Traffic-sign-classifier | deep networks | Machine Learning library

Traffic-sign-classifier is a Python library typically used in Artificial Intelligence, Machine Learning, Deep Learning, Tensorflow applications. Traffic-sign-classifier has no bugs, it has no vulnerabilities, it has build file available, it has a Permissive License and it has low support. You can download it from GitHub.

This grid of images is representing one chosen random image from of each class from the training set. Now we are going to explore the distribution and take look at the distribution of classes in the training, validation and test set. From the histograms below, we can clearly see that the distribution of train, validation, and test set is nearly the same, but the problem is that there is a huge variability of the distribution between class instances within the dataset, and we can further investigate whether it can cause some problems during our training, and maybe we can develop augmentation techniques to equalize them. Maximum class labels instances in train data 2010.0 Minimum class labels instances in test data 180.0. Maximum class labels instances in validation data 240.0 Mininum class labels instances in validation data 30.0. Maximum class labels instances in test data 750.0 Minimum class labels instances in test data 60.0.