5 Commits

Author	SHA1	Message	Date
Junjie Bai	c1f974aa9f	Deprecate CNNModelHelper in python/crf.py ... Reviewed By: harouwu Differential Revision: D5241631 fbshipit-source-id: 3dc448355bc2a766ae9eda1dc579e501743b35cf	2017-06-14 08:49:27 -07:00
Ahmed Aly	58bc830660	Integrate CRF in DeepText + New caffe2 operator for viterbi decode ... Summary: Inegration of the CRF Layer in DeepText wordmodels + Implementing the viterbi decode operator in C++ instead of python so that the CRF models can be deployed in production. Differential Revision: D4912196 fbshipit-source-id: 64f499a1bd47e811e7a96dde839904dcd05cacb3	2017-05-01 20:39:41 -07:00
Aapo Kyrola	e13e9c1302	cuDNN version of TransposeOp ... Summary: Uses the cudnnTransformTensor function. It works by shuffling the strides according to the transpose axis. Significant speedup over current GPU version . + moves the transpose test under utility_ops, because hypothesis_test is too big Reviewed By: jamesr66a Differential Revision: D4810993 fbshipit-source-id: 82577c4ced1389e70bd5992820ae4d8297a3817f	2017-04-03 13:33:10 -07:00
Aaron Markham	58f7f2b441	doxygen python block added ... Summary: Closes https://github.com/caffe2/caffe2/pull/226 Differential Revision: D4793550 Pulled By: JoelMarcey fbshipit-source-id: cc33e58186304fa8dcac2ee9115dcc271d785b1e	2017-03-29 06:46:16 -07:00
Ahmed Aly	99bfd36a04	CRF layer in caffe2 ... Summary: This is implementation of a CRF layer in caffe2 according to this paper: https://arxiv.org/abs/1603.01360 Currently this implementation works only for batch_size = 1 Reference implementations: - Tensorflow: 63a21e0540/tensorflow/contrib/crf/python/ops/crf.py - Theano: https://github.com/glample/tagger/blob/master/model.py#L286 Differential Revision: D4644004 fbshipit-source-id: bf0801fd8562d11dca3fefe371c3d85e1dd69ccc	2017-03-23 22:02:02 -07:00