Python Deep Learning Projects

Defining hyperparameters

The following are some of the defined hyperparameters that we will be using throughout the code, and they are totally configurable:

# define optimizeroptimizer = Adam(lr=0.002)# input shape to the modelinput_shape=(3, 360, 480)# training batchsizebatch_size = 6# number of training epochsnb_epoch = 60

To learn more about optimizers and their APIs in Keras, visit https://keras.io/optimizers/. Reduce batch_size if you get a resource exhaustion error with respect to the GPU.

Experiment with different learning rates, optimizers, and batch_size to see how these factors affect the quality of your model, and if you get better results, show them to the deep learning community.