1. Global Average Pooling Layers for Object Localization

    For image classification tasks, a common choice for convolutional neural network (CNN) architecture is repeated blocks of convolution and max pooling layers, followed by two or more densely connected layers. The final dense layer has a softmax activation function and a node for each potential object category. …


  2. Using Transfer Learning to Classify Images with Keras

    In this blog post, I will detail my repository that performs object classification with transfer learning. This blog post is inspired by a Medium post that made use of Tensorflow. The code is written in Keras (version 2.0.2) and Python 3.5. …