0 ×

01_​Classify_​images_​using_​InceptionV3

Workflow

KNIME Deep Learning - Classify images using InceptionV3
This workflow performs classification on some sample images using the InceptionV3 deep learning network architecture, trained on ImageNet, via Keras (TensorFlow).
deep learning Keras image classification
KNIME Deep Learning - Classify images using InceptionV3 This workflow performs classification on some sample images using the InceptionV3 deeplearning network architecture, trained on ImageNet, via Keras (TensorFlow).In order to run the example, please make sure you have the following KNIME extensionsinstalled:* KNIME Deep Learning - Keras Integration (Labs)* KNIME Image Processing (Community Contributions Trusted)* KNIME Image Processing - Deep Learning Extension (Community Contributions Trusted)You also need a local Python installation that includes Keras. Please refer to https://www.knime.com/deeplearning#keras for installation recommendations and furtherinformation. Acknowledgements:The enclosed network was originally released by Szegedy et al. [1] underthe Apache License 2.0 (https://github.com/google/inception/blob/master/LICENSE).It was created using keras.applications.inception_v3.InceptionV3 and itsweights were fetched from https://github.com/fchollet/deep-learning-models/releases/download/v0.5/inception_v3_weights_tf_dim_ordering_tf_kernels.h5 [2].The enclosed pictures were modified from Caltech 101 dataset (http://www.vision.caltech.edu/Image_Datasets/Caltech101/Caltech101.html) [3].[1] Christian Szegedy, Vincent Vanhoucke, Sergey Ioffe, Jonathon Shlens,Zbigniew Wojna. Rethinking the Inception Architecture for ComputerVision. arXiv:1512.00567, 2015.[2] Chollet, Francois and others. Keras. https://github.com/fchollet/keras.2015.[3] L. Fei-Fei, R. Fergus and P. Perona. Learning generative visual modelsfrom few training examples: an incremental Bayesian approach tested on101 object categories. IEEE. CVPR 2004, Workshop on Generative-ModelBased Vision. 2004 InceptionV3,pre-trained on ImageNet6 sampleimages......of size299x299x3InceptionV3-specificpreprocessingtransform probabilitiesto predicted classes’ labelsinput: InceptionV3 networkand test imagesoutput: probabilitiesof predicted ImageNet classes Keras NetworkReader List Files Image Reader(Table) Image Viewer Preprocessing Format results DL Network Executor KNIME Deep Learning - Classify images using InceptionV3 This workflow performs classification on some sample images using the InceptionV3 deeplearning network architecture, trained on ImageNet, via Keras (TensorFlow).In order to run the example, please make sure you have the following KNIME extensionsinstalled:* KNIME Deep Learning - Keras Integration (Labs)* KNIME Image Processing (Community Contributions Trusted)* KNIME Image Processing - Deep Learning Extension (Community Contributions Trusted)You also need a local Python installation that includes Keras. Please refer to https://www.knime.com/deeplearning#keras for installation recommendations and furtherinformation. Acknowledgements:The enclosed network was originally released by Szegedy et al. [1] underthe Apache License 2.0 (https://github.com/google/inception/blob/master/LICENSE).It was created using keras.applications.inception_v3.InceptionV3 and itsweights were fetched from https://github.com/fchollet/deep-learning-models/releases/download/v0.5/inception_v3_weights_tf_dim_ordering_tf_kernels.h5 [2].The enclosed pictures were modified from Caltech 101 dataset (http://www.vision.caltech.edu/Image_Datasets/Caltech101/Caltech101.html) [3].[1] Christian Szegedy, Vincent Vanhoucke, Sergey Ioffe, Jonathon Shlens,Zbigniew Wojna. Rethinking the Inception Architecture for ComputerVision. arXiv:1512.00567, 2015.[2] Chollet, Francois and others. Keras. https://github.com/fchollet/keras.2015.[3] L. Fei-Fei, R. Fergus and P. Perona. Learning generative visual modelsfrom few training examples: an incremental Bayesian approach tested on101 object categories. IEEE. CVPR 2004, Workshop on Generative-ModelBased Vision. 2004 InceptionV3,pre-trained on ImageNet6 sampleimages......of size299x299x3InceptionV3-specificpreprocessingtransform probabilitiesto predicted classes’ labelsinput: InceptionV3 networkand test imagesoutput: probabilitiesof predicted ImageNet classes Keras NetworkReader List Files Image Reader(Table) Image Viewer Preprocessing Format results DL Network Executor

Download

Get this workflow from the following link: Download

Nodes

01_​Classify_​images_​using_​InceptionV3 consists of the following 26 nodes(s):

Plugins

01_​Classify_​images_​using_​InceptionV3 contains nodes provided by the following 6 plugin(s):