Deploy Quantized Network Example
This example shows how to train, compile, and deploy a dlhdl.Workflow
object that has quantized ResNet-18 as the network object by using the Deep Learning HDL Toolbox™ Support Package for Xilinx FPGA and SoC. Quantization helps reduce the memory requirement of a deep neural network by quantizing weights, biases and activations of network layers to 8-bit scaled integer data types. Use MATLAB® to retrieve the prediction results from the target device.
Required Products
For this example, you need:
Deep Learning Toolbox ™
Deep Learning HDL Toolbox ™
Deep Learning Toolbox Model Quantization Library
Deep Learning Toolbox Model for ResNet-18 Network
Deep Learning HDL Toolbox Support Package for Xilinx FPGA and SoC Devices
MATLAB Coder Interface for Deep Learning Libraries.
Load Pretrained DAG Network
To load the pretrained DAG network ResNet-18, enter:
net = resnet18;
To view the layers of the pretrained DAG network, enter:
analyzeNetwork(net);
The first layer, the image input layer, requires input images of size 227-by-227-by-3, where 3 is the number of color channels.
inputSize = net.Layers(1).InputSize;
inputSize =
1×3
227 227 3
Define Training and Validation Data Sets
This example uses the logos_dataset
data set. The data set consists of 320 images. Create an augmentedImageDatastore
object to use for training and validation.
curDir = pwd; newDir = fullfile(matlabroot,'examples','deeplearning_shared','data','logos_dataset.zip'); copyfile(newDir,curDir,'f'); unzip('logos_dataset.zip'); imds = imageDatastore('logos_dataset', ... 'IncludeSubfolders',true, ... 'LabelSource','foldernames'); [imdsTrain,imdsValidation] = splitEachLabel(imds,0.7,'randomized');
Replace Final Layers
The last three layers of the pretrained network net
are configured for 1000 classes. These three layers must be fine-tuned for the new classification problem. Extract all the layers, except the last three layers, from the pretrained network.
Extract the layer graph from the trained network.
lgraph = layerGraph(net)
lgraph = LayerGraph with properties: Layers: [71×1 nnet.cnn.layer.Layer] Connections: [78×2 table] InputNames: {'data'} OutputNames: {'ClassificationLayer_predictions'}
Remove 'fc1000', 'prob' and 'ClassificationLayer_predictions' layers from the lgraph.
layers = net.SortedLayers; for i = 0:2 lgraph = removeLayers(lgraph,layers(end-i).Name); end
Transfer the layers to the new classification task by replacing the last three layers with a fully connected layer, a softmax layer, and a classification output layer. Set the fully connected layer to have the same size as the number of classes in the new data.
numClasses = numel(categories(imdsTrain.Labels));
numClasses = 32
Create three new layers and add them to the lgraph. Ensure the transferred and new layers are properly connected together in the lgraph.
newLayers = [ fullyConnectedLayer(numClasses,'WeightLearnRateFactor',20,'BiasLearnRateFactor',20,'Name','newFC') softmaxLayer('Name','newProb') classificationLayer('Name','newClassOutput',"Classes","auto")]; lgraph = addLayers(lgraph,newLayers); lgraph = connectLayers(lgraph,layers(end-3).Name,'newFC');
Train Network
The network requires input images of size 227-by-227-by-3, but the images in the image datastores have different sizes. Use an augmented image datastore to automatically resize the training images. Specify additional augmentation operations to perform on the training images, such as randomly flipping the training images along the vertical axis and randomly translating them up to 30 pixels horizontally and vertically. Data augmentation helps prevent the network from overfitting and memorizing the exact details of the training images.
pixelRange = [-30 30]; imageAugmenter = imageDataAugmenter( ... 'RandXReflection',true, ... 'RandXTranslation',pixelRange, ... 'RandYTranslation',pixelRange); augimdsTrain = augmentedImageDatastore(inputSize(1:2),imdsTrain, ... 'DataAugmentation',imageAugmenter);
To automatically resize the validation images without performing further data augmentation, use an augmented image datastore without specifying any additional preprocessing operations.
