diff options
author | Matthew Sloyan <matthew.sloyan@arm.com> | 2021-04-15 20:46:24 +0100 |
---|---|---|
committer | Matthew Sloyan <matthew.sloyan@arm.com> | 2021-04-15 20:51:23 +0100 |
commit | ed7fce413410d15c501ea52f9e6bfbbf71b3daf1 (patch) | |
tree | f72645fdb44fec0fee95e00bd6c6f51b404ed5c7 /docs/01_01_parsers.dox | |
parent | 86723e67a940ed9f288c3cb59c120b9a10a1d590 (diff) | |
download | armnn-ed7fce413410d15c501ea52f9e6bfbbf71b3daf1.tar.gz |
IVGCVSW-5829 Segfault in tflite-parser, int8 models
* Updated ParseSplit TfLiteParser function to read correct axis data.
* Improved validation in ParseSplit and ParseSplitV function.
* Added TensorFlow BOOL support to TfLiteParser.
* Added supported ElementWiseUnary operators to TfLiteParser
E.g. ABS, LOGICAL_NOT and RSQRT.
* Removed ParseExp and ParseNeg function implementation in favour
of reusable ParseElementWiseUnary function.
* Removed Exp.cpp and Neg.cpp files and moved tests to ElementWiseUnary.cpp.
Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com>
Change-Id: Ibce36e3ce4d95755dda88abc2ddde1e07e62c5e2
Diffstat (limited to 'docs/01_01_parsers.dox')
-rw-r--r-- | docs/01_01_parsers.dox | 5 |
1 files changed, 4 insertions, 1 deletions
diff --git a/docs/01_01_parsers.dox b/docs/01_01_parsers.dox index 05e1225f93..6607921585 100644 --- a/docs/01_01_parsers.dox +++ b/docs/01_01_parsers.dox @@ -157,9 +157,10 @@ This reference guide provides a list of TensorFlow Lite operators the Arm NN SDK ### Fully supported The Arm NN SDK TensorFlow Lite parser currently supports the following operators: +- ABS - ADD - ARG_MAX -_ ARG_MIN +- ARG_MIN - AVERAGE_POOL_2D, Supported Fused Activation: RELU , RELU6 , TANH, NONE - BATCH_TO_SPACE - CONCATENATION, Supported Fused Activation: RELU , RELU6 , TANH, NONE @@ -174,6 +175,7 @@ _ ARG_MIN - GATHER - HARD_SWISH - LEAKY_RELU +- LOGICAL_NOT - LOGISTIC - L2_NORMALIZATION - MAX_POOL_2D, Supported Fused Activation: RELU , RELU6 , TANH, NONE @@ -192,6 +194,7 @@ _ ARG_MIN - RESHAPE - RESIZE_BILINEAR - RESIZE_NEAREST_NEIGHBOR +- RSQRT - SLICE - SOFTMAX - SPACE_TO_BATCH |