predictAndUpdateState

Class: dlhdl.Workflow
Namespace: dlhdl

Predict responses by using a trained and deployed recurrent neural network and update the deployed network state

Since R2022b

Syntax

Y = predictAndUpdateState(workflowObject,sequences)

[Y,performance] = predictAndUpdateState(workflowObject,sequences,Name,Value)

Description

Y = predictAndUpdateState(workflowObject,sequences) predicts responses for data in sequences using the deployed network and updates the network state. The method does not initialize the network state before running. This method supports recurrent neural networks only. The specified network must have at least one recurrent layer, such as an LSTM layer or a custom layer with state parameters.

[Y,performance] = predictAndUpdateState(workflowObject,sequences,Name,Value) predicts responses and updates the network state with one or more arguments specified by optional name-value pair arguments.

Input Arguments

workflowObject — Deep learning network deployment options

dlhdl.Workflow object

Deep learning network deployment options, specified as a dlhdl.Workflow object.

sequences — Sequence or time series data

numeric array

For numeric array input, the dimensions of the numeric arrays containing the sequences depend on the type of data.

Input	Description
Vector sequences	c-by-s matrices, where c is the number of features of the sequences and s is the sequence length.
1-D image sequences	h-by-c-by-s arrays, where h and c correspond to the height and number of channels of the images, respectively, and s is the sequence length.
2-D image sequences	h-by-w-by-c-by-s arrays, where h, w, and c correspond to the height, width, and number of channels of the images, respectively, and s is the sequence length.
3-D image sequences	h-by-w-by-d-by-c-by-s, where h, w, d, and c correspond to the height, width, depth, and number of channels of the 3-D images, respectively, and s is the sequence length.

The dimensions of the sequence data must correspond to the table.

Data Types: single | double | int8 | int16 | int32 | int64 | uint8 | uint16 | uint32 | uint64

Name-Value Arguments

Specify optional pairs of arguments as Name1=Value1,...,NameN=ValueN, where Name is the argument name and Value is the corresponding value. Name-value arguments must appear after other arguments, but the order of the pairs does not matter.

Before R2021a, use commas to separate each name and value, and enclose Name in quotes.

Example:

Profile — Flag that returns profiling results

"off" (default) | "on"

Flag to return profiling results, for the deep learning network deployed to the target board, specified as "off" or "on".

Example: "Profile", "On"

Output Arguments

Y — Predicted responses

numeric array

Predicted responses, returned as a numeric array. The format of Y depends on the type of task.

This table describes the format for regression problems.

Task	Format
2-D image regression	h-by-w-by-c-by-N numeric array, where h, w, and c are the height, width, and number of channels of the images, respectively, and N is the number of images
3-D image regression	h-by-w-by-d-by-c-by-N numeric array, where h, w, d, and c are the height, width, depth, and number of channels of the images, respectively, and N is the number of images
Sequence-to-one regression	N-by-R matrix, where N is the number of sequences and R is the number of responses
Sequence-to-sequence regression	N-by-R matrix, where N is the number of sequences and R is the number of responses
Feature regression	N-by-R matrix, where N is the number of observations and R is the number of responses

For sequence-to-sequence regression problems with one observation, sequences can be a matrix. In this case, Y is a matrix of responses.

If the output layer of the network is a classification layer, then Y is the predicted classification scores. This table describes the format of the scores for classification tasks.

Task	Format
Image classification	N-by-K matrix, where N is the number of observations and K is the number of classes
Sequence-to-label classification
Feature classification

performance — Deployed network performance data

table

Deployed network performance data, returned as an N-by-5 table, where N is the number of layers in the network. This method returns performance only when the Profile name-value argument is set to 'on'. To learn about the data in the performance table, see Profile Inference Run.

Examples

Run Sequence Forecasting on FPGA by Using Deep Learning HDL Toolbox

This example shows how to create, compile, and deploy a long short-term memory (LSTM) network trained on waveform data by using the Deep Learning HDL Toolbox™ Support Package for Xilinx FPGA and SoC. Use the deployed network to predict future values by using open-loop and closed-loop forecasting. Use MATLAB® to retrieve the prediction results from the target device.

Waveform Data Network

The network attached to this example was trained using the Time Series Forecasting Using Deep Learning. This example uses the WaveformData.mat data set, which contains 2000 synthetically generated waveforms of varying lengths with three channels. This example uses a trained LSTM network to forecast future values of the waveforms given the values from the previous time steps using both closed loop and open loop forecasting.

