IVGCVSW-2635 Update TensorFlowSupport.md
* Also fixed a format issue in TfParser.hpp
Change-Id: I5b0ae1d5909f03e166a40d3aca8859024cd5e5b6
Signed-off-by: Jim Flynn <jim.flynn@arm.com>
diff --git a/src/armnnTfParser/TensorFlowSupport.md b/src/armnnTfParser/TensorFlowSupport.md
index e3f4ae2..954f8e8 100644
--- a/src/armnnTfParser/TensorFlowSupport.md
+++ b/src/armnnTfParser/TensorFlowSupport.md
@@ -24,7 +24,7 @@
**local_response_normalization**
-See the TensorFlow [local_response_normalization documentation](https://www.tensorflow.org/api_docs/python/tf/nn/local_response_normalization) for more information.
+See the TensorFlow [local_response_normalization documentation](https://www.tensorflow.org/api_docs/python/tf/nn/local_response_normalization) for more information.
**max_pool**
@@ -62,12 +62,32 @@
See the TensorFlow [tanh documentation](https://www.tensorflow.org/api_docs/python/tf/tanh) for more information.
+**expand_dims**
+
+See the TensorFlow [expand_dims documentation](https://www.tensorflow.org/api_docs/python/tf/expand_dims) for more information.
+
+**placeholder**
+
+See the TensorFlow [placeholder documentation](https://www.tensorflow.org/api_docs/python/tf/placeholder) for more information.
+
+**minimum**
+
+See the TensorFlow [minimum documentation](https://www.tensorflow.org/api_docs/python/tf/math/minimum) for more information.
+
+**greater**
+
+See the TensorFlow [greater documentation](https://www.tensorflow.org/api_docs/python/tf/math/greater) for more information.
+
## Partially supported
**add**
The parser does not support all forms of [broadcast composition](https://www.tensorflow.org/performance/xla/broadcasting), only broadcasting of scalars and 1D tensors. See the TensorFlow [add operator documentation](https://www.tensorflow.org/api_docs/python/tf/add) for more information.
+**add_n**
+
+The parser does not support all forms of [broadcast composition](https://www.tensorflow.org/performance/xla/broadcasting), only broadcasting of scalars and 1D tensors. See the TensorFlow [add operator documentation](https://www.tensorflow.org/api_docs/python/tf/add_n) for more information.
+
**concat**
Arm NN supports concatenation along the channel dimension for data formats NHWC and NCHW.
@@ -90,15 +110,11 @@
**multiply**
-The parser does not support all forms of [broadcast composition](https://www.tensorflow.org/performance/xla/broadcasting), only broadcasting of scalars and 1D tensors. See the TensorFlow [multiply documentation](https://www.tensorflow.org/api_docs/python/tf/multiply) for more information.
-
-**placeholder**
-
- The parser only supports the NHWC data format in the input layer. See the TensorFlow [placeholder documentation](https://www.tensorflow.org/api_docs/python/tf/placeholder) for more information.
+The parser does not support all forms of [broadcast composition](https://www.tensorflow.org/performance/xla/broadcasting), only broadcasting of scalars and 1D tensors. See the TensorFlow [multiply documentation](https://www.tensorflow.org/api_docs/python/tf/multiply) for more information.
**realdiv**
-The parser does not support all forms of [broadcast composition](https://www.tensorflow.org/performance/xla/broadcasting), only broadcasting of scalars and 1D tensors. See the TensorFlow [realdiv documentation](https://www.tensorflow.org/api_docs/python/tf/realdiv) for more information.
+The parser does not support all forms of [broadcast composition](https://www.tensorflow.org/performance/xla/broadcasting), only broadcasting of scalars and 1D tensors. See the TensorFlow [realdiv documentation](https://www.tensorflow.org/api_docs/python/tf/realdiv) for more information.
**reshape**
@@ -125,7 +141,15 @@
* max(x, mul(a, x))
* max(x, mul(x, a)
-This is interpreted as a ActivationLayer with a LeakyRelu activation function. Any other usage of max will currently cause an unsupported error. See the TensorFlow [maximum documentation](https://www.tensorflow.org/api_docs/python/tf/maximum) for more information.
