diff options
author | Chunseok Lee <chunseok.lee@samsung.com> | 2022-09-07 19:04:21 +0900 |
---|---|---|
committer | Chunseok Lee <chunseok.lee@samsung.com> | 2022-09-07 19:04:21 +0900 |
commit | c690d52bdd137ed6a17353aa7af35e8141ece77b (patch) | |
tree | dbb7dd99133132dfbffcb8c9e9af4f1ffc2f4808 /docs/release/1.21/release-note_1.21.0.md | |
parent | 3ad689f0803519e343c36d5700646e86059df961 (diff) | |
download | nnfw-tizen_7.0_hotfix.tar.gz nnfw-tizen_7.0_hotfix.tar.bz2 nnfw-tizen_7.0_hotfix.zip |
Imported Upstream version 1.21.0upstream/1.21.0tizen_7.0_m2_releaseaccepted/tizen/unified/20220912.170817accepted/tizen/unified/20220912.164738accepted/tizen/7.0/unified/hotfix/20221116.105341accepted/tizen/7.0/unified/20221110.060236tizen_7.0_hotfixtizen_7.0accepted/tizen_7.0_unified_hotfixaccepted/tizen_7.0_unified
Diffstat (limited to 'docs/release/1.21/release-note_1.21.0.md')
-rw-r--r-- | docs/release/1.21/release-note_1.21.0.md | 35 |
1 files changed, 35 insertions, 0 deletions
diff --git a/docs/release/1.21/release-note_1.21.0.md b/docs/release/1.21/release-note_1.21.0.md new file mode 100644 index 000000000..49bf074b6 --- /dev/null +++ b/docs/release/1.21/release-note_1.21.0.md @@ -0,0 +1,35 @@ +# Release Note 1.21.0 + +## ONE Compiler + +- Support unrolling of LSTM and RNN Ops in `one-import-onnx` tool +- Introduced new tools `one-infer`, `circle-operator`, `circle-interpreter` +- Introduced `Workflow`(WIP) in `one-cmds` +- New option `quant_config` in `one-quantize` +- New option `fake_quantize` in `one-quantize` +- More Ops supported: Densify +- More Ops for quantization: ReduceMax +- More Ops for mixed-precision quantization (MPQ): LeakyRelu, Neg, Relu6, Squeeze +- More Ops for `convert_nchw_to_nhwc` option: LogSoftmax, ReduceMax, SplitV, Softmax +- New optimization options in `one-optimize`: `replace_non_const_fc_with_bmm`, `resolve_customop_splitv`, `fold_densify` +- Improved reshape elimination in `convert_nchw_to_nhwc` option. +- Support fusion of Channel-wise Add + Relu with TConv +- Support negative axis in ArgMin/Max +- Show errors for unrecognized options in `one-optimize` +- Fix shape inference for `StridedSlice` +- Fix FuseBatchNormWithTConvPass to support TConv with bias +- Deprecate `--O1` option in `circle2circle` +- Support gcc-11 +- Support limited Float16 for kernels constants with dequantization to Float32 + +## ONE Runtime + +### Basic Multimodel nnpackage +- Runtime supports to run nnpackage with two models + +### Channel Wise Quantization on Conv2D and Depthwise Conv2D +- Conv2D and Depthwise Conv2D supports per-channel quantization of uint8 type. + +### Batch Execution with TRIX backend +- TRIX backend supports batch execution which run in parallel with multicore + |