Prerequisites

• Xilinx® Zynq® Ultrascale+™ ZCU102 SoC development kit

• Deep Learning HDL Toolbox™ Support Package for Xilinx FPGA and SoC

• Deep Learning Toolbox™

• Deep Learning HDL Toolbox™

Load the Pretrained Network

To load the LSTM network enter:

load WaveformForcastingNet

Use the analyzeNetwork function to obtain information about the network layers. the function returns a graphical representation of the network that contains detailed parameter information for every layer in the network.

analyzeNetwork(net)

Define FPGA Board Interface

Define the target FPGA board programming interface by using the dlhdl.Target object. Specify that the interface is for a Xilinx board with an Ethernet interface.

To create the target object, enter:

hTarget = dlhdl.Target('Xilinx','Interface','Ethernet');

To use the JTAG interface, install Xilinx™ Vivado™ Design Suite 2022.1. To set the Xilinx Vivado toolpath, enter:

hdlsetuptoolpath('ToolName', 'Xilinx Vivado', 'ToolPath', 'C:\Xilinx\Vivado\2022.1\bin\vivado.bat');
hTarget = dlhdl.Target('Xilinx','Interface','JTAG');

Prepare Network for Deployment

Prepare the network for deployment by creating a dlhdl.Workflow object. Specify the network and the bitstream name. Ensure that the bitstream name matches the data type and the FPGA board. In this example the target FPGA board is the Xilinx ZCU102 SOC board. The bitstream uses a single data type.

hW = dlhdl.Workflow('network', net, 'Bitstream', 'zcu102_lstm_single','Target',hTarget);

Tu run the example on the Xilinx ZC706 board, enter:

hW = dlhdl.Workflow('Network', snet, 'Bitstream', 'zc706_lstm_single','Target',hTarget);

Compile the LSTM Network

Run the compile method of the dlhdl.Workflow object to compile the network and generate the instructions, weights, and biases for deployment. The total number of frames exceeds the default value of 30. Set the InputFrameNumberLimit name-value argument to 1000 to run predictions in chunks of 1000 frames to prevent timeouts.

dn = compile(hW,'InputFrameNumberLimit',1000)

### Compiling network for Deep Learning FPGA prototyping ...
### Targeting FPGA bitstream zcu102_lstm_single.
### The network includes the following layers:
     1   'sequenceinput'      Sequence Input      Sequence input with 3 dimensions             (SW Layer)
     2   'lstm'               LSTM                LSTM with 128 hidden units                   (HW Layer)
     3   'fc'                 Fully Connected     3 fully connected layer                      (HW Layer)
     4   'regressionoutput'   Regression Output   mean-squared-error with response 'Response'  (SW Layer)
                                                                                             
### Notice: The layer 'sequenceinput' with type 'nnet.cnn.layer.ImageInputLayer' is implemented in software.
### Notice: The layer 'regressionoutput' with type 'nnet.cnn.layer.RegressionOutputLayer' is implemented in software.
### Compiling layer group: lstm.wi ...
### Compiling layer group: lstm.wi ... complete.
### Compiling layer group: lstm.wo ...
### Compiling layer group: lstm.wo ... complete.
### Compiling layer group: lstm.wg ...
### Compiling layer group: lstm.wg ... complete.
### Compiling layer group: lstm.wf ...
### Compiling layer group: lstm.wf ... complete.
### Compiling layer group: fc ...
### Compiling layer group: fc ... complete.

### Allocating external memory buffers:

          offset_name          offset_address     allocated_space 
    _______________________    ______________    _________________
    "InputDataOffset"           "0x00000000"     "16.0 kB"        
    "OutputResultOffset"        "0x00004000"     "16.0 kB"        
    "SchedulerDataOffset"       "0x00008000"     "612.0 kB"       
    "SystemBufferOffset"        "0x000a1000"     "20.0 kB"        
    "InstructionDataOffset"     "0x000a6000"     "4.0 kB"         
    "FCWeightDataOffset"        "0x000a7000"     "272.0 kB"       
    "EndOffset"                 "0x000eb000"     "Total: 940.0 kB"
### Network compilation complete.

dn = struct with fields:
             weights: [1×1 struct]
        instructions: [1×1 struct]
           registers: [1×1 struct]
    syncInstructions: [1×1 struct]
        constantData: {}
             ddrInfo: [1×1 struct]
       resourceTable: [6×2 table]

