NAME

RAMINENI,PARDHA SARADHI

CLASS ID

32

i) Import required libraries keras, cifar10, numpy.

ii)Read the cifar10 data.

iii) Now Split the data into train and test.

iv)Change into float type and dividing it by 255 to normalize the data.

v)Change the categorical data to numerical data.

vi)Initialize the deep learning sequential model.

vii)Add below layers to the existing model

Add Conv2D layer is activation: Relu output-shape 64 feature maps with a size of 3×3

Adding dropout layer 0.2

Add Conv2D layer is activation: Relu output-shape 128 feature maps with a size of 3×3

Add MaxPooling2D layer of pool size (2,2)

viii)Flatting the layer

ix)No of neurons in the dense layer is 1024, activation: Relu and dropout of 0.2.

x)No of neurons in the dense layer is 512, activation: Relu and dropout of 0.2

xi)Add a final layer of softmax to generate the predicted outputs.

xii)No of epochs is 2, as per the system configurations constraints. 1.The loss function used is categorical_crossentropy and LR is 0.01, a metric used is accuracy.

xii)Accuracy is 43.35%.