augimdsValidation = augmentedImageDatastore(inputSize(1:2),imdsValidation);
Specify the training options. For transfer learning, keep the features from the early layers of the pretrained network (the transferred layer weights). To slow down learning in the transferred layers, set the initial learning rate to a small value. Specify the mini-batch size and validation data. The software validates the network every ValidationFrequency
iterations during training.
options = trainingOptions('sgdm', ... 'MiniBatchSize',10, ... 'MaxEpochs',6, ... 'InitialLearnRate',1e-4, ... 'Shuffle','every-epoch', ... 'ValidationData',augimdsValidation, ... 'ValidationFrequency',3, ... 'Verbose',false, ... 'Plots','training-progress');
Train the network that consists of the transferred and new layers. By default, trainNetwork
uses a GPU if one is available (requires Parallel Computing Toolbox™ and a supported GPU device. For more information, see GPU Computing Requirements (Parallel Computing Toolbox)). Otherwise, the network uses a CPU (requires MATLAB Coder Interface for Deep learning Libraries™). You can also specify the execution environment by using the 'ExecutionEnvironment'
name-value argument of trainingOptions
.
netTransfer = trainNetwork(augimdsTrain,lgraph,options);
Create dlquantizer
Object
Create a dlquantizer
object and specify the network to quantize. Specify the execution environment as FPGA.
dlQuantObj = dlquantizer(netTransfer,'ExecutionEnvironment','FPGA');
Calibrate Quantized Network
The dlquantizer
object uses calibration data to collect dynamic ranges for the learnable parameters of the convolution and fully connected layers of the network.
For best quantization results, the calibration data must be a representative of actual inputs predicted by the LogoNet network. Expedite the calibration process by reducing the calibration data set to 20 images.
imageData = imageDatastore(fullfile(curDir,'logos_dataset'),... 'IncludeSubfolders',true,'FileExtensions','.JPG','LabelSource','foldernames'); imageData_reduced = imageData.subset(1:20); dlQuantObj.calibrate(imageData_reduced)
ans=95×5 table
Optimized Layer Name Network Layer Name Learnables / Activations MinValue MaxValue
__________________________ __________________ ________________________ ________ ________
{'conv1_Weights' } {'conv1' } "Weights" -0.52595 0.83365
{'conv1_Bias' } {'conv1' } "Bias" -0.66142 0.67493
{'res2a_branch2a_Weights'} {'res2a_branch2a'} "Weights" -0.36239 0.42815
{'res2a_branch2a_Bias' } {'res2a_branch2a'} "Bias" -0.83058 1.1734
{'res2a_branch2b_Weights'} {'res2a_branch2b'} "Weights" -0.80143 0.54724
{'res2a_branch2b_Bias' } {'res2a_branch2b'} "Bias" -1.2691 1.7777
{'res2b_branch2a_Weights'} {'res2b_branch2a'} "Weights" -0.26073 0.25689
{'res2b_branch2a_Bias' } {'res2b_branch2a'} "Bias" -1.0012 1.2976
{'res2b_branch2b_Weights'} {'res2b_branch2b'} "Weights" -1.1361 0.77358
{'res2b_branch2b_Bias' } {'res2b_branch2b'} "Bias" -1.1981 1.1897
{'res3a_branch2a_Weights'} {'res3a_branch2a'} "Weights" -0.13934 0.21123
{'res3a_branch2a_Bias' } {'res3a_branch2a'} "Bias" -0.54418 0.71134
{'res3a_branch2b_Weights'} {'res3a_branch2b'} "Weights" -0.49925 0.69286
{'res3a_branch2b_Bias' } {'res3a_branch2b'} "Bias" -0.66837 1.4745
{'res3a_branch1_Weights' } {'res3a_branch1' } "Weights" -0.63797 0.66549
{'res3a_branch1_Bias' } {'res3a_branch1' } "Bias" -1.0594 0.92627
⋮
Create Target Object
Create a target object with a custom name for your target device and an interface to connect your target device to the host computer. Interface options are JTAG and Ethernet. To use JTAG, install Xilinx™ Vivado™ Design Suite 2020.2. To set the Xilinx Vivado toolpath, enter:
% hdlsetuptoolpath('ToolName', 'Xilinx Vivado', 'ToolPath', 'C:\Xilinx\Vivado\2020.2\bin\vivado.bat');
To create the target object, enter:
hTarget = dlhdl.Target('Xilinx','Interface','Ethernet');
Alternatively, you can also use the JTAG interface.
