In a past university project my teammates and I were researching which parts of a face are the most discriminative for a convolutional neural network to classify emotions. For that we trained several facial emotion recognition models with TensorFlow on two databases: FER+ and RAF-DB. The final model architecture as…
Comments closedTag: Tensorflow
A method to visualize internal representations of a convolutional neural network and perform object localization without bounding box annotations. For a university project we investigated the question of where a deep convolutional neural network (CNN) looks, when classifying emotions. For this purpose, we evaluated three visualization methods for CNNs, one…
Comments closed
When training an object detection model, you have surely stumbled across the Intersection over Union, in short IoU. In this short post, I will explain what it is and how to implement it in native Python. Furthermore, I will describe the implementation in Tensorflow using vector operations, so that it…
Comments closedSimple object localization and classification using a convolutional neural network build with Tensorflow/Keras in Python. In my previous post I wrote about a simple object localization problem: predicting the bounding box of a single rectangle on neutral background. However, this approach was limited to a single shape and could not…
Comments closedSimple introduction to object localization using a convolutional neural network build with Tensorflow/Keras in Python. In the past days I worked myself into object detection with neural networks. For simplicity, I decided to start with a simple task: predict the bounding box of one single rectangle on a neutral background.…
Comments closed