+This is interpreted as a ActivationLayer with a LeakyRelu activation function. Any other usage of max will result in the insertion of a simple maximum layer. See the TensorFlow [maximum documentation](https://www.tensorflow.org/api_docs/python/tf/maximum) for more information.
+
+**pad**
+
+Only supports tf.pad function with mode = 'CONSTANT' and constant_values = 0. See the TensorFlow [pad documentation](https://www.tensorflow.org/api_docs/python/tf/pad) for more information.
+
+**subtract**
+
+The parser does not support all forms of broadcasting [broadcast composition](https://www.tensorflow.org/performance/xla/broadcasting), only broadcasting of scalars and 1D tensors. See the TensorFlow [subtract documentation](https://www.tensorflow.org/api_docs/python/tf/math/subtract) for more information.
## Tested networks
diff --git a/src/armnnTfParser/TfParser.hpp b/src/armnnTfParser/TfParser.hpp
index 2b80941..46da55f 100644
--- a/src/armnnTfParser/TfParser.hpp
+++ b/src/armnnTfParser/TfParser.hpp
@@ -133,8 +133,9 @@
ParsedTfOperationPtr ParseAddN(const tensorflow::NodeDef& nodeDef, const tensorflow::GraphDef& graphDef);
ParsedTfOperationPtr ParseBiasAdd(const tensorflow::NodeDef& nodeDef, const tensorflow::GraphDef& graphDef);
ParsedTfOperationPtr ParseConv2D(const tensorflow::NodeDef& nodeDef, const tensorflow::GraphDef& graphDef);
- ParsedTfOperationPtr ParseDepthwiseConv2D(const tensorflow::NodeDef& nodeDef,const tensorflow::GraphDef& graphDef);
- ParsedTfOperationPtr ParseExpandDims(const tensorflow::NodeDef& nodeDef,const tensorflow::GraphDef& graphDef);
+ ParsedTfOperationPtr ParseDepthwiseConv2D(const tensorflow::NodeDef& nodeDef,
+ const tensorflow::GraphDef& graphDef);
+ ParsedTfOperationPtr ParseExpandDims(const tensorflow::NodeDef& nodeDef, const tensorflow::GraphDef& graphDef);
ParsedTfOperationPtr ParseFusedBatchNorm(const tensorflow::NodeDef& nodeDef, const tensorflow::GraphDef& graphDef);
ParsedTfOperationPtr ParseConcat(const tensorflow::NodeDef& nodeDef, const tensorflow::GraphDef& graphDef);
ParsedTfOperationPtr ParseIdentity(const tensorflow::NodeDef& nodeDef, const tensorflow::GraphDef& graphDef);
@@ -158,8 +159,9 @@
ParsedTfOperationPtr ParseTanh(const tensorflow::NodeDef& nodeDef, const tensorflow::GraphDef& graphDef);
ParsedTfOperationPtr ParseMaxPool(const tensorflow::NodeDef& nodeDef, const tensorflow::GraphDef& graphDef);
ParsedTfOperationPtr ParseAvgPool(const tensorflow::NodeDef& nodeDef, const tensorflow::GraphDef& graphDef);
- ParsedTfOperationPtr ParsePooling2d(const tensorflow::NodeDef& nodeDef, const tensorflow::GraphDef& graphDef,
- armnn::PoolingAlgorithm pooltype);
+ ParsedTfOperationPtr ParsePooling2d(const tensorflow::NodeDef& nodeDef,
+ const tensorflow::GraphDef& graphDef,
+ armnn::PoolingAlgorithm pooltype);
ParsedTfOperationPtr ParseEqual(const tensorflow::NodeDef& nodeDef, const tensorflow::GraphDef& graphDef);
ParsedTfOperationPtr ParseMaximum(const tensorflow::NodeDef& nodeDef, const tensorflow::GraphDef& graphDef);
ParsedTfOperationPtr ParseMinimum(const tensorflow::NodeDef& nodeDef, const tensorflow::GraphDef& graphDef);