints and collision impulses. Furthermore it has some basic support for forward and inverse kinematics.

• articulated-body-algorithm
• inverse-dynamics
• forward-dynamics
• multi-body-dynamics

A collection of state-of-the-art algorithms for the training, serving and interpretation of Decision Forest models in Keras.

• python
• machine-learning
• random-forest
• tensorflow

List of topic-specific resources to help you prepare for Symfony certification

• list
• links
• symfony
• certification

Skill training with a corruption and reconstruction loop: train an agent's skill library, not its weights.

Database constraints made easy for ActiveRecord.

• ruby
• rails
• activerecord
• database

Update version constraints in your Terraform / OpenTofu configurations

• terraform
• hcl
• go
• opentofu

oneAPI Data Analytics Library (oneDAL)

• onedal
• data-analysis
• oneapi
• machine-learning

🚧 Under construction — no-training RefMod reference adapters for MiniMax H3 (compress reference images/videos into tiny latents, no training needed).

• comfyui
• comfyui-custom-node
• comfyui-extension
• comfyui-manager

BlueBERT, pre-trained on PubMed abstracts and clinical notes (MIMIC-III).

• bert
• bert-model
• natural-language-processing
• pubmed