% hTarget = dlhdl.Target('Xilinx', 'Interface', 'JTAG');
Create Workflow Object
Create an object of the dlhdl.Workflow
class. When you create the class, an instance of the dlquantizer object, the bitstream name, and the target information are specified. Specify dlQuantObj
as the network. Make sure that the bitstream name matches the data type and the FPGA board that you are targeting. In this example, the target FPGA board is the Xilinx ZCU102 SOC board and the bitstream uses the int8 data type.
hW = dlhdl.Workflow('Network', dlQuantObj, 'Bitstream', 'zcu102_int8','Target',hTarget);
Compile the Quantized DAGNetwork
To compile the quantized ResNet-18 DAG network, run the compile function of the dlhdl.Workflow
object.
dn = hW.compile
### Compiling network for Deep Learning FPGA prototyping ... ### Targeting FPGA bitstream zcu102_int8. ### The network includes the following layers: 1 'data' Image Input 224×224×3 images with 'zscore' normalization (SW Layer) 2 'conv1' Convolution 64 7×7×3 convolutions with stride [2 2] and padding [3 3 3 3] (HW Layer) 3 'bn_conv1' Batch Normalization Batch normalization with 64 channels (HW Layer) 4 'conv1_relu' ReLU ReLU (HW Layer) 5 'pool1' Max Pooling 3×3 max pooling with stride [2 2] and padding [1 1 1 1] (HW Layer) 6 'res2a_branch2a' Convolution 64 3×3×64 convolutions with stride [1 1] and padding [1 1 1 1] (HW Layer) 7 'bn2a_branch2a' Batch Normalization Batch normalization with 64 channels (HW Layer) 8 'res2a_branch2a_relu' ReLU ReLU (HW Layer) 9 'res2a_branch2b' Convolution 64 3×3×64 convolutions with stride [1 1] and padding [1 1 1 1] (HW Layer) 10 'bn2a_branch2b' Batch Normalization Batch normalization with 64 channels (HW Layer) 11 'res2a' Addition Element-wise addition of 2 inputs (HW Layer) 12 'res2a_relu' ReLU ReLU (HW Layer) 13 'res2b_branch2a' Convolution 64 3×3×64 convolutions with stride [1 1] and padding [1 1 1 1] (HW Layer) 14 'bn2b_branch2a' Batch Normalization Batch normalization with 64 channels (HW Layer) 15 'res2b_branch2a_relu' ReLU ReLU (HW Layer) 16 'res2b_branch2b' Convolution 64 3×3×64 convolutions with stride [1 1] and padding [1 1 1 1] (HW Layer) 17 'bn2b_branch2b' Batch Normalization Batch normalization with 64 channels (HW Layer) 18 'res2b' Addition Element-wise addition of 2 inputs (HW Layer) 19 'res2b_relu' ReLU ReLU (HW Layer) 20 'res3a_branch2a' Convolution 128 3×3×64 convolutions with stride [2 2] and padding [1 1 1 1] (HW Layer) 21 'bn3a_branch2a' Batch Normalization Batch normalization with 128 channels (HW Layer) 22 'res3a_branch2a_relu' ReLU ReLU (HW Layer) 23 'res3a_branch2b' Convolution 128 3×3×128 convolutions with stride [1 1] and padding [1 1 1 1] (HW Layer) 24 'bn3a_branch2b' Batch Normalization Batch normalization with 128 channels (HW Layer) 25 'res3a' Addition Element-wise addition of 2 inputs (HW Layer) 26 'res3a_relu' ReLU ReLU (HW Layer) 27 'res3a_branch1' Convolution 128 1×1×64 convolutions with stride [2 2] and padding [0 0 0 0] (HW Layer) 28 'bn3a_branch1' Batch