Performance optimization tips and best practices

In this section, we will explore a deeper network for improving the performance of the image-classification model. We will look at the results for comparison.

Deeper networks

The code used for experimenting with a deeper network in this section are as follows:

# Model architecture
model <- keras_model_sequential() 
model %>% 
  layer_dense(units = 512, activation = 'relu', input_shape = c(2352)) %>% 
  layer_dropout(rate = 0.1) %>%
  layer_dense(units = 256, activation = 'relu') %>%
  layer_dropout(rate = 0.1) %>%
  layer_dense(units = 3, activation = 'softmax')
summary(model)

OUTPUT
_______________________________________________________________________...