Program Bitstream onto FPGA and Download Network Weights

To deploy the network on the Xilinx ZCU102 SoC hardware, run the deploy function of the dlhdl.Workflow object. This function uses the output of the compile function to program the FPGA board by using the programming file. It also downloads the network weights and biases. The deploy function starts programming the FPGA device and displays progress messages, and the required time to deploy the network.

 deploy(hW)

### Programming FPGA Bitstream using Ethernet...
### Attempting to connect to the hardware board at 192.168.1.101...
### Connection successful
### Programming FPGA device on Xilinx SoC hardware board at 192.168.1.101...
### Copying FPGA programming files to SD card...
### Setting FPGA bitstream and devicetree for boot...
# Copying Bitstream zcu102_lstm_single.bit to /mnt/hdlcoder_rd
# Set Bitstream to hdlcoder_rd/zcu102_lstm_single.bit
# Copying Devicetree devicetree_dlhdl.dtb to /mnt/hdlcoder_rd
# Set Devicetree to hdlcoder_rd/devicetree_dlhdl.dtb
# Set up boot for Reference Design: 'AXI-Stream DDR Memory Access : 3-AXIM'
### Rebooting Xilinx SoC at 192.168.1.101...
### Reboot may take several seconds...
### Attempting to connect to the hardware board at 192.168.1.101...
### Connection successful
### Programming the FPGA bitstream has been completed successfully.
### Resetting network state.
### Loading weights to FC Processor.
### 50% finished, current time is 10-Dec-2023 14:33:24.
### FC Weights loaded. Current time is 10-Dec-2023 14:33:24

Test Network

Prepare the test data for prediction. Normalize the test data using the statistics calculated from the training data. To forecast the values of future time steps of a sequence, specify the targets as the test sequences with values shifted by one time step. In other words, at each time step of the input sequence, the LSTM network learns to predict the value of the next time step. The predictors as the test sequences without the final time step.

load WaveformData.mat
data = cellfun(@(x)x',data,UniformOutput=false);
numChannels = size(data{1},1);
numObservations = numel(data);

idxTrain = 1:floor(0.9*numObservations);
idxTest = floor(0.9*numObservations)+1:numObservations;
dataTrain = data(idxTrain);
dataTest = data(idxTest);

for n = 1:numel(dataTrain)
    X = dataTrain{n};
    XTrain{n} = X(:,1:end-1);
    TTrain{n} = X(:,2:end);
end

muX = mean(cat(2,XTrain{:}),2);
sigmaX = std(cat(2,XTrain{:}),0,2);
muT = mean(cat(2,TTrain{:}),2);
sigmaT = std(cat(2,TTrain{:}),0,2);

for n = 1:size(dataTest,1)
    X = dataTest{n};
    XTest{n} = (X(:,1:end-1) - muX) ./ sigmaX;
    TTest{n} = (X(:,2:end) - muT) ./ sigmaT;
end

Make predictions using the test data.

YTest = hW.predict(XTest{1},Profile ='on');

### Resetting network state.
### Finished writing input activations.
### Running a sequence of length 115.


              Deep Learning Processor Profiler Performance Results

                   LastFrameLatency(cycles)   LastFrameLatency(seconds)       FramesNum      Total Latency     Frames/s
                         -------------             -------------              ---------        ---------       ---------
Network                      33810                  0.00015                     115            3916501           6459.8
    memSeparator_0              95                  0.00000 
    memSeparator_3             184                  0.00000 
    lstm.wi                   7580                  0.00003 
    lstm.wo                   7569                  0.00003 
    lstm.wg                   7549                  0.00003 
    lstm.wf                   7649                  0.00003 
    lstm.sigmoid_1             222                  0.00000 
    lstm.sigmoid_3             224                  0.00000 
    lstm.tanh_1                244                  0.00000 
    lstm.sigmoid_2             224                  0.00000 
    lstm.multiplication_2       294                  0.00000 
    lstm.multiplication_1       364                  0.00000 
    lstm.c_add                 288                  0.00000 
    lstm.tanh_2                228                  0.00000 
    memSeparator_2             174                  0.00000 
    lstm.multiplication_3       294                  0.00000 
    fc                         460                  0.00000 
    memSeparator_1             168                  0.00000 
 * The clock frequency of the DL processor is: 220MHz