Normalization Batch normalization with 128 channels (HW Layer) 29 'res3b_branch2a' Convolution 128 3×3×128 convolutions with stride [1 1] and padding [1 1 1 1] (HW Layer) 30 'bn3b_branch2a' Batch Normalization Batch normalization with 128 channels (HW Layer) 31 'res3b_branch2a_relu' ReLU ReLU (HW Layer) 32 'res3b_branch2b' Convolution 128 3×3×128 convolutions with stride [1 1] and padding [1 1 1 1] (HW Layer) 33 'bn3b_branch2b' Batch Normalization Batch normalization with 128 channels (HW Layer) 34 'res3b' Addition Element-wise addition of 2 inputs (HW Layer) 35 'res3b_relu' ReLU ReLU (HW Layer) 36 'res4a_branch2a' Convolution 256 3×3×128 convolutions with stride [2 2] and padding [1 1 1 1] (HW Layer) 37 'bn4a_branch2a' Batch Normalization Batch normalization with 256 channels (HW Layer) 38 'res4a_branch2a_relu' ReLU ReLU (HW Layer) 39 'res4a_branch2b' Convolution 256 3×3×256 convolutions with stride [1 1] and padding [1 1 1 1] (HW Layer) 40 'bn4a_branch2b' Batch Normalization Batch normalization with 256 channels (HW Layer) 41 'res4a' Addition Element-wise addition of 2 inputs (HW Layer) 42 'res4a_relu' ReLU ReLU (HW Layer) 43 'res4a_branch1' Convolution 256 1×1×128 convolutions with stride [2 2] and padding [0 0 0 0] (HW Layer) 44 'bn4a_branch1' Batch Normalization Batch normalization with 256 channels (HW Layer) 45 'res4b_branch2a' Convolution 256 3×3×256 convolutions with stride [1 1] and padding [1 1 1 1] (HW Layer) 46 'bn4b_branch2a' Batch Normalization Batch normalization with 256 channels (HW Layer) 47 'res4b_branch2a_relu' ReLU ReLU (HW Layer) 48 'res4b_branch2b' Convolution 256 3×3×256 convolutions with stride [1 1] and padding [1 1 1 1] (HW Layer) 49 'bn4b_branch2b' Batch Normalization Batch normalization with 256 channels (HW Layer) 50 'res4b' Addition Element-wise addition of 2 inputs (HW Layer) 51 'res4b_relu' ReLU ReLU (HW Layer) 52 'res5a_branch2a' Convolution 512 3×3×256 convolutions with stride [2 2] and padding [1 1 1 1] (HW Layer) 53 'bn5a_branch2a' Batch Normalization Batch normalization with 512 channels (HW Layer) 54 'res5a_branch2a_relu' ReLU ReLU (HW Layer) 55 'res5a_branch2b' Convolution 512 3×3×512 convolutions with stride [1 1] and padding [1 1 1 1] (HW Layer) 56 'bn5a_branch2b' Batch Normalization Batch normalization with 512 channels (HW Layer) 57 'res5a' Addition Element-wise addition of 2 inputs (HW Layer) 58 'res5a_relu' ReLU ReLU (HW Layer) 59 'res5a_branch1' Convolution 512 1×1×256 convolutions with stride [2 2] and padding [0 0 0 0] (HW Layer) 60 'bn5a_branch1' Batch Normalization Batch normalization with 512 channels (HW Layer) 61 'res5b_branch2a' Convolution 512 3×3×512 convolutions with stride [1 1] and padding [1 1 1 1] (HW Layer) 62 'bn5b_branch2a' Batch Normalization Batch normalization with 512 channels (HW Layer) 63 'res5b_branch2a_relu' ReLU ReLU (HW Layer) 64 'res5b_branch2b' Convolution 512 3×3×512 convolutions with stride [1 1] and padding [1 1 1 1] (HW Layer) 65 'bn5b_branch2b' Batch Normalization Batch normalization