Hands-On Computer Vision with Julia

Preparing the network

We assume that you have successfully run the example from the Predicting an image class using MobileNet v2 section. We will start by loading the network and verifying that the process works, as follows:

using Images, MXNetconst MODEL_NAME = "weights/inception-v3/Inception-7"const MODEL_CLASS_NAMES = "weights/inception-v3/synset.txt"nnet = mx.load_checkpoint(MODEL_NAME, 1, mx.FeedForward);synset = readlines(MODEL_CLASS_NAMES);