Supported Networks, Layers and Boards

Supported Pretrained Networks

Deep Learning HDL Toolbox™ supports code generation for series convolutional neural networks (CNNs or ConvNets). You can generate code for any trained convolutional neural network whose computational layers are supported for code generation. See Supported Layers. You can use one of the pretrained networks listed in the table and generate code for your target Intel^® or Xilinx^® FPGA boards.

Network	Network Description	Type	Single Data Type (with Shipping Bitstreams)			INT8 data type (with Shipping Bitstreams)			Application Area
			ZCU102	ZC706	Arria10 SoC	ZCU102	ZC706	Arria10 SoC	Classification
AlexNet	AlexNet convolutional neural network.	Series Network	Yes	Yes	Yes	Yes	Yes	Yes	Classification
LogoNet	Logo recognition network (LogoNet) is a MATLAB^® developed logo identification network. For more information, see Logo Recognition Network.	Series Network	Yes	Yes	Yes	Yes	Yes	Yes	Classification
MNIST	MNIST Digit Classification.	Series Network	Yes	Yes	Yes	Yes	Yes	Yes	Regression
Lane detection	LaneNet convolutional neural network. For more information, see Deploy Transfer Learning Network for Lane Detection	Series Network	Yes	Yes	Yes	Yes	Yes	Yes	Classification
VGG-16	VGG-16 convolutional neural network. For the pretrained VGG-16 model, see `vgg16`.	Series Network	No. Network exceeds PL DDR memory size	No. Network exceeds FC module memory size.	Yes	Yes	No. Network exceeds FC module memory size.	Yes	Classification
VGG-19	VGG-19 convolutional neural network. For the pretrained VGG-19 model, see `vgg19` .	Series Network	No. Network exceeds PL DDR memory size	No. Network exceeds FC module memory size.	Yes	Yes	No. Network exceeds FC module memory size.	Yes	Classification
Darknet-19	Darknet-19 convolutional neural network. For the pretrained darknet-19 model, see `darknet19`.	Series Network	Yes	Yes	Yes	No. the network contains a `globalAveragePooling` layer that is not supported for INT8 quantization.	No. the network contains a `globalAveragePooling` layer that is not supported for INT8 quantization.	No. the network contains a `globalAveragePooling` layer that is not supported for INT8 quantization.	Classification
Radar Classification	Convolutional neural network that uses micro-Doppler signatures to identify and classify the object. For more information, see Bicyclist and Pedestrian Classification by Using FPGA.	Series Network	Yes	Yes	Yes	No. the network contains a `AveragePooling` layer that is not supported for INT8 quantization.	No. the network contains a `AveragePooling` layer that is not supported for INT8 quantization.	No. the network contains a `AveragePooling` layer that is not supported for INT8 quantization.	Classification and Software Defined Radio (SDR)
Defect Detection `snet_defnet`	`snet_defnet` is a custom AlexNet network used to identify and classify defects. For more information, see Defect Detection.	Series Network	Yes	Yes	Yes	Yes	Yes	Yes	Classification
Defect Detection`snet_blemdetnet`	`snet_blemdetnet` is a custom convolutional neural network used to identify and classify defects. For more information, see Defect Detection.	Series Network	Yes	Yes	Yes	Yes	Yes	Yes	Classification
YOLO v2 Vehicle Detection	You look only once (YOLO) is an object detector that decodes the predictions from a convolutional neural network and generates bounding boxes around the objects. For more information, see Vehicle Detection Using YOLO v2 Deployed to FPGA	Series Network based	Yes	Yes	Yes	Yes	Yes	Yes	Object detection

Supported Layers

The following layers are supported by Deep Learning HDL Toolbox.

Input Layers

Layer	Layer Type Hardware (HW) or Software(SW)	Description and Limitations	INT8 Compatible
`imageInputLayer`	SW	An image input layer inputs 2-D images to a network and applies data normalization.	Yes. Runs as single datatype in SW.

