3 Repos
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.
Visdom 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.
Srez ist ein Deep-Learning-Framework für Image-Super-Resolution, das entwickelt wurde, um niedrig aufgelöste Bilder in scharfe, hochauflösende visuelle Features hochzuskalieren. Es fungiert als Trainings-Tool für neuronale Netze, das generative gegnerische Netzwerke (GANs) einsetzt, um realistische Bilddetails zu synthetisieren. Das Projekt enthält einen Visualizer für die Modellentwicklung, der Animationen und Bildstapel generiert, um visuelle Verbesserungen während des Trainingsprozesses zu verfolgen. Es nutzt eine Kombination aus Adversarial- und L1-Loss-Funktionen zur Optimierung der Modellgewichte und unterstützt regelmäßige State-Checkpoints zur Wiederherstellung und Bereitstellung. Das System deckt den Aufbau neuronaler Netze mittels Feedforward-Layern, Batch-Normalisierung und Aktivierungsfunktionen ab. Es bietet zudem Observability-Tools zum Vergleich der Upscaling-Qualität mit Ground-Truth-Daten und zur Überwachung des Trainingsfortschritts durch iterative visuelle Sequenzen.
Ships a tool that creates animations and image batches to track visual improvements during training.
This 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.