Deprecation Notice: With the introduction of daal4py, a package that supersedes PyDAAL, Intel is deprecating PyDAAL and will discontinue support starting with Intel® DAAL 2021 and Intel® Distribution for Python 2021. Until then Intel will continue to provide compatible pyDAAL pip and conda packages for newer releases of Intel DAAL and make it available in open source. However, Intel will not add the new features of Intel DAAL to pyDAAL. Intel recommends developers switch to and use daal4py.

Note: To find daal4py examples, refer to daal4py documentation or browse github repository.

 # file:
 # Copyright 2014-2019 Intel Corporation.
 # This software and the related documents are Intel copyrighted  materials,  and
 # your use of  them is  governed by the  express license  under which  they were
 # provided to you (License).  Unless the License provides otherwise, you may not
 # use, modify, copy, publish, distribute,  disclose or transmit this software or
 # the related documents without Intel's prior written permission.
 # This software and the related documents  are provided as  is,  with no express
 # or implied  warranties,  other  than those  that are  expressly stated  in the
 # License.
 # !  Content:
 # !    Python example of forward and backward dropout layer usage
 # !
 # !*****************************************************************************
 ## \example
 import os
 import sys
 from daal.algorithms.neural_networks import layers
 from daal.data_management import HomogenTensor, TensorIface
 utils_folder = os.path.realpath(os.path.abspath(os.path.dirname(os.path.dirname(__file__))))
 if utils_folder not in sys.path:
     sys.path.insert(0, utils_folder)
 from utils import printTensor, readTensorFromCSV
 # Input data set parameters
 datasetName = os.path.join("..", "data", "batch", "layer.csv")
 if __name__ == "__main__":
     # Read datasetFileName from a file and create a tensor to store input data
     tensorData = readTensorFromCSV(datasetName)
     # Create an algorithm to compute forward dropout layer results using default method
     dropoutLayerForward = layers.dropout.forward.Batch()
     # Set input objects for the forward dropout layer
     dropoutLayerForward.input.setInput(, tensorData)
     # Compute forward dropout layer results
     forwardResult = dropoutLayerForward.compute()
     printTensor(forwardResult.getResult(layers.forward.value), "Forward dropout layer result (first 5 rows):", 5)
     printTensor(forwardResult.getLayerData(layers.dropout.auxRetainMask), "Dropout layer retain mask (first 5 rows):", 5)
     # Get the size of forward dropout layer output
     gDims = forwardResult.getResult(layers.forward.value).getDimensions()
     tensorDataBack = HomogenTensor(gDims, TensorIface.doAllocate, 0.01)
     # Create an algorithm to compute backward dropout layer results using default method
     dropoutLayerBackward = layers.dropout.backward.Batch()
     # Set input objects for the backward dropout layer
     dropoutLayerBackward.input.setInput(layers.backward.inputGradient, tensorDataBack)
     dropoutLayerBackward.input.setInputLayerData(layers.backward.inputFromForward, forwardResult.getResultLayerData(layers.forward.resultForBackward))
     # Compute backward dropout layer results
     backwardResult = dropoutLayerBackward.compute()
     # Print the results of the backward dropout layer
     printTensor(backwardResult.getResult(layers.backward.gradient), "Backward dropout layer result (first 5 rows):", 5)
Para obter informações mais completas sobre otimizações do compilador, consulte nosso aviso de otimização.
Selecione a cor do botão adesivo: 
Orange (only for download buttons)