From 89c5a9e6ecfa169512c43e659b1833f9a3c41d90 Mon Sep 17 00:00:00 2001 From: Sadik Armagan Date: Wed, 20 Jan 2021 17:48:07 +0000 Subject: IVGCVSW-5391 'ArmNN TfLiteDelegate: Implement the Space/Depth operators' * Added DEPTH_TO_SPACE and SPACE_TO_DEPTH operators support Signed-off-by: Sadik Armagan Change-Id: I2595f759181bd7339127e7b114b850b534210dd5 --- delegate/TensorFlowLiteDelegateSupport.md | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'delegate/TensorFlowLiteDelegateSupport.md') diff --git a/delegate/TensorFlowLiteDelegateSupport.md b/delegate/TensorFlowLiteDelegateSupport.md index ed1124a1ff..a5d4faf3ef 100644 --- a/delegate/TensorFlowLiteDelegateSupport.md +++ b/delegate/TensorFlowLiteDelegateSupport.md @@ -20,6 +20,8 @@ The Arm NN SDK TensorFlow Lite delegate currently supports the following operato * CONV_2D, Supported Fused Activation: RELU , RELU6 , TANH, NONE +* DEPTH_TO_SPACE + * DEPTHWISE_CONV_2D, Supported Fused Activation: RELU , RELU6 , TANH, NONE * DEQUANTIZE @@ -94,6 +96,8 @@ The Arm NN SDK TensorFlow Lite delegate currently supports the following operato * SOFTMAX +* SPACE_TO_DEPTH + * SPLIT * SPLIT_V -- cgit v1.2.1