emuccino

emuccino

import matplotlib.pyplot as plt

def show_image_compression(samples):
    #get encoded samples offloaded to edge
    _, offload_end = device_models['end'].predict(samples)
    #get encoded samples offloaded to cloud
    _, offload_edge = device_models['edge'].predict(offload_end)
    #show sample represenations at each device level
    for i in range(len(samples)):
        print(i)

emuccino

import numpy as np
from scipy.special import softmax

def get_results(confidence_threshold):
    print('confidence threshold:',confidence_threshold)
    
    predictions = []
    confidence = []
    exit_level = []
    

emuccino

from tensorflow.keras.callbacks import EarlyStopping

early_stop = EarlyStopping(
    monitor='val_loss', min_delta=0, patience=5, verbose=0, mode='auto',
    baseline=None, restore_best_weights=True)

model.fit(x_train, {device:y_train for device in device_names},
          batch_size=64,
          epochs=1000,
          verbose=1,

emuccino

outputs = {}

#complete model input
inputs = Input(shape=x_train.shape[1:])
net = {'offload':inputs}

#stack all 3 device models together
for device in device_names:    
    net = device_models[device](net['offload'])
    outputs[device] = net[device+'_outputs']

emuccino

from tensorflow.keras.models import Model
from tensorflow.keras.layers import Input, Conv2D, Dense, GlobalAvgPool2D, GlobalMaxPool2D, Concatenate, BatchNormalization
from tensorflow.keras.losses import SparseCategoricalCrossentropy

#function compiling device model
def compile_device_model(input_shape=None,n_filters=None,name=None,offload=False):
    outputs = {}
    
    inputs = Input(shape=input_shape)
    net = inputs

emuccino

from tensorflow.keras.datasets import mnist

#load mnist data
(x_train,y_train),(x_test,y_test) = mnist.load_data()

#reshape and scale input image data
x_train, x_test = (x.reshape(*x.shape,1)/x.max() for x in (x_train,x_test))

emuccino

#function for building classifier (very similar to the discriminator)
def compile_classifier():
    
    inputs = {}
    
    numeric_nets = []
    string_nets = []

    for name in numeric_data:
        numeric_input = Input(shape=(1,),name=name)

emuccino

import itertools
import matplotlib.pyplot as plt

def train_gan(n_epochs,n_batch,n_plot,n_eval):
    
    #discriminator/generator training logs
    disc_loss_hist = []
    gen_loss_hist = []

    for epoch in range(n_epochs):

emuccino

from tensorflow.keras.utils import to_categorical   

#function for generating latent samples for synthetic data for generator training
def generate_latent_samples(n):
    
    #generate latent vectors with balanced targets
    x = {'latent': np.random.normal(size=(n, latent_dim)),
         'target': to_categorical(np.hstack([np.array([_x for _ in range(n//2)]) for _x in range(2)]),2)}
    
    #outputs indicating postive discirmination (target value)