You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

Michał Gallus 0c39b97b4e [MKL-DNN] Add Fully Connected Op for inference only(#15226) ... * fuse mul and elementwise add to fc * Reimplement the FC forward operator * Fix FC MKLDNN integration by transposing weights * Add FC MKLDNN Pass test=develop * FC MKLDNN Pass: change memcpy to std::copy * Fix MKLDNN FC handling of mismatch input and weights dims * Lower tolerance for MKL-DNN in resnet50 test test=develop * Adjust FC to support MKLDNN Op placement test=develop * Adjust Placement Op to set use_mkldnn attribute for graph test=develop * MKLDNN FC: fix weights format so that gemm version is called test=develop * FC MKLDNN: Remove tolerance decrease from tester_helper * FC MKL-DNN: Refactor the code, change input reorder to weight reorder * MKL-DNN FC: Introduce operator caching test=develop * FC MKL-DNN: Fix the tensor type in ExpectedKernelType test=develop * FC MKL-DNN: fix style changes test=develop * FC MKL-DNN: fallback to native on non-supported dim sizes test=develop * FC MKLDNN: fix CMake paths test=develop * FC MKLDNN: Refine placement pass graph mkldnn attribute test=develop * Fix Transpiler error for fuse_conv_eltwise test=develop * Fix missing STL includes in files test=develop * FC MKL-DNN: Enable new output size computation Also, refine pass to comply with newest interface. test=develop * FC MKL-DNN: enable only when fc_mkldnn_pass is enabled * FC MKL-DNN: Allow Weights to use oi or io format * FC MKL-DNN: Adjust UT to work with correct dims test=develop * Enable MKL DEBUG for resnet50 analyzer test=develop * FC MKL-DNN: Improve Hashing function test=develop * FC MKL-DNN: Fix shape for fc weights in transpiler * FC MKL-DNN: Update input pointer in re-used fc primitive * Add log for not handling fc fuse for unsupported dims test=develop * FC MKL-DNN: Move transpose from pass to Op Kernel test=develop * FC MKL-DNN: Disable transpose in unit test test=develop * FC MKL-DNN: Remove fc_mkldnn_pass from default list * Correct Flag for fake data analyzer tests test=develop * FC MKL-DNN: Add comment about fc mkldnn pass disablement test=develop * FC MKL-DNN: Disable fc in int8 tests test=develop		6 years ago
..
CMakeLists.txt	Make separate folders for mkldnn codes	6 years ago
__init__.py	Make separate folders for mkldnn codes	6 years ago
mkldnn_op_test.py	Add Requantize OP (#15318)	6 years ago
test_activation_mkldnn_op.py	Add UTs to check whether primitives for activations and softmax already exist in backward	6 years ago
test_batch_norm_mkldnn_op.py	Make separate folders for mkldnn codes	6 years ago
test_concat_int8_mkldnn_op.py	Enable MKL-DNN INT8 Concat Kernel. (#16156)	6 years ago
test_concat_mkldnn_op.py	Make separate folders for mkldnn codes	6 years ago
test_conv2d_int8_mkldnn_op.py	Fix the bug of test_conv2d_int8_mkldnn case which raised by improper parameter passing (#17058)	6 years ago
test_conv2d_mkldnn_op.py	Enable the convolution/relu6(bounded_relu) fusion for FP32 on Intel platform. (#17130)	6 years ago
test_conv2d_transpose_mkldnn_op.py	MKLDNN: Add UT for conv_transpose_mkldnn op. (#16030)	6 years ago
test_conv3d_mkldnn_op.py	Make separate folders for mkldnn codes	6 years ago
test_dequantize_mkldnn_op.py	Make separate folders for mkldnn codes	6 years ago
test_elementwise_add_mkldnn_op.py	Make separate folders for mkldnn codes	6 years ago
test_elementwise_mul_mkldnn_op.py	remove unnecessary new line	6 years ago
test_fc_mkldnn_op.py	[MKL-DNN] Add Fully Connected Op for inference only(#15226)	6 years ago
test_gaussian_random_mkldnn_op.py	Make separate folders for mkldnn codes	6 years ago
test_lrn_mkldnn_op.py	Make separate folders for mkldnn codes	6 years ago
test_pool2d_int8_mkldnn_op.py	Make separate folders for mkldnn codes	6 years ago
test_pool2d_mkldnn_op.py	Add test for ceil mode	6 years ago
test_quantize_mkldnn_op.py	Make separate folders for mkldnn codes	6 years ago
test_requantize_mkldnn_op.py	Add Requantize OP (#15318)	6 years ago
test_softmax_mkldnn_op.py	Add UTs to check whether primitives for activations and softmax already exist in backward	6 years ago
test_sum_mkldnn_op.py	Make separate folders for mkldnn codes	6 years ago
test_transpose_int8_mkldnn_op.py	Enable INT8 transpose kernel for MobileNet-SSD improvement. (#16159)	6 years ago
test_transpose_mkldnn_op.py	Make separate folders for mkldnn codes	6 years ago