From 032cce9bd3d691c3f7e481f1c0015a5f2aa4b4f6 Mon Sep 17 00:00:00 2001 From: Michalis Spyrou Date: Thu, 16 May 2019 17:40:23 +0100 Subject: COMPMID-2218: 19.05 Release notes Change-Id: I481aa18e340ff08babb6bbcaa3e66fcb99156f2a Signed-off-by: Michalis Spyrou --- docs/00_introduction.dox | 27 +++++++++++++++++++++++++++ 1 file changed, 27 insertions(+) diff --git a/docs/00_introduction.dox b/docs/00_introduction.dox index d4ad358f70..cbfd456689 100644 --- a/docs/00_introduction.dox +++ b/docs/00_introduction.dox @@ -237,6 +237,8 @@ If there is more than one release in a month then an extra sequential number is @subsection S2_2_changelog Changelog v19.05 Public major release + - Various bug fixes. + - Various optimisations. - New Neon kernels / functions: - @ref NEBatchToSpaceLayerKernel / @ref NEBatchToSpaceLayer - @ref NEComplexPixelWiseMultiplicationKernel / @ref NEComplexPixelWiseMultiplication @@ -276,6 +278,31 @@ v19.05 Public major release - @ref CLDepthConcatenateLayer - @ref CLGEMMInterleave4x4 - @ref CLGEMMTranspose1xW + - Support different quantization info in CLConcatLayer. + - Add checks on different input/output quantization info were not supported. + - Tensors have different quantization information. + - Add FP16 support checks. + - Fix output quantization CLDeptwiseConv3x3 when activation is fused. + - New graph examples: + - graph_convolution + - graph_fully_connected + - graph_depthwise_convolution + - Deepspeech v0.4.1 + - Add support for QASYMM8 in NEArithmeticSubtractionKernel. + - Add support for QASYMM8 in NEPixelWiseMultiplicationKernel. + - Add support for QASYMM8 NEDeconvolution. + - Add support for DequantizationLayer for NEON/CL. + - Add support for dilation in CLDepthwiseConvolution. + - Fuse offset contribution with the output stage when we use NEGEMMLowpMatrixMultiplyCore. + - Optimize CLDeconvolution. + - Add StackLayer to the graph API. + - Add support for "reflect" padding mode in NEPad. + - Winograd 7x7 NHWC on OpenCL. + - Rework CL ML layers to run exclusively on CL. + - Support different quantization info in PoolingLayer. + - Implement and test import memory interfaces. + - Added new tests and removed old ones. + - Various clang-tidy fixes. v19.02 Public major release - Various bug fixes. -- cgit v1.2.1