with 512 channels (HW Layer) 66 'res5b' Addition Element-wise addition of 2 inputs (HW Layer) 67 'res5b_relu' ReLU ReLU (HW Layer) 68 'pool5' 2-D Global Average Pooling 2-D global average pooling (HW Layer) 69 'newFC' Fully Connected 32 fully connected layer (HW Layer) 70 'newProb' Softmax softmax (HW Layer) 71 'newClassOutput' Classification Output crossentropyex with 'adidas' and 31 other classes (SW Layer) ### Optimizing network: Fused 'nnet.cnn.layer.BatchNormalizationLayer' into 'nnet.cnn.layer.Convolution2DLayer' ### Notice: The layer 'data' with type 'nnet.cnn.layer.ImageInputLayer' is implemented in software. ### Notice: The layer 'newProb' with type 'nnet.cnn.layer.SoftmaxLayer' is implemented in software. ### Notice: The layer 'newClassOutput' with type 'nnet.cnn.layer.ClassificationOutputLayer' is implemented in software. ### Compiling layer group: conv1>>pool1 ... ### Compiling layer group: conv1>>pool1 ... complete. ### Compiling layer group: res2a_branch2a>>res2a_branch2b ... ### Compiling layer group: res2a_branch2a>>res2a_branch2b ... complete. ### Compiling layer group: res2b_branch2a>>res2b_branch2b ... ### Compiling layer group: res2b_branch2a>>res2b_branch2b ... complete. ### Compiling layer group: res3a_branch1 ... ### Compiling layer group: res3a_branch1 ... complete. ### Compiling layer group: res3a_branch2a>>res3a_branch2b ... ### Compiling layer group: res3a_branch2a>>res3a_branch2b ... complete. ### Compiling layer group: res3b_branch2a>>res3b_branch2b ... ### Compiling layer group: res3b_branch2a>>res3b_branch2b ... complete. ### Compiling layer group: res4a_branch1 ... ### Compiling layer group: res4a_branch1 ... complete. ### Compiling layer group: res4a_branch2a>>res4a_branch2b ... ### Compiling layer group: res4a_branch2a>>res4a_branch2b ... complete. ### Compiling layer group: res4b_branch2a>>res4b_branch2b ... ### Compiling layer group: res4b_branch2a>>res4b_branch2b ... complete. ### Compiling layer group: res5a_branch1 ... ### Compiling layer group: res5a_branch1 ... complete. ### Compiling layer group: res5a_branch2a>>res5a_branch2b ... ### Compiling layer group: res5a_branch2a>>res5a_branch2b ... complete. ### Compiling layer group: res5b_branch2a>>res5b_branch2b ... ### Compiling layer group: res5b_branch2a>>res5b_branch2b ... complete. ### Compiling layer group: pool5 ... ### Compiling layer group: pool5 ... complete. ### Compiling layer group: newFC ... ### Compiling layer group: newFC ... complete. ### Allocating external memory buffers: offset_name offset_address allocated_space _______________________ ______________ ________________ "InputDataOffset" "0x00000000" "12.0 MB" "OutputResultOffset" "0x00c00000" "4.0 MB" "SchedulerDataOffset" "0x01000000" "4.0 MB" "SystemBufferOffset" "0x01400000" "28.0 MB" "InstructionDataOffset" "0x03000000" "4.0 MB" "ConvWeightDataOffset" "0x03400000" "16.0 MB" "FCWeightDataOffset" "0x04400000" "4.0 MB" "EndOffset" "0x04800000" "Total: 72.0 MB" ### Network compilation complete.
