Harald Scheidl·Oct 15, 2024A simple neural network written in plain C++No Python, no PyTorch, no NumPy, … just 260 lines of plain C++ code to train, evaluate and test a simple binary classifier.A response icon3A response icon3
Harald Scheidl·Jul 21, 2022Why pooling layers in deep learning can cause problemsPooling layers are omnipresent in today’s computer vision deep learning models. They reduce the size of the feature maps from layer to…
Harald Scheidl·Aug 9, 2021AdaHessian: a second order optimizer for deep learningMost of the optimizers used in deep learning are (stochastic) gradient descent methods. They only consider the gradient of the loss…A response icon1A response icon1
Harald Scheidl·Mar 24, 2021Does padding matter in deep learning models?The article presents two experiments that show the influence of padding in deep learning models.A response icon1A response icon1
Harald Scheidl·Jan 5, 2019What a text recognition system actually seesSome insights into the neural network “black box” of a text recognition systemA response icon9A response icon9
Harald Scheidl·Oct 29, 2018GPU Image Processing using OpenCLImplementation of two image processing methods in less than 120 lines of code using Python and OpenCL.A response icon2A response icon2
Harald Scheidl·Sep 13, 2018FAQ: Build a Handwritten Text Recognition System using TensorFlowA response icon22A response icon22
Harald Scheidl·Jul 19, 2018Word Beam Search: A CTC Decoding AlgorithmImprove text recognition results: avoid spelling mistakes, allow arbitrary numbers and punctuation marks and make use of a word-level…A response icon14A response icon14
Harald Scheidl·Jul 10, 2018Beam Search Decoding in CTC-trained Neural NetworksA fast and well-performing algorithm with integrated language model to decode the neural network output in the context of text recognitionA response icon8A response icon8