3 repositorios
Awesome GitHub RepositoriesModel Visualization Tools
Utilities for visualizing the internal states, embeddings, and performance metrics of PyTorch models.
Distinct from PyTorch Training Frameworks: Focuses on the visual analysis of model performance and embeddings rather than the training execution framework.
Explore 3 awesome GitHub repositories matching artificial intelligence & ml · Model Visualization Tools. Refine with filters or upvote what's useful.
Awesome Model Visualization Tools GitHub Repositories
Encuentra los mejores repositorios con IA.Buscaremos los repositorios que mejor coincidan usando IA.
- fossasia/visdom
fossasia/visdom
10,268Ver en GitHubVisdom is a tool for scientific experiment tracking and real-time data monitoring. It provides a programmatic interface for broadcasting live plots, rich media, and training metrics from scripts to an interactive web dashboard. The project specializes in high-dimensional data analysis, offering capabilities to project complex feature sets into 2D space using t-SNE and visualize PyTorch model embeddings. It organizes visualizations into named environments, allowing users to isolate different experimental runs and compare plots across these environments in a single view. The system covers a br
Visualizes high-dimensional embeddings and training metrics using PyTorch and Numpy to analyze model performance.
Python - david-gpu/srez
david-gpu/srez
5,271Ver en GitHubSrez es un framework de aprendizaje profundo para superresolución de imágenes diseñado para escalar imágenes de baja resolución a características visuales nítidas de alta resolución. Funciona como una herramienta de entrenamiento de redes neuronales que emplea redes generativas antagónicas (GAN) para sintetizar detalles de imagen realistas. El proyecto incluye un visualizador de evolución de modelos que genera animaciones y lotes de imágenes para rastrear las mejoras visuales durante el proceso de entrenamiento. Utiliza una combinación de funciones de pérdida adversaria y L1 para optimizar los pesos del modelo y soporta puntos de control (checkpoints) de estado periódicos para la recuperación y el despliegue. El sistema cubre la construcción de redes neuronales utilizando capas feedforward, normalización de lotes y funciones de activación. También proporciona herramientas de observabilidad para comparar la calidad del escalado contra datos de referencia (ground truth) y monitorear el progreso del entrenamiento mediante secuencias visuales iterativas.
Ships a tool that creates animations and image batches to track visual improvements during training.
Python - instruction-tuning-with-gpt-4/gpt-4-llm
Instruction-Tuning-with-GPT-4/GPT-4-LLM
4,335Ver en GitHubThis project is an instruction tuning framework and synthetic data generator that uses high-capacity teacher models to produce instruction-following pairs for training smaller student models. It provides datasets and tools for supervised instruction tuning and reinforcement learning from human feedback. The framework specializes in cross-lingual tuning, offering high-quality instruction-following examples in English and Chinese to improve model generalization across different scripts. It includes a reward modeling tool for creating preference datasets and comparative ratings used to train rew
Generates performance figures and plots from extracted training data using a notebook-based workflow.
HTMLalpacachatgptgpt-4
