Gitiles
Code Review
Sign In
review.mlplatform.org
/
ml
/
ComputeLibrary
/
215b4ea6c9dee480a22070d5873b0b8cb52531a0
« Previous
78c0090
COMPMID-754: Add validation to kernels.
by Georgios Pinitas
· 7 years ago
e4904c7
COMPMID-765: Cleaned up FIXMEs
by Anthony Barbier
· 7 years ago
7ef9018
COMPMID-765: Add Winograd Convolution Hint for NEON Convolution
by Georgios Pinitas
· 7 years ago
1a03d76
COMPMID-765: Fix windows in DirectConvLayer and DepthwiseConvLayer
by Georgios Pinitas
· 7 years ago
aad9f2c
COMPMID-754: Add CLPermute validation method
by Isabella Gottardi
· 7 years ago
2d0ce77
COMPMID-765: Updated changelog for v18.02
by Anthony Barbier
· 7 years ago
328891c
COMPMID-933: Replaced StaticWindow with RectangleWindow
by Anthony Barbier
· 7 years ago
995f552
COMPMID-864 Window::collapse_if_possible() is misused in several CL kernels
by Michalis Spyrou
· 7 years ago
8913d8d
COMPMID-915: Create ResNet50 example
by Alex Gilday
· 7 years ago
1599787
COMPMID-934: Asymmetric padding support.
by Georgios Pinitas
· 7 years ago
933fe86
COMPMID-927: Adding support for FP16 in CLDepthwiseConvolutionLayer3x3
by Michele Di Giorgio
· 7 years ago
4406fd6
APPBROWSER-391: Fix GLES COMPUTE alignment issues
by Frank Lei
· 7 years ago
898d399
COMPMID-945: Fix GEMM CL FP32 mismatch
by Michele Di Giorgio
· 7 years ago
9414f64
COMPMID-582: Add validation to channel_extract kernels.
by Ioan-Cristian Szabo
· 7 years ago
6acc6ad
COMPMID-846: Create a ConvolutionLayer for NEON
by Isabella Gottardi
· 7 years ago
51b074a
COMPMID-764 Removed reciprocal QS tests
by Anthony Barbier
· 7 years ago
cac4a2e
COMPMID-765 - Fix get_convolution_method in order to return the correct method.
by Isabella Gottardi
· 7 years ago
9be0c5a
COMPMID-936: Convolution failure in NEON Convolution Layer.
by Georgios Pinitas
· 7 years ago
287b570
COMPMID-853 Use tile 2 for CL depthwise convolution QASYM8
by Giorgio Arena
· 7 years ago
d267b05
COMPMID-784: Fixed SAME paddding in WinogradLayer
by Pablo Tello
· 7 years ago
1fbb812
Revert "COMPMID-582: Add validation to channel_extract kernels."
by Anthony Barbier
· 7 years ago
562fe0f
COMPMID-578: Faster common keypoint validation routine for FAST and Harris corners
by Abe Mbise
· 7 years ago
6a3daf1
COMPMID-942: Created 'embed_only' build target for ArmNN
by Anthony Barbier
· 7 years ago
931b489
Revert "COMPMID-915: Create ResNet50 example"
by Anthony Barbier
· 7 years ago
140fdc7
COMPMID-913: Fix preprocessing step for TF models.
by Georgios Pinitas
· 7 years ago
72f39be
COMPMID-939 Fix mismatches and finalize CLSoftmaxLayer optimization
by Giorgio Arena
· 7 years ago
7bfb199
COMPMID-915: Create ResNet50 example
by Alex Gilday
· 7 years ago
dde9ec9
COMPMID-909: Enabling in-place computation for batchnormalization and activation at graph level
by Michele Di Giorgio
· 7 years ago
e3fba0a
COMPMID-925: Enabling OpenCL tuner in the graph examples
by Michele Di Giorgio
· 7 years ago
f07d28d
COMPMID-845: Create a ConvolutionLayer for CL
by Isabella Gottardi
· 7 years ago
21f67d6
COMPMID-934: Return an error in Validate when we don't support asymmetric padding
by Anthony Barbier
· 7 years ago
7567f5f
COMPMID-828 - Add support for pool widths 4, 5 & 6 and for non square data sizes - Part 2 (NEON)
by Isabella Gottardi
· 7 years ago
3cfd237
COMPMID-938: OCLgrind: Mismatches in depthwise convolution on Bifrost
by Georgios Pinitas
· 7 years ago
f6c572c
COMPMID-784: Productise Winograd.
