This article discusses different types of normalizations in a Convolutional Neural Network and why Batch Normalization is necessary. There is an experiment that involves random dropping of BatchNorm Layers based on a hyperparameter in an Object Recognition model and validating it across the accuracy.
This article discusses the usage of ReLU in a Convolutional Neural Network. There is also an experiment that involves random dropping of Activation Layers based on a hyperparameter in an Object Recognition model and validating it across the accuracy.
Given a facial image, this can generate 24 different images by altering the race, gender and age of the person.
An attempt to beat DawnBench using modified Resnet9
Modified version of DenseNet architecture to train on tiny-ImageNet dataset.