ELEG 6183 Deep Learning Python Assignment

[ad_1]

ELEG 6183 Deep Learning Python Assignment

Simple convolution neural network:

Project Title: COVID-19 Recognition on Medical Images via Convolutional Neural Networks (CNN).

Goal: Compare performance differences generated with three CNNs that have different structures.

Detailed steps: 

  • Building three CNNs with the following three different CNN structures on the training set (x_train.npy, y_train.npy)
    • CNN structure 1: CONV1(16, (3*3))-Relu1-Maxpooling1(2*2)-Dropout1(0.25)-CONV2(32, (3*3))-Relu2-Maxpooling2(2*2)-Dropout2(0.25)-Dense(512)-Relu3- Dropout3(0.5)-Output(Softmax)
    • CNN structure 2:

CONV1(16, (3*3))-CONV2(16, (3*3))-Relu1-Maxpooling1(2*2)-Dropout1(0.25)-CONV3(32, (3*3))-Relu2-Maxpooling2(2*2)-Dropout2(0.25)-Dense(512) -Relu3- Dropout3(0.5)-Output(Softmax)

    • CNN structure 3:

CONV1(16, (3*3))-Relu1-Maxpooling1(2*2)-Dropout2(0.25)-CONV2(16, (3*3))-CONV3(32, (3*3))-Relu2-Maxpooling2(2*2)-Dropout2(0.25)-Dense1(512) -Relu3- Dropout3(0.5)-Output(Softmax)

  • Testing these three implemented CNNs on the testing dataset (x_test.npy, y_test.npy), respectively, with the same hyper-parameters: learning rate: 0.0001, epoch: 10.
  • Calculate and compare the training accuracies
  • Calculate and compare the testing accuracies
  • Plot the learning curves for these three CNNs with their losses, respectively, and compare and analyze their differences.

Reference:

  • Load COVID-19 Data: https://docs.scipy.org/doc/numpy/reference/generated/numpy.load.html

Requirements:

    • Submit the source code (.py files) and the data you use for the project, where the codes have no bugs.
    • Write and submit the project report with the following parts:
      • Project description
      • Model description
      • Result analysis
        • Make a table to show the comparison of Precision, Recall, Fscore, Accuracy, and total training time (seconds)
        • Analyze the observations on the comparison, for example, why these observations are obtained.
        • List 3 prediction results
    • Presentation
      • 10 ~ 15 minutes’ presentation with slides (around 15 pages)
      • Slide Outline
        • Project description
        • Model description
        • Result analysis

 

Please submit all required materials (source codes, data, report, and slides) within one package (.zip file) before the due.

ELEG 6183 Deep Learning Python Assignment

Need Help with a similar Assignment?

 

 

The post ELEG 6183 Deep Learning Python Assignment appeared first on EssayPanthers.

[ad_2]

Source link

 
"Looking for a Similar Assignment? Get Expert Help at an Amazing Discount!"

Hi there! Click one of our representatives below and we will get back to you as soon as possible.

Chat with us on WhatsApp