Commit Graph

423 Commits

Author SHA1 Message Date
Brandon Amos e8344fbe34 Change lfw interface. 2016-01-12 14:32:54 -05:00
Brandon Amos 6409661f5f Remove unused fbnn dependency. 2016-01-12 14:32:54 -05:00
Brandon Amos d4a5e342b9 Add blank line. 2016-01-12 14:32:54 -05:00
Brandon Amos 12612b098a Add opencv-dlib-torch.Dockerfile 2016-01-12 13:43:09 -05:00
Brandon Amos 8e29377952 Tests: Add more debug output for failed tests. 2016-01-12 13:31:00 -05:00
Brandon Amos a4dd1c74ee API Tests: Remove image norms. 2016-01-12 13:26:24 -05:00
Brandon Amos 338a0e43fd Tests: Disable rgb check. 2016-01-12 11:54:36 -05:00
Brandon Amos 4477b5e0cf NN Tests: Use workDir for aligned images. 2016-01-11 17:50:31 -05:00
Brandon Amos f42eceb452 Fix pep257 warnings. 2016-01-11 17:42:20 -05:00
Brandon Amos 17e8dc5f2b Tests: Use tmp directory when writing to disk. 2016-01-11 17:36:54 -05:00
Brandon Amos b84d57a6df Add checks for 'None' to resolve #25. 2016-01-11 17:24:52 -05:00
Brandon Amos bddc2538ed Add two nn4.small definitions. 2016-01-11 17:01:42 -05:00
Brandon Amos 0fbb283789 lfw-subset: Wget: Use -nv. 2016-01-11 16:59:56 -05:00
Brandon Amos 0cb17becc7 Travis: Wget: Use -nv. 2016-01-11 16:58:27 -05:00
Brandon Amos 49aa43ece3 Travis: Source torch-active so 'th' is on the path for tests. 2016-01-11 16:55:50 -05:00
Brandon Amos 55928e9f95 Tests: Fix flake8 warnings. 2016-01-11 16:55:49 -05:00
Brandon Amos aef46e7bab Dockerfile: Use ./luarocks since sourcing in a Dockerfile doesn't work. 2016-01-11 16:48:08 -05:00
Brandon Amos 0479d0e345 Finish tensor size checks for #36. 2016-01-11 16:44:50 -05:00
Brandon Amos d0b40686a2 Training: OpenFaceOptim: Correct Tensor type. 2016-01-11 16:44:32 -05:00
Brandon Amos 5f78673b7d Move imgDim to models. 2016-01-11 16:38:24 -05:00
Brandon Amos 27f71cdf5d Dockerfile: Source torch-active for luarocks. 2016-01-11 16:38:05 -05:00
Brandon Amos b7facaa8a7 get-models.sh: Correct note about network traffic. 2016-01-11 16:23:05 -05:00
Brandon Amos 5634a4f563 Set executable bit on run-tests.sh. 2016-01-11 16:19:37 -05:00
Brandon Amos c8bc687983 get-models: wget: Use -nv. 2016-01-11 16:19:07 -05:00
Brandon Amos 8e81c62e3c Tests: Add neural network training tests for #13. 2016-01-11 16:17:36 -05:00
Brandon Amos c5b0accd4d Training: Add conditionals for cuda portions. 2016-01-11 16:17:36 -05:00
Brandon Amos 15cc5fef00 Training: Add CPU execution for tests. 2016-01-11 16:17:36 -05:00
Brandon Amos ff06eff893 Docker: Move Python dependencies to Ubuntu package binaries. 2016-01-11 16:12:45 -05:00
Brandon Amos 43751a25c1 Add download-lfw-subset script. 2016-01-11 12:44:42 -05:00
Brandon Amos c69bb8434e Fix comments at the top of tests. 2016-01-11 12:41:23 -05:00
Brandon Amos a7b10d483c Add batch-represent test for #13. 2016-01-11 12:41:03 -05:00
Brandon Amos d48957bcdf Tests: Fix falke8 errors. 2016-01-11 12:29:07 -05:00
Brandon Amos 343389f936 Dockerfile: Remove pip install numpy 2016-01-11 12:23:49 -05:00
Brandon Amos 9ed7a42c85 Move tests to separate directory. 2016-01-11 12:13:14 -05:00
Brandon Amos 3ba7574e4d Add test for SVM classifier training. 2016-01-11 12:00:22 -05:00
Brandon Amos 79bd9ac1e7 Dockerfile: Install nose from apt-get. 2016-01-11 11:20:44 -05:00
Brandon Amos f11b9df9fa Requirements: Add ranges. 2016-01-11 11:20:44 -05:00
Brandon Amos b4b0b60e7b Code Citation: Add @melgor. 2016-01-11 11:03:11 -05:00
Brandon Amos 1de080d65b Web Demo: Use outer eyes and nose. 2016-01-11 10:31:38 -05:00
Brandon Amos 2a3f0efed2 Fix luacheck warning. 2016-01-11 08:47:34 -05:00
Brandon Amos ce0fe8e4a8 batch-represent: Add cache option. 2016-01-11 08:25:04 -05:00
Brandon Amos 46251db1e2 lfw: Output accuracy. 2016-01-11 08:11:37 -05:00
Brandon Amos 6a5d95d451 Fix luacheck warning in sanitize. 2016-01-11 07:48:01 -05:00
Brandon Amos 8155840989 Training: Use e-lab's torch-toolbox sanitize. 2016-01-09 17:17:30 -05:00
Brandon Amos 6029baf48e Attempt to shorten Docker build with pre-built Python libs. 2016-01-08 14:27:38 -05:00
Brandon Amos 697fac07c1 Training: Output the number of model parameters. 2016-01-08 11:18:44 -05:00
Brandon Amos 2b249d02e6 DNN Models: Add parameters as comment and use opt.embSize 2016-01-08 11:18:30 -05:00
Brandon Amos 1bac754aca nn4 def: Don't validate shape by default. 2016-01-08 11:00:17 -05:00
Brandon Amos 22cf225923 Training: By default use an epoch size of 500. 2016-01-08 11:00:17 -05:00
Brandon Amos d7ae2a3885 Docs: Fix typo. 2016-01-08 10:20:45 -05:00