RSS Feed - Blog
About: Caffe aims to provide computer vision scientists with a clean, modifiable implementation of state-of-the-art deep learning algorithms. We believe that Caffe is the fastest available GPU CNN implementation. Caffe also provides seamless switching between CPU and GPU, which allows one to train models with fast GPUs and then deploy them on non-GPU clusters. Even in CPU mode, computing predictions on an image takes only 20 ms (in batch mode). Changes:LOTS of stuff: https://github.com/BVLC/caffe/releases/tag/v0.9999
|
Projects authored by bvlc.
Search
Manage
Sort by
Filter by
Latest Thoughts
- MLOSS workshop at ICML 2015: Open Ecosystems
by Antti Honkela on March 30, 2015
- A third of the top 100 papers are about software
by Cheng Soon Ong on October 30, 2014
- Open Machine Learning Workshop
by Cheng Soon Ong on July 28, 2014
- Machine Learning Distro
by Cheng Soon Ong on July 22, 2014
- Google Summer of Code 2014
by Cheng Soon Ong on June 3, 2014
- Reproducibility is not simple
by Cheng Soon Ong on March 30, 2014
- Keynotes at ACML 2013
by Cheng Soon Ong on November 14, 2013
- What does the “OSS” in MLOSS mean?
by Mark Reid on September 1, 2013
- Code review for science
by Cheng Soon Ong on August 14, 2013
- GSoC 2013
by Cheng Soon Ong on April 9, 2013
No forum yet.
