Cadene/pretrained-models.pytorch
Pretrained Models.pytorch
This project is a pretrained model library for PyTorch, providing a collection of convolutional neural network architectures and weights. It serves as a computer vision model zoo for image classification and feature extraction, offering a framework for transfer learning where pretrained networks are adapted for custom image recognition tasks.
The library focuses on transforming images into high-level numerical representations and calculating class probability scores. It includes utilities for downloading and initializing standard architectures such as ResNet, Inception, and Xception.
Capabilities cover the entire computer vision pipeline, from retrieving model-specific normalization metadata and input dimensions to executing inference. It supports both full image classification and layer-based feature extraction by isolating high-level tensors for downstream analysis.
Features
- Pretrained Model Zoos - Serves as a centralized model zoo for downloading and initializing various pretrained convolutional neural networks.
- Computer Vision Models - Offers a comprehensive collection of neural network architectures for image classification and feature extraction.
- Convolutional Neural Network Architectures - Provides standard convolutional neural network architectures like ResNet, Inception, and Xception.
- Feature Extraction - Transforms raw images into high-level numerical representations by passing them through pretrained feature extraction layers.
- Feature Extractors - Uses pretrained models to transform images into high-dimensional vector representations for downstream analysis.
- Image Classification - Processes images through neural networks to assign labels and predict class probabilities.
- Computer Vision - Implements a full computer vision pipeline to calculate class probability scores for image recognition.
- Transfer Learning Frameworks - Provides the tools and pretrained networks necessary to adapt models to new image recognition tasks via fine-tuning.
- Pretrained Model Libraries - Provides a library of pretrained convolutional neural network architectures specifically for PyTorch users.
- Transfer Learning - Facilitates adapting pretrained weights to custom image recognition tasks with limited labeled data.
- Pretrained Weight Initializers - Loads pre-optimized network weights from external files to enable immediate inference or transfer learning.
- PyTorch Tensor Operations - Utilizes the PyTorch framework to execute tensor operations and mathematical computations for image processing.
- PyTorch Computer Vision Pipelines - Provides an end-to-end computer vision workflow implemented entirely within the PyTorch ecosystem.
- Input Normalizers - Includes utilities to normalize image pixels using mean and standard deviation values specific to each architecture.
- Neural Layer Extraction - Allows isolating high-level tensors by truncating the final classification layer for downstream analysis.
- Developer Tools - Reproducible research models.
- Model Utilities and Tools - Repository for reproducing research results.
- Learning and Reference - Collection of pre-trained convolutional neural networks.
Star history
How this analysis was created: This summary and feature list are AI-generated from collected project material and can contain mistakes. Stars, license and language are imported from GitHub. Inclusion does not mean that we have tested or audited this project. Check the source documentation for any feature you depend on. Learn more on our About page.
