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:
The Arm NN SDK supports the following machine learning layers for Caffe networks:
Argmax, excluding the top_k and out_max_val parameters.
BatchNorm, in inference mode.
Convolution, excluding Weight Filler, Bias Filler, Engine, Force nd_im2col, and Axis parameters.
Deconvolution, excluding the Dilation Size, Weight Filler, Bias Filler, Engine, Force nd_im2col, and Axis parameters.
Caffe doesn't support depthwise convolution, the equivalent layer is implemented through the notion of groups. ArmNN supports groups this way:
Concat, along the channel dimension only.
Dropout, in inference mode.
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.
More machine learning layers will be supported in future releases.