| commit | 0eda7955bdb8da11330a6e4e2b4779dbf6aa1e9a | [log] [tgz] |
|---|---|---|
| author | James Cross <jcross@fb.com> | Mon Jul 24 14:49:50 2017 -0700 |
| committer | Facebook Github Bot <facebook-github-bot@users.noreply.github.com> | Mon Jul 24 14:53:11 2017 -0700 |
| tree | 7ef323009a6dc7d3121d957fc3c87dbee7552e2b | |
| parent | 0deee2194f12cbae5877e412344c13683f513d54 [diff] |
use internal cell for DropoutCell output prep methods Summary: In order to get dimensions right, correctly identify gradients, etc., DropoutCell should call the _prepare_output and _prepare_output_sequence methods of its internal cell for its own such methods. This bug was identified by NVIDIA intern Syed Tousif Ahmed. Reviewed By: akyrola Differential Revision: D5483082 fbshipit-source-id: f6df5b4a0502ed0771056638aab219fb5cc7d964
Caffe2 is a lightweight, modular, and scalable deep learning framework. Building on the original Caffe, Caffe2 is designed with expression, speed, and modularity in mind.
Caffe2 research award competition request for proposals
Please use Github issues (https://github.com/caffe2/caffe2/issues) to ask questions, report bugs, and request new features.
Please participate in our survey (https://www.surveymonkey.com/r/caffe2). We will send you information about new releases and special developer events/webinars.
Caffe2 is released under the BSD 2-Clause license.