captum
Model explainer
Provides tools and algorithms to understand how machine learning models make predictions
Model interpretability and understanding for PyTorch
5k stars
278 watching
503 forks
Language: Python
last commit: 2 months ago
Linked from 4 awesome lists
feature-attributionfeature-importanceinterpretabilityinterpretable-aiinterpretable-ml
Related projects:
Repository | Description | Stars |
---|---|---|
| A PyTorch-based library for Bayesian optimization, providing a modular interface for composing and optimizing probabilistic models. | 3,126 |
| A collection of curated examples showcasing various PyTorch applications in computer vision, natural language processing, and reinforcement learning. | 22,530 |
| A Python-based framework for training and testing image captioning models using PyTorch. | 1,458 |
| Analyzing knowledge development and evolution in large language models during training | 2,309 |
| A C++ implementation of PyTorch tutorials | 1,978 |
| A repository providing tools and examples to serve PyTorch models as C++ inference applications. | 226 |
| A comprehensive tutorial project that provides code examples for learning PyTorch by implementing various deep learning models and demonstrating their usage. | 30,401 |
| A collection of notes and references on deploying deep learning models in production environments | 4,313 |
| This is an implementation of the PointNet algorithm in PyTorch for 3D point cloud classification and segmentation tasks. | 2,175 |
| A Python library providing tensors and dynamic neural networks with strong GPU acceleration | 84,978 |
| Trains a large-scale PyTorch language model on the 1-Billion Word dataset | 123 |
| An implementation of Google's 2018 BERT model in PyTorch, allowing pre-training and fine-tuning for natural language processing tasks | 6,251 |
| A tutorial repository for building sentiment analysis models with PyTorch using various architectures and techniques. | 4,419 |
| A comprehensive library for training and applying deep learning models for image segmentation | 9,829 |
| This project provides an official PyTorch implementation of a method to interpret and edit vision-language representations to mitigate hallucinations in image captions. | 46 |