Skip to content

Release 21.05
Compare
Choose a tag to compare
@nikraj01 nikraj01 released this 20 May 16:35
v21.05
42d0f1f

New Features

  • CAST operator support on HAL 1.2 and HAL 1.3.
  • REDUCE_SUM operator support on HAL 1.2 and HAL 1.3.
  • REDUCE_MIN operator support on HAL 1.2 and HAL 1.3.
  • REDUCE_MAX operator support on HAL 1.2 and HAL 1.3.
  • Non-const weights support added on FULLY_CONNECTED layer.

Bug Fixes

  • Fix added for dump files to handle situations where a shape has no dimensions or unspecified dimensions.
  • Fix added to avoid driver abort when tests use invalid filter shape.
  • Improved performance on SqueezeNet v1.1.

Other Changes

  • Removed cross-wiring in DepthwiseConvolution2d. The permutation of the full tensor info is now performed in armnnUtils::Permuted.
  • Removed data layout from dump files.
Assets 7
Loading