With all the parameter-related details discussed, we can start the training with the downloaded script:

python retrain.py 
--bottleneck_dir=./ 
--how_many_training_steps=4000 
--model_dir=./ 
--output_graph=./retrained_graph.pb 
--output_labels=retrained_labels.txt 
--architecture=" mobilenet_v2_1.4_224" 
--image_dir=/Users/karthikeyan/Documents/ /book/Chapter5/images

Based on our processor's capability, as well as the number of images we have, the script might take longer for training. For me, it took more than 10 hours for 50 different car categories containing 10,000 images each. Once the script has completed, we will get the TensorFlow model in its output.