To evaluate the accuracy, calculate the root mean squared error (RMSE) between the predictions and the target for each test sequence.

for i = 1:size(YTest,1)
    rmse(i) = sqrt(mean((YTest(i) - TTest{1}(i)).^2,"all"));
end

Visualize the errors in a histogram. Lower values indicate greater accuracy.

figure
histogram(rmse)
xlabel("RMSE")
ylabel("Frequency")

Calculate the mean RMSE over all test observations.

mean(rmse)

ans = single
    0.8385

Forecast Future Time Steps

To forecast the values of multiple future time steps, when given an input time series or sequence, use the predict function. This function predicts time steps one at a time and updates the network state at each prediction. For each prediction, use the previous prediction as the input to the function.

Visualize one of the test sequences in a plot.

idx = 2;
X = XTest{idx};
T = TTest{idx};

figure
stackedplot(X',DisplayLabels="Channel " + (1:numChannels))
xlabel("Time Step")
title("Test Observation " + idx)

Open-Loop Forecasting

Open-loop forecasting predicts the next time step in a sequence using only the input data. When making predictions for subsequent time steps, you collect the true values form your data source and use those as input. For example, suppose that you want to predict the value for time step $$t$$ of a sequence by using data collected in time steps 1 through $$t-1$$. To make predictions for time step $$t+1$$, wait until you record the true value for time step $$t$$ and use that value as input to make the next prediction. Use open-loop forecasting when you have true values to provide to the network before making the next prediction.

Initialize the network state by resetting the state using the resetState function, then make an initial prediction using the first few time steps of the input data. Update the network state by using the first 75 time steps of the input data.

resetState(hW)
offset = 75;
[~,~] = hW.predict(X(:,1:offset),KeepState=true,Profile='on'); 

### Resetting network state.
### Finished writing input activations.
### Running a sequence of length 75.


              Deep Learning Processor Profiler Performance Results

                   LastFrameLatency(cycles)   LastFrameLatency(seconds)       FramesNum      Total Latency     Frames/s
                         -------------             -------------              ---------        ---------       ---------
Network                      33730                  0.00015                      75            2554104           6460.2
    memSeparator_0              95                  0.00000 
    memSeparator_3             184                  0.00000 
    lstm.wi                   7620                  0.00003 
    lstm.wo                   7449                  0.00003 
    lstm.wg                   7549                  0.00003 
    lstm.wf                   7659                  0.00003 
    lstm.sigmoid_1             222                  0.00000 
    lstm.sigmoid_3             224                  0.00000 
    lstm.tanh_1                254                  0.00000 
    lstm.sigmoid_2             224                  0.00000 
    lstm.multiplication_2       344                  0.00000 
    lstm.multiplication_1       294                  0.00000 
    lstm.c_add                 288                  0.00000 
    lstm.tanh_2                228                  0.00000 
    memSeparator_2             174                  0.00000 
    lstm.multiplication_3       294                  0.00000 
    fc                         420                  0.00000 
    memSeparator_1             208                  0.00000 
 * The clock frequency of the DL processor is: 220MHz

To forecast further predictions, loop over time steps and update the network state by using the predict function and setting the KeepState name-value argument to true. Forecast values for the remaining time steps of the test observation by looping over the time steps of the input data and using them as input to the network. The first prediction is the value that corresponds to the time step offset + 1.

numTimeSteps = size(X,2);
numPredictionTimeSteps = numTimeSteps - offset;
Y = hW.predict(X(:,offset+1:offset+numPredictionTimeSteps),KeepState=true,Profile='on');

### Finished writing input activations.
### Running a sequence of length 116.


              Deep Learning Processor Profiler Performance Results

                   LastFrameLatency(cycles)   LastFrameLatency(seconds)       FramesNum      Total Latency     Frames/s
                         -------------             -------------              ---------        ---------       ---------
Network                      33770                  0.00015                     116            3947829           6464.3
    memSeparator_0              95                  0.00000 
    memSeparator_3             174                  0.00000 
    lstm.wi                   7570                  0.00003 
    lstm.wo                   7549                  0.00003 
    lstm.wg                   7589                  0.00003 
    lstm.wf                   7609                  0.00003 
    lstm.sigmoid_1             222                  0.00000 
    lstm.sigmoid_3             224                  0.00000 
    lstm.tanh_1                274                  0.00000 
    lstm.sigmoid_2             224                  0.00000 
    lstm.multiplication_2       334                  0.00000 
    lstm.multiplication_1       294                  0.00000 
    lstm.c_add                 308                  0.00000 
    lstm.tanh_2                238                  0.00000 
    memSeparator_2             184                  0.00000 
    lstm.multiplication_3       294                  0.00000 
    fc                         420                  0.00000 
    memSeparator_1             168                  0.00000 
 * The clock frequency of the DL processor is: 220MHz

