This workflow performs classification on some sample images using the InceptionV3 deep learning network architecture, trained on ImageNet, via Keras (TensorFlow). In order to run the example, please make sure you have the following KNIME extensions installed: * 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 further information. Acknowledgements: The enclosed network was originally released by Szegedy et al. [1] under the Apache License 2.0 (https://github.com/google/inception/blob/master/LICENSE). It was created using keras.applications.inception_v3.InceptionV3 and its weights 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 Computer Vision. 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 models from few training examples: an incremental Bayesian approach tested on 101 object categories. IEEE. CVPR 2004, Workshop on Generative-Model Based Vision. 2004
This is a companion discussion topic for the original entry at https://kni.me/w/TP18AZfk5yExkbzy