List your company
ResearchFormerly WizWand

Execution time modeling on Nexus 5 profiling Convolutional layer (test)

6.4MAPEDNN
-2.69658.702120.1181.498Sep 19, 2018
Updated 4mo ago

Evaluation results

MethodLinks
DNNHardware=Nexus 5, Layer Type=Convolutional2018.096.416.40.994
DNNArchitecture=four-layer fully connected neural network, Input features=explanatory variable vector x, Device=Nexus 5, Target layer=Convolutional layer2018.096.416.40.994
FastDeepIoTHardware=Nexus 5, Layer Type=Convolutional2018.097.615.20.991
FastDeepIoTModel type=tree-structured linear regression model, Input features=explanatory variable vector x, Device=Nexus 5, Target layer=Convolutional layer2018.097.615.20.991
GBRTHardware=Nexus 5, Layer Type=Convolutional2018.0910.920.50.988
GBRTDescription=gradient boosted regression trees, Input features=explanatory variable vector x, Device=Nexus 5, Target layer=Convolutional layer2018.0910.920.50.988
RFHardware=Nexus 5, Layer Type=Convolutional2018.0919.727.30.985
RFDescription=random forest regression, Input features=explanatory variable vector x, Device=Nexus 5, Target layer=Convolutional layer2018.0919.727.30.985
DTHardware=Nexus 5, Layer Type=Convolutional2018.0923.839.20.969
DTDescription=classification and regression trees, Input features=explanatory variable vector x, Device=Nexus 5, Target layer=Convolutional layer2018.0923.839.20.969
SVRHardware=Nexus 5, Layer Type=Convolutional2018.09233.8227.1-0.229
SVRKernel=radial basis function, Input features=explanatory variable vector x, Device=Nexus 5, Target layer=Convolutional layer2018.09233.8227.1-0.229