by Pablo Tello
· 7 years ago
91d20d9
COMPMID-582: Add validation to channel_extract kernels.
by Ioan-Cristian Szabo
· 7 years ago
19835e5
COMPMID-882 - Optimizing GEMMLowp on OpenCL reshaping matrices
by Gian Marco
· 7 years ago
6fa009e
COMPMID-930 Disable warning about implicit-fallthrough in new versions of GCC
by Anthony Barbier
· 7 years ago
4402cb9
COMPMID-905 Optimize CLSoftmaxLayer for QASYMM8
by Giorgio Arena
· 7 years ago
a086a0a
COMPMID-765 Move direct convolution output stage to the right file
by Giorgio Arena
· 7 years ago
de5a1cc
COMPMID-856: CL Depthwise Convolution QASYMM8 support
by Georgios Pinitas
· 7 years ago
f36ac35
COMPMID-931 Bugfix for NumPyBinLoader with SubTensor output. (#345)
by hakanardo
· 7 years ago
57c033b
COMPMID-906: Use fused activation in NEON Batch normalization
by Georgios Pinitas
· 7 years ago
02ee429
COMPMID-765: Fix CPPPermute error when permuting the strides.
by Georgios Pinitas
· 7 years ago
82833b8
COMPMID-765 : NEON Wrapper initial traits and overloads
by Georgios Pinitas
· 7 years ago
ba8fcb0
COMPMID-765: Remove wrong shape in LargeShapesBroadcast
by Michele Di Giorgio
· 7 years ago
056b5d9
COMPMID-765: Switch 1x1 DeconvolutionLayer to use the ConvolutionLayer
by Georgios Pinitas
· 7 years ago
69af6cf
COMPMID-765: Sanitize permutation vector for Permute.
by Georgios Pinitas
· 7 years ago
b99f00d
COMPMID-905 Asymm functions support for all vec sizes
by Giorgio Arena
· 7 years ago
77e4a2d
COMPMID-850: Increase tolerance while issue is being investigated
by Anthony Barbier
· 7 years ago
36e0075
COMPMID-589: Refactor HOGDescriptor validation test
by John Richardson
· 7 years ago
5ca7409
COMPMID-765 - Used GEMM-based convolution in VGG16
by Gian Marco
· 7 years ago
284cfe2
COMPMID-903: Implements NEPermute for NHWC conversions
by Georgios Pinitas
· 7 years ago
f299758
COMPMID-918: AArch32 SGEMM generic kernel fix.
by David Mansell
· 7 years ago
59716fa
COMPMID-765: Fix CLDeconvolutionLayerUpsampleKernel access window.
by Georgios Pinitas
· 7 years ago
7df3541
COMPMID-792: Update doctrings of CL kernels supporting broadcast operations
by Michele Di Giorgio
· 7 years ago
ced7a8d
COMPMID-875: Deconvolution 4x4 not working
by Georgios Pinitas
· 7 years ago
1d6d211
COMPMID-884: Valgrind: NEDirectConvolutionLayerKernel invalid read
by Georgios Pinitas
· 7 years ago
a527e8c
COMPMID-828 - Add support for pool widths 4, 5 & 6 and for non square data sizes - Part 2 (CL)
by Isabella Gottardi
· 7 years ago
1aede36
COMPMID-765 - Extended GEMM benchmark
by Gian Marco
· 7 years ago
1167487
COMPMID-897 Merge batch normalization with bounded relu
by Giorgio Arena
· 7 years ago
4e1e7dc
COMPMID-892: OCLGrind failures on both validation and benchmark
by Georgios Pinitas
· 7 years ago
6232d04
COMPMID-907 Optimizing FixedPoint calculation in the output stage of GEMMLowp
by Giorgio Arena
· 7 years ago
c67bb3d
COMPMID-878: Integrate AArch32 SGEMM Arm Cortex-A55r1 kernel from RSH
by Michele Di Giorgio
· 7 years ago
f1a89fe
COMPMID-877: Integrate AArch32 SGEMM Arm Cortex-A53 kernel from RSH
by Michele Di Giorgio
· 7 years ago
240beb7
COMPMID-765: Fixes DepthwiseConvolution weights shape
by Georgios Pinitas
· 7 years ago
1d77263
COMPMID-765: Fix inclusion error.
