jgong5 329d901a91 Fold AffineChannel to Conv, the same way as BN (for Detectron models) (#10293) ... Summary: AffineChannel is being used by public Detectron models, e.g. Mask-RCNN and Faster-RCNN. This PR folds this op into convolution the same way as BN to speed up inference. Pull Request resolved: https://github.com/pytorch/pytorch/pull/10293 Differential Revision: D9276789 Pulled By: yinghai fbshipit-source-id: fbf6dd2c1be05f5713f760752e7245b1320a122b		2018-08-13 22:43:37 -07:00
..
concat_split_op_test.py	Fix fbcode compatibility (#7939)	2018-05-30 13:35:46 -04:00
conv_op_test.py	Enable Conv fusion optimizations in optimizeForIdeep (#9255)	2018-07-16 21:28:50 -07:00
convfusion_op_test.py	Fold AffineChannel to Conv, the same way as BN (for Detectron models) (#10293)	2018-08-13 22:43:37 -07:00
copy_op_test.py	Add fallback to TensorCPU if there are unsupported types for IDEEP Tensor (#9667)	2018-07-23 13:54:57 -07:00
dropout_op_test.py
elementwise_sum_op_test.py
fc_op_test.py	Fix fbcode compatibility (#7939)	2018-05-30 13:35:46 -04:00
LRN_op_test.py
pool_op_test.py
relu_op_test.py
softmax_op_test.py
spatial_bn_op_test.py	Normalize IDEEP spatial bn op test (#9276)	2018-07-09 11:55:41 -07:00
squeeze_op_test.py	[ideep] Add IDEEP Squeeze op (#8227)	2018-06-06 21:58:51 -07:00
test_ideep_net.py
transform_ideep_net.py