Gitiles
Code Review
Sign In
review.mlplatform.org
/
ml
/
ComputeLibrary
/
69e44dc073bae7f7f54923d306a52d809b1334d5
69e44dc
COMPMID-415: New framework - datasets [2/5]
by Moritz Pflanzer
· 7 years ago
9247c92
COMPMID-428: Port NESoftmaxLayer to 16-bit fixed point.
by Georgios Pinitas
· 7 years ago
0979675
COMPMID-429: Port CLSoftmaxLayer to QS16.
by Georgios Pinitas
· 7 years ago
dcdc85e
COMPMID-421: Added F16 support in FC Layer.
by Pablo Tello
· 7 years ago
fc95ed2
COMPMID-415: New framework - base framework [1/5]
by Moritz Pflanzer
· 7 years ago
7d323a6
COMPMID-440, COMPMID-441 - Port CLConvolutionLayer and CLFullyConnectedLayer to support 16 bit fixed point
by Gian Marco Iodice
· 7 years ago
ab0a77e
COMPMID-409: Add support for QS8 and QS16 CLPixelWiseMultiplication.
by Michele Di Giorgio
· 7 years ago
ccc65d4
COMPMID-427: Port NEActivationLayer in 16bit fixed point.
by Georgios Pinitas
· 7 years ago
0745a98
COMPMID-417: Fix assert in GEMMTranspose
by Moritz Pflanzer
· 7 years ago
b158fba
COMPMID-417: Fix output access window in ChannelExtract Kernels.
by Georgios Pinitas
· 7 years ago
9502f31
COMPMID-417: Increase NEON QS16 tolerance for reciprocal
by Moritz Pflanzer
· 7 years ago
331fc74
COMPMID-421: Fixed compiler error for arm-v8.2-a.
by Pablo Tello
· 7 years ago
565e176
COMPMID-417 Updating 3rd party folder with the new x86_64 libs (The correct ones this time).
by Anthony Barbier
· 7 years ago
d368df3
COMPMID-417: Auto initialize for SoftmaxLayer NEON/CL.
by Georgios Pinitas
· 7 years ago
21efeb4
COMPMID-417: DepthConvert NEON for QS8/QS16.
by Georgios Pinitas
· 7 years ago
368da83
COMPMID-420, COMPMID-414 - Port CLConvolutionLayer and CLFullyConnectedLayer to use 8 bit fixed point
by Gian Marco Iodice
· 7 years ago
adffa30
COMPMID-417 Updating 3rd party folder with the new x86_64 libs
by Anthony Barbier
· 7 years ago
1b31afc
COMPMID-417: Fix Dimensions::collapse
by Moritz Pflanzer
· 7 years ago
b93f5de
COMPMID-417 - Fixed bug in gemm_interleave_16bit and gemm_interleave_32_bit due to the non non representable numbers in half and float
by Gian Marco Iodice
· 7 years ago
2bbd964
COMPMID-436, COMPMID-437 - Port NEConvolutionLayer & NEFullyConnectedLayer to support 16 bit fixed point
by Gian Marco Iodice
· 7 years ago
8a38369
COMPMID-434 - Port CLGEMM to support 16 bit fixed point
by Gian Marco Iodice
· 7 years ago
bdb6b0b
COMPMID-433 - Port NEGEMM to support 16 bit fixed point
by Gian Marco Iodice
· 7 years ago
ac69aa1
COMPMID-418 Add check and fix comments after preprocessor conditions
by Anthony Barbier
· 7 years ago
05da6dd
COMPMID-417: Remove val_to_string
by Moritz Pflanzer
· 7 years ago
221f381
COMPMID-421: Fixed FP16 support in Neon GEMM.
by Pablo Tello
· 7 years ago
6410fb2
COMPMID-417: Revert invsqrt validation implementation.
by Georgios Pinitas
· 7 years ago
f0dea70
COMPMID-417: Auto configuration for Add/Sub/Mul Neon/CL.
by Georgios Pinitas
· 7 years ago
1dad50e
COMPMID-417: Auto initialization for PoolingLayer for NEON/CL.
by Georgios Pinitas
· 7 years ago
b76346d
COMPMID-417: Autoconfigure for BatchNormalization CL/NEON.
by Georgios Pinitas
· 7 years ago
d8539b2
COMPMID-417: Fix neon_cnn example.
by Georgios Pinitas
· 7 years ago
09004ca
COMPMID-417: Add autoconfigure in NormalizationLayer CL/NEON.
by Georgios Pinitas
· 7 years ago
d7e8281
COMPMID-408 Create OpenCL complex math functions for 8 bit fixed point arithmetic.
by Michalis Spyrou
· 7 years ago
13edbff
COMPMID-432 - Extended Convolution Layer to support rectangular kernels
by Gian Marco Iodice
· 7 years ago
238cfc0
COMPMID-417: Fix broken build after rebase gone wrong
by Moritz Pflanzer
· 7 years ago
3a3066b
COMPMID-411 - Port CLGEMM to support 8 bit fixed point
by Gian Marco Iodice
· 7 years ago
94450f1
COMPMID-417: Use a common create_tensor function
by Moritz Pflanzer
· 7 years ago
d4f8c27
COMPMID-417: Include std::vector where needed.
by Georgios Pinitas
· 7 years ago
997aba2
COMPMID-421: Fixed a problem in Convolution Layer reference values for FP16.
