model-visualization

moDel Agnostic Language for Exploration and eXplanation

A multi-functional library for full-stack Deep Learning. Simplifies Model Building, API development, and Model Deployment.

LiteCNN: Intuitive Python library for creating, training and visualizing convolutional neural networks. Features simplified CNN layer definition, automated training workflows, model visualization, and seamless Keras-to-ONNX conversion. Includes 15 pre-configured popular models for immediate use.

PyTorch model architecture diagram generator: neural network diagram, SVG, PNG, TikZ, LaTeX

Portable ML bridges and visual neural-network topology across PyTorch, Keras, TensorFlow, and serialized models.

Local-first ML experiments with complete visual explanations from data and layers to gradients, health, and replay.

Inspectable PyTorch training with visual layer shapes, activations, sparsity, gradients, and topology.

Librería Python para generar reportes de evaluación (clasificación, regresión, forecasting) con métricas y gráficos listos en Markdown, JSON y pronto HTML.

Powerful Python tool for visualizing and interacting with pre-trained Masked Language Models (MLMs) like BERT. Features include self-attention visualization, masked token prediction, model fine-tuning, embedding analysis with PCA/t-SNE, and SHAP-based model interpretability.

Display outputs of each layer in CNN models

Publication-ready forest plots for regression models (logistic, linear, gamma, ordinal) in Python.

This will utilize neural network and machine learning models to paper trade on the stock market.

Easy-to-use UI based tool that visualizes the internal layers and activations of any Pytorch network that takes image as input , built using PyQt

Visualizing Modern LLM Mechanics, Loss Landscapes & HPC Topologies

Readable architecture diagrams for PyTorch models. The tracer supplies the facts, an agent supplies the abstraction, and a coverage check proves nothing was silently dropped.

Code to visualize how different layers view the input when the output is changed. Also visualize the salient features as seen by the input image