Google Git
Sign in
android / platform / external / pytorch / e3d38fa933
commite3d38fa9334c9b38002bb5f3aebe670fb725cefb[log] [tgz]
authorMaxime Boucher <maxime@instagram.com>Mon Dec 19 20:45:38 2016 -0800
committerFacebook Github Bot <facebook-github-bot@users.noreply.github.com>Mon Dec 19 20:59:30 2016 -0800
tree56bd708a03706d4d87a06468768118cda62bb175
parentd4bbcab558263720658ade4e7b227c25a8f59f28 [diff]
Add rank loss options to mlp

Summary: This diff adds an option to use rank loss instead of cross entropy loss during training. This assumes that the data is loaded in batches which corresponds to sessions, which is something that was implemented for RNN training

Differential Revision: D4261923

fbshipit-source-id: e92a60cc9f53acc1585ac35d1fdb430c2ebbfa33
2 files changed
tree: 56bd708a03706d4d87a06468768118cda62bb175
  1. caffe/
  2. caffe2/
  3. docs/
  4. third_party/
  5. .Doxyfile
  6. .gitignore
  7. .gitmodules
  8. build.py
  9. build_android.py
  10. build_android_prepare.py
  11. LICENSE
  12. Makefile
  13. README.md
README.md

Caffe2

Caffe2 is a deep learning framework made with expression, speed, and modularity in mind. It is an experimental refactoring of Caffe, and allows a more flexible way to organize computation.

Read the installation instructions for installation details.

License and Citation

Caffe2 is released under the BSD 2-Clause license.