by Georgios Pinitas
· 7 years ago
4074c99
COMPMID-873: Integrate RSH NEON Depthwise Convolution routine
by Georgios Pinitas
· 7 years ago
c5694af
COMPMID-879: Invalid convolution data type in validation.
by Georgios Pinitas
· 7 years ago
cc327b2
COMPMID-876: Integrate RSH native GEMM kernel.
by Georgios Pinitas
· 7 years ago
25a340f
COMPMID-578: Implement FAST corners for CL/NEON
by Abe Mbise
· 7 years ago
40df1e9
COMPMID-887 Valgrind invalid read in print_measurements
by Michalis Spyrou
· 7 years ago
f75ab3f
COMPMID-888 Valgrind invalid read in NEGEMVAArch64Kernel
by Michalis Spyrou
· 7 years ago
5ae9b69
COMPMID-885 Valgrind NEConvolutionSquare::configure relies on uninitialised values
by Michalis Spyrou
· 7 years ago
54f18c4
COMPMID-901 - Optimizing CLCol2ImKernel
by Gian Marco
· 7 years ago
e9146ed
COMPMID-879: Investigate CL mismatches in Convolution S16
by Georgios Pinitas
· 7 years ago
6e464c3
COMPMID-828 - Add support for non square pool size - Part1
by Isabella Gottardi
· 7 years ago
3364c4c
COMPMID-893: Fix segfault in graph_squeezenet_v1_1
by Georgios Pinitas
· 7 years ago
c799ed8
COMPMID-895 - Optimizing CLDepthwiseConvolution3x3Kernel
by Gian Marco
· 7 years ago
604afc0
COMPMID-894: Segfault: neon_cnn on S5 neo
by Georgios Pinitas
· 7 years ago
562deff
COMPMID-765 - Added LWS hint in CLIm2Col
by Gian Marco
· 7 years ago
101de50
COMPMID-896: Replace legacy 4x4 u8 GEMM kernel with safe version.
by David Mansell
· 7 years ago
679463a
COMPMID-784: Added support for PADDING = SAME in Winograd layer.
by Pablo Tello
· 7 years ago
85e6f51
COMPMID-891 - Use OpenCL timer in CLTuner
by Gian Marco
· 7 years ago
76faef8
COMPMID-855 - Optimizing im2col on OpenCL (DCHW)
by Gian Marco
· 7 years ago
b28f329
COMPMID-754: Add validation method to CLPermute kernel
by Michele Di Giorgio
· 7 years ago
2d40555
COMPMID-765 - Used GEMM instead of Direct into the GoogleNet graph example
by Gian Marco
· 7 years ago
bc4484a
COMPMID-889 - Implement Squeezenet 1.1 as a graph example
by Isabella Gottardi
· 7 years ago
53d1227
COMPMID-874: Improve default number of threads choice in the Scheduler
by Georgios Pinitas
· 7 years ago
b7e3028
COMPMID-890: Valgrind: NEON Convolution Layer validation fails
by Isabella Gottardi
· 7 years ago
f525eab
COMPMID-871: Remove vst4q/vld4q from NEActivationLayer.
by Georgios Pinitas
· 7 years ago
6259e5f
COMPMID-787: Add CL support for broadcast multiply
by Michele Di Giorgio
· 7 years ago
19d0547
COMPMID-765: Fix direct convolution output stage.
by Georgios Pinitas
· 7 years ago
f6169d8
COMPMID-765: Fixed clangtidy warnings.
by Pablo Tello
· 7 years ago
456e479
COMPMID-765: Fixed CPU detection code to read larger buffer (was failing on Arm Cortex-A55 FPGA with 8 CPUs with lots of flags).
by Pablo Tello
· 7 years ago
52140b4
COMPMID-784: Winograd tramsforms refactoring
by Pablo Tello
· 7 years ago
054a714
COMPMID-765 Small fixes to MobileNet dwc dataset
by Giorgio Arena
· 7 years ago
33ff9ef
APPBROWSER-400: Implement the tensorshift kernel for fixing DC's alignment issue on OpenGL ES
by Xinghang Zhou
· 7 years ago
1c0d0ff
COMPMID-832: Decrease validation coverage of QS8/QS16
by Anthony Barbier
· 7 years ago
cdd1e85
APPBROWSER-394: GLES fails to compile Dropout kernel on S5
by steli01
· 7 years ago
18d352a
COMPMID-765: Added tolerance of 1 for CL Convolution S16 while the issue is investigated
by Anthony Barbier
· 7 years ago
Next »