dn = struct with fields:
weights: [1×1 struct]
instructions: [1×1 struct]
registers: [1×1 struct]
syncInstructions: [1×1 struct]
constantData: {}
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, displays progress messages, and the time it takes to deploy the network.
hW.deploy
### FPGA bitstream programming has been skipped as the same bitstream is already loaded on the target FPGA. ### Loading weights to Conv Processor. ### Conv Weights loaded. Current time is 09-Dec-2021 18:36:39 ### Loading weights to FC Processor. ### FC Weights loaded. Current time is 09-Dec-2021 18:36:39
Load Example Images and Run the Prediction
To load the example image, execute the predict
function of the dlhdl.Workflow
object, and then display the FPGA result, enter:
idx = randperm(numel(imdsValidation.Files),4); figure for i = 1:4 subplot(2,2,i) I = readimage(imdsValidation,idx(i)); I = imresize(I,[224 224]); imshow(I) [prediction, speed] = hW.predict(single(I),'Profile','on'); [val, index] = max(prediction); netTransfer.Layers(end).ClassNames{index} label = netTransfer.Layers(end).ClassNames{index} title(string(label)); end
### Finished writing input activations. ### Running single input activation. Deep Learning Processor Profiler Performance Results LastFrameLatency(cycles) LastFrameLatency(seconds) FramesNum Total Latency Frames/s ------------- ------------- --------- --------- --------- Network 7335952 0.02934 1 7338581 34.1 conv1 1115480 0.00446 pool1 238029 0.00095 res2a_branch2a 269834 0.00108 res2a_branch2b 269956 0.00108 res2a 88905 0.00036 res2b_branch2a 269794 0.00108 res2b_branch2b 269965 0.00108 res2b 88783 0.00036 res3a_branch1 156139 0.00062 res3a_branch2a 227324 0.00091 res3a_branch2b 245055 0.00098 res3a 44462 0.00018 res3b_branch2a 244852 0.00098 res3b_branch2b 245048 0.00098 res3b 44426 0.00018 res4a_branch1 135525 0.00054 res4a_branch2a 136187 0.00054 res4a_branch2b 237212 0.00095 res4a 22312 0.00009 res4b_branch2a 236600 0.00095 res4b_branch2b 237466 0.00095 res4b 22542 0.00009 res5a_branch1 311891 0.00125 res5a_branch2a 311873 0.00125 res5a_branch2b 596194 0.00238 res5a 11201 0.00004 res5b_branch2a 595857 0.00238 res5b_branch2b 596713 0.00239 res5b 11431 0.00005 pool5 36976 0.00015 newFC 17733 0.00007 * The clock frequency of the DL processor is: 250MHz
ans = 'becks'
label = 'becks'
### Finished writing input activations. ### Running single input activation. Deep Learning Processor Profiler Performance Results LastFrameLatency(cycles) LastFrameLatency(seconds) FramesNum Total Latency Frames/s ------------- ------------- --------- --------- --------- Network 7336472 0.02935 1 7339005 34.1 conv1 1115736 0.00446 pool1 237938 0.00095 res2a_branch2a 269787 0.00108 res2a_branch2b 270062 0.00108 res2a 88865 0.00036 res2b_branch2a 269710 0.00108 res2b_branch2b 269870 0.00108 res2b 88975 0.00036 res3a_branch1 156178 0.00062 res3a_branch2a 227565 0.00091 res3a_branch2b 245130 0.00098 res3a 44486 0.00018 res3b_branch2a 244733 