by Pablo Tello
· 7 years ago
7b7858d
COMPMID-359: Implement NEON ROIPoolingLayer
by Georgios Pinitas
· 7 years ago
d0ae8b8
COMPMID-417: Extract common toolchain support file
by Moritz Pflanzer
· 7 years ago
5cb4c42
COMPMID-414 - Port CLConvolutionLayer to support 8 bit fixed point - CLWeightsReshapeKernel
by Gian Marco Iodice
· 7 years ago
0a8334c
COMPMID-400 Add support for 16 bit fixed point arithmetic.
by Michalis Spyrou
· 7 years ago
e5f8fd6
COMPMID-423: Port CLSoftmaxLayer to QS8
by Georgios Pinitas
· 7 years ago
443c8b9
COMPMID-417: Move ActivationLayer tests to boost
by Moritz Pflanzer
· 7 years ago
7a03575
COMPMID-424 Clean up validation tests for 2D spatial filter functions
by SiCong Li
· 7 years ago
4e28869
COMPMID-417 - Adding support for rectangular kernels
by Gian Marco Iodice
· 7 years ago
3b77e9d
COMPMID-378 - Implemented reference implementation and tests (NEON and CL) for Non Linear Filter
by Isabella Gottardi
· 7 years ago
3eb263e
COMPMID-424 Add validation tests for Gaussian5x5
by SiCong Li
· 7 years ago
0326eae
COMPMID-417: Check for nullptr in mismatching data types check.
by Georgios Pinitas
· 7 years ago
5a53664
COMPMID-424 Add tests for Gaussian3x3
by SiCong Li
· 7 years ago
d9afd9c
COMPMID-417: Remove dependency on CLScheduler from core
by Moritz Pflanzer
· 7 years ago
bacaf9a
COMPMID-424 Add CL validation tests for Box3x3
by SiCong Li
· 7 years ago
50f9fd7
COMPMID-378 NEON/CL Sobel 3x3 and 5x5 tests.
by Giorgio Arena
· 7 years ago
bee466b
COMPID-345 Add caffe_data_extractor.py script and the instructions
by steniu01
· 7 years ago
8af2dd6
COMPMID-403: Add 7x7 NEON Pooling support.
by Michele Di Giorgio
· 7 years ago
c6cb35a
COMPMID-345: Updated scons scripts to link computer_vision statically against libgcc, libstdc++ and computer_vision.
by Pablo Tello
· 7 years ago
ee12254
COMPMID-417: Fix negative overflowing in NESoftmaxLayer.
by Georgios Pinitas
· 7 years ago
659abc0
COMPMID-421: Added FP16 support in Convolutional layer (Neon)
by Pablo Tello
· 7 years ago
b30dcc5
COMPMID-345 - In-place computation for Activation Layer
by Gian Marco Iodice
· 7 years ago
9ea47f6
COMPMID-417: Always print seed
by Moritz Pflanzer
· 7 years ago
2509fba
COMPMID-417: Fix PaddingCalculator
by Moritz Pflanzer
· 7 years ago
383deec
COMPMID-345: Added support for arm8.2+FP16 in the the validation framework.
by Pablo Tello
· 7 years ago
fabb038
COMPMID-344 Fixed instructions to build Android examples
by Anthony Barbier
· 7 years ago
960b084
COMPMID-250 make BorderSize explicit and fix float value validation bug
by steniu01
· 7 years ago
79c6178
COMPMID-344 Update documentation for new build options
by Anthony Barbier
· 7 years ago
e2b999e
COMPMID-345: Update 3rdparty module
by Moritz Pflanzer
· 7 years ago
578ab61
COMPMID-414 - Port CLConvolutionLayer to support 8 bit fixed point - CLGEMMMatrixAccumulateBiasesKernel
by Gian Marco Iodice
· 7 years ago
ec8b45e
COMPMID-345 - Auto-inizialization for NECol2ImKernel and NEGEMMInterleave4x4Kernel
by Gian Marco Iodice
· 7 years ago
9f89bae
COMPMID-411 - Ported CLGEMMInterleave4x4Kernel and CLGEMMTranspose1xWKernel to support 8 bit fixed point
by Gian Marco Iodice
· 7 years ago
10c672c
COMPMID-399 Add MatrixMultiply to benchmark
by SiCong Li
· 7 years ago
84e3120
COMPMID-378 CLIntegralImage testing completed.
by Giorgio Arena
· 7 years ago
423d88f
COMPMID-250 handle single float comparision
by steniu01
· 7 years ago
4cbee6e
COMPMID-345: Scale input valid region in TransposeWindow.
by Georgios Pinitas
· 7 years ago
ce09314
COMPMID-403:Add support for 7x7 pooling on CL.
by Georgios Pinitas
· 7 years ago
4c2938e
COMPMID-315 Fix NEMinMaxLocation bug
by steniu01
· 7 years ago
fda4618
COMPMID-378 IntegralImage testing completed.
by Giorgio Arena
· 7 years ago
5b51229
COMPMID-250: Add PaddingCalculator class
by Moritz Pflanzer
· 7 years ago
9746fd8
COMPMID-250 handle validation results comparision correctly
by steniu01
· 7 years ago
f795986
COMPMID-378 NEMeanStdDev test completed.
by Giorgio Arena
· 7 years ago
7b06cde
COMPMID-345 - Fixed issue with non rectangular kernels in NEConvolutionLayer funcion
by Gian Marco Iodice
· 7 years ago
6ff3b19
COMPMID-344 Updated doxygen
by Anthony Barbier
· 7 years ago