diff options
Diffstat (limited to 'docs/00_introduction.dox')
| -rw-r--r-- | docs/00_introduction.dox | 10 |
1 files changed, 7 insertions, 3 deletions
diff --git a/docs/00_introduction.dox b/docs/00_introduction.dox index 92bb1c4cbb..df71c90f3f 100644 --- a/docs/00_introduction.dox +++ b/docs/00_introduction.dox @@ -240,6 +240,13 @@ If there is more than one release in a month then an extra sequential number is v20.08 Public major release - Various bug fixes. - Various optimisations. + - Added new data type QASYMM8_SIGNED support for: + - @ref CLArgMinMaxLayer + - @ref CLArgMinMaxLayerKernel + - New graph example: + - graph_yolov3_output_detector + - Removed padding from: + - @ref NEPixelWiseMultiplicationKernel - Deprecated functions / interfaces: - Non-descriptor based interfaces for @ref NEThreshold, @ref CLThreshold - In @ref NESoftmaxLayer, @ref NELogSoftmaxLayer, @ref CLSoftmaxLayer, @ref CLLogSoftmaxLayer and @ref GCSoftmaxLayer : @@ -247,9 +254,6 @@ v20.08 Public major release The default "axis" (now "reduce_end_axis") value for @ref NESoftmaxLayer and @ref NELogSoftmaxLayer is changed from -1 to 0. The default "axis" (now "reduce_end_axis") value for @ref CLSoftmaxLayer, @ref CLLogSoftmaxLayer and @ref GCSoftmaxLayer is changed from 1 to 0. - The support for quantized data types has been removed from @ref CLLogSoftmaxLayer due to implementation complexity. - - Added new data type QASYMM8_SIGNED support for: - - @ref CLArgMinMaxLayer - - @ref CLArgMinMaxLayerKernel v20.05 Public major release - Various bug fixes. |