0.00098 res3b_branch2b 244875 0.00098 res3b 44486 0.00018 res4a_branch1 135725 0.00054 res4a_branch2a 136247 0.00054 res4a_branch2b 236972 0.00095 res4a 22382 0.00009 res4b_branch2a 236891 0.00095 res4b_branch2b 237046 0.00095 res4b 22402 0.00009 res5a_branch1 312061 0.00125 res5a_branch2a 311738 0.00125 res5a_branch2b 596238 0.00238 res5a 11261 0.00005 res5b_branch2a 595867 0.00238 res5b_branch2b 596768 0.00239 res5b 11351 0.00005 pool5 36999 0.00015 newFC 17941 0.00007 * The clock frequency of the DL processor is: 250MHz
ans = 'nvidia'
label = 'nvidia'
### Finished writing input activations. ### Running single input activation. Deep Learning Processor Profiler Performance Results LastFrameLatency(cycles) LastFrameLatency(seconds) FramesNum Total Latency Frames/s ------------- ------------- --------- --------- --------- Network 7335649 0.02934 1 7338257 34.1 conv1 1115615 0.00446 pool1 237521 0.00095 res2a_branch2a 269761 0.00108 res2a_branch2b 270039 0.00108 res2a 88844 0.00036 res2b_branch2a 269603 0.00108 res2b_branch2b 269901 0.00108 res2b 88855 0.00036 res3a_branch1 156360 0.00063 res3a_branch2a 227646 0.00091 res3a_branch2b 245061 0.00098 res3a 44526 0.00018 res3b_branch2a 244836 0.00098 res3b_branch2b 244944 0.00098 res3b 44566 0.00018 res4a_branch1 135820 0.00054 res4a_branch2a 136251 0.00055 res4a_branch2b 236828 0.00095 res4a 22352 0.00009 res4b_branch2a 237023 0.00095 res4b_branch2b 236932 0.00095 res4b 22392 0.00009 res5a_branch1 311901 0.00125 res5a_branch2a 311751 0.00125 res5a_branch2b 596252 0.00239 res5a 11281 0.00005 res5b_branch2a 595829 0.00238 res5b_branch2b 596743 0.00239 res5b 11249 0.00004 pool5 36913 0.00015 newFC 17867 0.00007 * The clock frequency of the DL processor is: 250MHz
ans = 'google'
label = 'google'
### Finished writing input activations. ### Running single input activation. Deep Learning Processor Profiler Performance Results LastFrameLatency(cycles) LastFrameLatency(seconds) FramesNum Total Latency Frames/s ------------- ------------- --------- --------- --------- Network 7336269 0.02935 1 7338849 34.1 conv1 1115457 0.00446 pool1 238045 0.00095 res2a_branch2a 269786 0.00108 res2a_branch2b 269928 0.00108 res2a 88895 0.00036 res2b_branch2a 269765 0.00108 res2b_branch2b 269928 0.00108 res2b 88825 0.00036 res3a_branch1 156232 0.00062 res3a_branch2a 227320 0.00091 res3a_branch2b 245058 0.00098 res3a 44493 0.00018 res3b_branch2a 244799 0.00098 res3b_branch2b 245040 0.00098 res3b 44456 0.00018 res4a_branch1 135640 0.00054 res4a_branch2a 136131 0.00054 res4a_branch2b 237165 0.00095 res4a 22312 0.00009 res4b_branch2a 236583 0.00095 res4b_branch2b 237521 0.00095 res4b 22512 0.00009 res5a_branch1 311839 0.00125 res5a_branch2a 311902 0.00125 res5a_branch2b 596212 0.00238 res5a 11211 0.00004 res5b_branch2a 595898 0.00238 res5b_branch2b 596808 0.00239 res5b 11381 0.00005 pool5 36989 0.00015 newFC 17951 0.00007 * The clock frequency of the DL processor is: 250MHz
ans = 'shell'
label = 'shell'