Hands-On Convolutional Neural Networks with TensorFlow

Mismatch of the Dev and Test set

In addition to the split of data, distribution of data has huge impact on the performance of a neural network. Most issues in applied deep learning come from the mismatch of the dev and test set data distribution. We need to bear in mind that the dev and test data should be coming from a similar distribution. For example, we will have a distribution mismatch if we collect and split person detection data in a way that training images of people are collected from web pages while test set images are collected using mobile phones. The problem here is that while training a model we finetune the parameters and architecture of a network based on its performance on the dev data, and if the dev data is similar to training ...