diff options
author | surmeh01 <surabhi.mehta@arm.com> | 2018-03-29 16:29:27 +0100 |
---|---|---|
committer | surmeh01 <surabhi.mehta@arm.com> | 2018-03-29 16:29:27 +0100 |
commit | bceff2fb3fc68bb0aa88b886900c34b77340c826 (patch) | |
tree | d867d3e090d58d3012dfbbac456e9ea8c7f789bc /src/armnnCaffeParser | |
parent | 4fcda0101ec3d110c1d6d7bee5c83416b645528a (diff) | |
download | armnn-bceff2fb3fc68bb0aa88b886900c34b77340c826.tar.gz |
Release 18.03
Diffstat (limited to 'src/armnnCaffeParser')
-rw-r--r-- | src/armnnCaffeParser/CaffeSupport.md | 31 | ||||
-rw-r--r-- | src/armnnCaffeParser/README.md | 5 |
2 files changed, 36 insertions, 0 deletions
diff --git a/src/armnnCaffeParser/CaffeSupport.md b/src/armnnCaffeParser/CaffeSupport.md new file mode 100644 index 0000000000..e7724800f6 --- /dev/null +++ b/src/armnnCaffeParser/CaffeSupport.md @@ -0,0 +1,31 @@ +#Caffe layers supported by the Arm NN SDK +This reference guide provides a list of Caffe layers the Arm NN SDK currently supports. + +Although some other neural networks might work, Arm tests the Arm NN SDK with Caffe implementations of the following neural networks: + +- AlexNet. +- Cifar10. +- Inception-BN. +- Resnet_50, Resnet_101 and Resnet_152. +- VGG_CNN_S, VGG_16 and VGG_19. +- Yolov1_tiny. +- Lenet. +- MobileNetv1. + +The Arm NN SDK supports the following machine learning layers for Caffe networks: + + +- BatchNorm, in inference mode. +- Convolution, excluding the Dilation Size, Weight Filler, Bias Filler, Engine, Force nd_im2col, and Axis parameters. +- Eltwise, excluding the coeff parameter. +- Inner Product, excluding the Weight Filler, Bias Filler, Engine, and Axis parameters. +- Input. +- LRN, excluding the Engine parameter. +- Pooling, excluding the Stochastic Pooling and Engine parameters. +- ReLU. +- Scale. +- Softmax, excluding the Axis and Engine parameters. +- Split. +- Dropout, in inference mode. + +More machine learning layers will be supported in future releases.
\ No newline at end of file diff --git a/src/armnnCaffeParser/README.md b/src/armnnCaffeParser/README.md new file mode 100644 index 0000000000..92d7d0a0bf --- /dev/null +++ b/src/armnnCaffeParser/README.md @@ -0,0 +1,5 @@ +#Arm NN Caffe parser + +`armnnCaffeParser` is a library for loading neural networks defined in Caffe protobuf files into the Arm NN runtime. + +For more information about the Caffe layers that are supported, and the networks that have been tested, see [CaffeSupport.md](./CaffeSupport.md).
\ No newline at end of file |