Caffe (Convolutional Architecture for Fast Feature Embedding) is an open-source deep learning framework developed by Yangqing Jia at the University of California, Berkeley and released in 2013. It was popular mainly for image recognition with convolutional neural networks, as it ran fast and models were defined in configuration files. The last version, 1.0, appeared in 2017; its successor Caffe2 was merged into PyTorch in 2018. Caffe is rarely used for new projects today.
PyTorch is an open-source framework for machine learning and deep learning in the Python programming language. It was originally developed at Meta (then Facebook) and has been stewarded since 2022 by the PyTorch Foundation under the umbrella of the Linux Foundation. PyTorch is widely used in research and industry because it lets developers build models flexibly, train them on GPUs and test them step by step; many well-known language and image models are built with it.
A convolutional neural network (CNN) is a neural network architecture particularly suited to image data. It scans the input with small filters, detecting simple features such as edges in the first layers and more complex shapes in deeper ones. CNNs shaped image recognition for many years and are used, for example, to spot defects in product photos or in medical image analysis.
TensorFlow is an open-source machine learning framework developed by Google and released in 2015. It is used to build, train and deploy neural networks in applications, on servers or on mobile devices. Keras provides an accessible high-level interface; typical uses include image classification, forecasting and recommendation systems.
Open Neural Network Exchange (ONNX) is an open file format for machine learning models, introduced in 2017 by Microsoft and Facebook (now Meta) and now hosted by the LF AI & Data Foundation. A model trained in PyTorch, for example, can be exported to ONNX and run with other tools or runtimes such as ONNX Runtime. This makes it easier to switch between frameworks and deploy on different hardware.
