vai_q_tensorflow Supported Operations and APIs

Table 1. Support Operations and APIs for vai_q_tensorflow
Type	Operation Type	tf.nn	tf.layers	tf.keras.layers
Convolution	Conv2D DepthwiseConv2dNative	atrous_conv2d conv2d conv2d_transpose depthwise_conv2d_native separable_conv2d	Conv2D Conv2DTranspose SeparableConv2D	Conv2D Conv2DTranspose DepthwiseConv2D SeparaleConv2D
Fully Connected	MatMul	/	Dense	Dense
BiasAdd	BiasAdd Add	bias_add	/	/
Pooling	AvgPool Mean MaxPool	avg_pool max_pool	AveragePooling2D MaxPooling2D	AveragePooling2D MaxPool2D
Activation	Relu Relu6	relu relu6 leaky_relu	/	ReLU LeakyReLU
BatchNorm[#1]	FusedBatchNorm	batch_normalization batch_norm_with_global_normalization fused_batch_norm	BatchNormalization	BatchNormalization
Upsampling	ResizeBilinear ResizeNearestNeighbor	/	/	UpSampling2D
Concat	Concat ConcatV2	/	/	Concatenate
Others	Placeholder Const Pad Squeeze Reshape ExpandDims	dropout[#2] softmax[#3]	Dropout[#2] Flatten	Input Flatten Reshape Zeropadding2D Softmax
Only supports Conv2D/DepthwiseConv2D/Dense+BN. BN is folded to speed up inference. Dropout is deleted to speed up inference. There is no need to quantize softmax because the DPU does not support it, and it should be deployed to the CPU.