TensorFlow based deep learning layer for Local Derivative Patterns
Deep learning architectures can extract features automatically via particular layers such as convolutions, recurrent networks, and pooling operations. In addition to the predefined layers in TensorFlow, developers can implement their custom layers based on the existing operators. This study presents a new library for using the Local Derivative Pattern (LDP) algorithm as a deep learning layer. The LDP layer has no trainable parameters and extracts the local patterns in four directions. The layer’s output provides the features to the following layers separately or combined. The developed library enables integrating LDP into any desired model that works with two-dimensional input data.
Code (1)
Tasks
Deep LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
A TensorFlow implementation of Local Binary Patterns Transform
Feature extraction layers like Local Binary Patterns (LBP) transform can be very useful for improving the accuracy of machine learning and deep learning models depending on the problem type. Direct implementations of suc…
CPUGPU$\mathcal{C}^k$-continuous Spline Approximation with TensorFlow Gradient Descent Optimizers
In this work we present an "out-of-the-box" application of Machine Learning (ML) optimizers for an industrial optimization problem. We introduce a piecewise polynomial model (spline) for fitting of $\mathcal{C}^k$-contin…
Completed Local Derivative Pattern for Rotation Invariant Texture Classification
In this paper, we propose a new texture descriptor, completed local derivative pattern (CLDP). In contrast to completed local binary pattern (CLBP), which involves only local differences at each scale, CLDP encodes the d…
ClassificationTexture ClassificationLocal properties of neural networks through the lens of layer-wise Hessians
We introduce a methodology for analyzing neural networks through the lens of layer-wise Hessian matrices. The local Hessian of each functional block (layer) is defined as the matrix of second derivatives of a scalar func…
Implementing graph neural networks with TensorFlow-Keras
Graph neural networks are a versatile machine learning architecture that received a lot of attention recently. In this technical report, we present an implementation of convolution and pooling layers for TensorFlow-Keras…