Icon

02_​Classify_​images_​using_​ResNet50

KNIME Deep Learning - Classify images using ResNet50

This workflow performs classification on some sample images using the ResNet50 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 He et al. [1] (https://github.com/KaimingHe/deep-residual-networks) under the MIT license (https://github.com/KaimingHe/deep-residual-networks/blob/master/LICENSE).
It was created using keras.applications.resnet50.ResNet50 and its weights were fetched from https://github.com/fchollet/deep-learning-models/releases/download/v0.2/resnet50_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] Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun. Deep Residual Learning for Image Recognition. arXiv:1512.03385, 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

KNIME Deep Learning - Classify images using ResNet 50 This workflow performs classification on some sample images using theResNet50 deep learning network architecture, trained on ImageNet, viaKeras (TensorFlow). ResNet50,pre-trained on ImageNet6 sampleimages......of size224x224x3ResNet50-specificpreprocessingtransform probabilitiesto predicted classes’ labelsinput: ResNet50 networkand test imagesoutput: probabilitiesof predicted ImageNet classes Keras NetworkReader List Files Image Reader(Table) Image Viewer Preprocessing Format results DL Network Executor(deprecated) KNIME Deep Learning - Classify images using ResNet 50 This workflow performs classification on some sample images using theResNet50 deep learning network architecture, trained on ImageNet, viaKeras (TensorFlow). ResNet50,pre-trained on ImageNet6 sampleimages......of size224x224x3ResNet50-specificpreprocessingtransform probabilitiesto predicted classes’ labelsinput: ResNet50 networkand test imagesoutput: probabilitiesof predicted ImageNet classesKeras NetworkReader List Files Image Reader(Table) Image Viewer Preprocessing Format results DL Network Executor(deprecated)

Nodes

Extensions

Links

Download

To use this workflow in KNIME, download it from the below URL and open it in KNIME:

Download Workflow
Created by: marcel
Created at: 2017-07-11
On NodePit since: 2019-07-12
Last update: 2024-04-16
Created with KNIME version: v4.1.0
Tags: deep learningKerasimage classification

Deploy, schedule, execute, and monitor your KNIME workflows locally, in the cloud or on-premises – with our brand new NodePit Runner.

Try NodePit Runner!