diff options
Diffstat (limited to 'src/armnnDeserializer/DeserializerSupport.md')
| -rw-r--r-- | src/armnnDeserializer/DeserializerSupport.md | 13 |
1 files changed, 10 insertions, 3 deletions
diff --git a/src/armnnDeserializer/DeserializerSupport.md b/src/armnnDeserializer/DeserializerSupport.md index 3b35e5c9f4..fce7064337 100644 --- a/src/armnnDeserializer/DeserializerSupport.md +++ b/src/armnnDeserializer/DeserializerSupport.md @@ -13,6 +13,7 @@ The Arm NN SDK Deserialize parser currently supports the following layers: * BatchToSpaceNd * BatchNormalization * Concat +* Comparison * Constant * Convolution2d * DepthToSpace @@ -20,11 +21,9 @@ The Arm NN SDK Deserialize parser currently supports the following layers: * Dequantize * DetectionPostProcess * Division -* Equal * Floor * FullyConnected * Gather -* Greater * Input * InstanceNormalization * L2Normalization @@ -44,7 +43,6 @@ The Arm NN SDK Deserialize parser currently supports the following layers: * Quantize * QuantizedLstm * Reshape -* ResizeBilinear * Rsqrt * Slice * Softmax @@ -59,3 +57,12 @@ The Arm NN SDK Deserialize parser currently supports the following layers: * Resize More machine learning layers will be supported in future releases. + +## Deprecated layers + +Some layers have been deprecated and replaced by others layers. In order to maintain backward compatibility, serializations of these deprecated layers will deserialize to the layers that have replaced them, as follows: + +* Equal will deserialize as Comparison +* Merger will deserialize as Concat +* Greater will deserialize as Comparison +* ResizeBilinear will deserialize as Resize |