3 repository-uri
Tools for visualizing internal layer activations and decision-making processes during model execution.
Distinct from Model Inspection Tools: Distinct from Model Inspection Tools by focusing on runtime activation visualization rather than static metadata analysis
Explore 3 awesome GitHub repositories matching artificial intelligence & ml · Runtime Activation Visualizations. Refine with filters or upvote what's useful.
This project is a TensorFlow and Keras implementation of the Mask R-CNN architecture. It provides a framework for performing simultaneous object detection and instance segmentation, transforming raw images into segmented masks and bounding boxes for individual object identification. The toolset enables custom computer vision training through fine-tuning pre-trained weights and integrating user-provided datasets. It includes capabilities for distributed GPU training to accelerate the optimization of large vision models. The framework covers model evaluation using standard precision metrics an
Includes diagnostics for internal model inspection through the visualization of layer activations.
React hotkeys is a keyboard shortcut manager designed for declaring, scoping, and handling keyboard shortcuts and focus areas in React applications. It allows developers to define declarative shortcuts by binding key combinations or sequences to action names and handler functions, enabling components to respond predictably to user input. The library provides distinct mechanisms for managing how keyboard events interact with the document. It supports scoping hotkeys to specific component subtrees and DOM descendants to match natural browser focus behavior, alongside global key event handling t
Retrieves active mappings and registered actions from mounted components to support help dialog generation.
Qt.py is a compatibility layer and shim library that enables Python desktop applications to run across multiple graphical toolkit bindings without changing underlying code. It standardizes interface loading and normalizes divergent application programming interfaces across various versions of PySide and PyQt. The library bridges disparate graphical toolkit implementations by normalizing behavioral differences and unifying multiple binding options through a single compatibility layer. It provides standardized functions for loading interface definition files into new or existing widget instance
Exposes metadata attributes indicating the currently active graphical toolkit, project version, and underlying component versions at runtime.