Compare the predictions with the target values.

figure
t = tiledlayout(numChannels,1);
title(t,"Open Loop Forecasting with LSTM layer")

for i = 1:numChannels
    nexttile
    plot(T(i,:))
    hold on
    plot(offset:numTimeSteps,[T(i,offset) Y(i,:)],'--')
    ylabel("Channel " + i)
end

xlabel("Time Step")
nexttile(1)
legend(["Input" "Forecasted"])

Closed-Loop Forecasting

Closed-loop forecasting predicts subsequent time steps in a sequence by using the previous predictions as input. In this case, the model does not require the true values to make the prediction. For example, suppose that you want to predict the value for time steps $$t$$ through $$t+k$$ of the sequence by using data collected in time steps 1 through $$t-1$$. To make predictions for time step $$i$$, use the predicted value for time step $$i-1$$ as input. Use closed-loop forecasting to forecast multiple subsequent time steps or when you do not have true values to provide to the network before making the next prediction.

Initialize the network state by resetting the state using the resetState function, then make an initial prediction, Z, using the first few time steps of the input data. Update the network state by using the first 75 time steps of the input data.

resetState(hW)
[Z, ~] = predict(hW,X,KeepState=true,Profile='on');

### Resetting network state.
### Finished writing input activations.
### Running a sequence of length 191.


              Deep Learning Processor Profiler Performance Results

                   LastFrameLatency(cycles)   LastFrameLatency(seconds)       FramesNum      Total Latency     Frames/s
                         -------------             -------------              ---------        ---------       ---------
Network                      33717                  0.00015                     191            6502666           6462.0
    memSeparator_0              95                  0.00000 
    memSeparator_3             174                  0.00000 
    lstm.wi                   7580                  0.00003 
    lstm.wo                   7548                  0.00003 
    lstm.wg                   7458                  0.00003 
    lstm.wf                   7649                  0.00003 
    lstm.sigmoid_1             221                  0.00000 
    lstm.sigmoid_3             224                  0.00000 
    lstm.tanh_1                244                  0.00000 
    lstm.sigmoid_2             224                  0.00000 
    lstm.multiplication_2       294                  0.00000 
    lstm.multiplication_1       364                  0.00000 
    lstm.c_add                 288                  0.00000 
    lstm.tanh_2                238                  0.00000 
    memSeparator_2             184                  0.00000 
    lstm.multiplication_3       294                  0.00000 
    fc                         470                  0.00000 
    memSeparator_1             168                  0.00000 
 * The clock frequency of the DL processor is: 220MHz

To forecast further predictions, loop over time steps and update the network state by using the predict function and setting the KeepState name-value argument to true. Forecast the next 200 time steps by iteratively passing the previously predicted value to the network. Because the network does not require the input data to make any further predictions, you can specify any number of time steps to forecast.

numPredictionTimeSteps = 200;
Xt = Z(:,end);
Y = zeros(numChannels,numPredictionTimeSteps);
fprintf("Run %d predictions:\n",numPredictionTimeSteps);

Run 200 predictions:

for t = 1:numPredictionTimeSteps
    fprintf(".");
    [Y(:,t),~] =  predict(hW,Xt,KeepState=true);
    Xt = Y(:,t);   
end

Visualize the forecasted values in a plot.

offset = size(X,2);
numTimeSteps = offset + numPredictionTimeSteps;

figure
t = tiledlayout(numChannels,1);
title(t,"Closed Loop Forecasting with LSTM layer")

for i = 1:numChannels
    nexttile
    plot(T(i,1:offset))
    hold on
    plot(offset:numTimeSteps,[T(i,offset) Y(i,:)],'--')
    ylabel("Channel " + i)
end

xlabel("Time Step")
nexttile(1)
legend(["Input" "Forecasted"])

Closed-loop forecasting allows you to forecast an arbitrary number of time steps, but can be less accurate when compared to open-loop forecasting because the network does not have access to the true values during the forecasting process.

Version History

Introduced in R2022b