Caffe - AshokBhat/ml GitHub Wiki
About
- Once popular deep learning framework, which is no longer actively developed
- Open-source, under a BSD license
- Written in C++, with a Python interface
- CAFFE (Convolutional Architecture for Fast Feature Embedding)
- https://github.com/BVLC/caffe
Features
- Supports many different types of deep learning architectures geared towards image classification and image segmentation.
- Supports CNN, R-CNN, LSTM and fully connected neural network designs.
- Supports GPU- and CPU-based acceleration computational kernel libraries such as NVIDIA cuDNN and Intel MKL
Caffe2
- In April 2017, Facebook announced Caffe2, which includes new features such as Recurrent Neural Networks.
- At the end of March 2018, Caffe2 was merged into PyTorch.
See also
- [PyTorch]] ](/AshokBhat/ml/wiki/[[Caffe2)