Convolution and Fully Connected Layers

Layer	Layer Type Hardware (HW) or Software(SW)	Description and Limitations	INT8 Compatible
`convolution2dLayer`	HW	A 2-D convolutional layer applies sliding convolutional filters to the input. These limitations apply when generating code for a network using this layer: Filter size must be 1-12 and square. For example [1 1] or [12 12]. Stride size must be 1,2 or 4 and square. Padding size must be in the range 0-8. Dilation factor must be [1 1].	Yes
`groupedConvolution2dLayer`	HW	A 2-D grouped convolutional layer separates the input channels into groups and applies sliding convolutional filters. Use grouped convolutional layers for channel-wise separable (also known as depth-wise separable) convolution. These limitations apply when generating code for a network using this layer: Filter size must be 1-12 and square. For example [1 1] or [12 12]. Stride size must be 1,2 or 4 and square. Padding size must be in the range 0-8. Dilation factor must be [1 1]. Number of groups must be 1 or 2.	Yes
`fullyConnectedLayer`	HW	A fully connected layer multiplies the input by a weight matrix, and then adds a bias vector. These limitations apply when generating code for a network using this layer: The layer input and output size are limited by the values specified in InputMemorySize and OutputMemorySize.	Yes

Activation Layers

Layer	Layer Type Hardware (HW) or Software(SW)	Description	INT8 Compatible
`reluLayer`	HW	A ReLU layer performs a threshold operation to each element of the input where any value less than zero is set to zero. A clipped ReLU layer is supported only when it is preceded by a convolution layer.	Yes
`leakyReluLayer`	HW	A leaky ReLU layer performs a threshold operation where any input value less than zero is multiplied by a fixed scalar. A leaky ReLU layer is supported only when it is preceded by a convolution layer.	No
`clippedReluLayer`	HW	A clipped ReLU layer performs a threshold operation where any input value less than zero is set to zero and any value above the clipping ceiling is set to that clipping ceiling value. A clipped ReLU layer is supported only when it is preceded by a convolution layer.	No

Normalization, Dropout, and Cropping Layers

Layer	Layer Type Hardware (HW) or Software(SW)	Description	INT8 Compatible
`batchNormalizationLayer`	HW	A batch normalization layer normalizes each input channel across a mini-batch. A batch normalization layer is only supported only when it is preceded by a convolution layer.	Yes
`crossChannelNormalizationLayer`	HW	A channel-wise local response (cross-channel) normalization layer carries out channel-wise normalization. The `WindowChannelSize` must be in the range of 3-9 for code generation.	Yes. Runs as single datatype in HW.
`dropoutLayer`	NoOP on inference	A dropout layer randomly sets input elements to zero with a given probability.	Yes

Pooling and Unpooling Layers

Layer	Layer Type Hardware (HW) or Software(SW)	Description	INT8 Compatible
`maxPooling2dLayer`	HW	A max pooling layer performs down sampling by dividing the input into rectangular pooling regions and computing the maximum of each region. These limitations apply when generating code for a network using this layer: Pool size must be 1-12and square. For example [1 1] or [12 12]. Stride size must be 1-7 and square. Padding size must be in the range 0-2. Padding size can only be used when the pool size is 3-by-3.	Yes
`averagePooling2dLayer`	HW	An average pooling layer performs down sampling by dividing the input into rectangular pooling regions and computing the average values of each region. These limitations apply when generating code for a network using this layer: Pool size must be 1-12 and square. For example [3 3] Stride size must be 1-7 and square. Padding size must be in the range 0-2. Padding size can only be used when the pool size is 3-by-3.	No
`globalAveragePooling2dLayer`	HW	A global average pooling layer performs down sampling by computing the mean of the height and width dimensions of the input. These limitations apply when generating code for a network using this layer: Pool size value must be in the range 1-12 and be square. For example, [1 1] or [12 12]. Total activation pixel size must be smaller than the deep learning processor convolution module input memory size. For more information, see InputMemorySize	No

Output Layer

Layer	Layer Type Hardware (HW) or Software(SW)	Description	INT8 Compatible
`softmax`	SW	A softmax layer applies a softmax function to the input.	Yes. Runs as single datatype in SW.
`classificationLayer`	SW	A classification layer computes the cross-entropy loss for multi class classification issues with mutually exclusive classes.	Yes
`regressionLayer`	SW	A regression layer computes the half-mean-squared-error loss for regression problems.	Yes

Keras and ONNX Layers

Layer Layer Type Hardware (HW) or Software(SW) Description INT8 Compatible

nnet.keras.layer.FlattenCStyleLayer

Flatten activations into 1-D layers assuming C-style (row-major) order.

A nnet.keras.layer.FlattenCStyleLayer is only supported only when it is followed by a fully connected layer.

Yes

nnet.keras.layer.ZeroPadding2dLayer

Zero padding layer for 2-D input.

A nnet.keras.layer.ZeroPadding2dLayer is only supported only when it is followed by a convolution layer or a maxpool layer.

Yes

Supported Boards

These boards are supported by Deep Learning HDL Toolbox:

Xilinx Zynq^®-7000 ZC706.
Intel Arria^® 10 SoC.
Xilinx Zynq UltraScale+™ MPSoC ZCU102.

Documentation