42028 Faculty 容错

42028: Assignment 2 – Autumn 2019 Page 1 of 4
Faculty of Engineering and Information Technology
School of Software
42028: Deep Learning and Convolutional Neural Networks
Autumn 2019
ASSIGNMENT-2 SPECIFICATION
Due date Friday 11:59pm, 31 May 2019
Demonstrations Optional, If required.
Marks 40% of the total marks for this subject
Submission 1. A report in PDF or MS Word document (10-pages)

1. Google Colab/iPython notebooks
   Submit to UTS Online assignment submission
   Note: This assignment is individual work.
   Summary
   This assessment requires you to customize the standard CNN architectures for
   image classification. Standard CNNs such as AlexNet, GoogleNet, ResNet should be
   used to create customized version of the architectures. Students are also required
   to implement a custom CNN architecture for object detection and localization.
   Both the customized CNNs (image classification and object detection) should be
   trained and tested using the dataset provided.
   Students need to provide the code (ipython Notebook) and a final report for the
   assignment, which will outline a brief assumptions/intuitions considered to create
   the customized CNNs and discuss the performance.
   Assignment Objectives
   The purpose of this assignment is to demonstrate competence in the following
   skills.
   To ensure that the student has a firm understanding of CNNs and object
   detections algorithms. This will facilitate the learning of advanced topics for
   research and also assist in completing the project.
   To ensure that the student can develop custom CNN architectures for different
   computer vision related tasks.
   42028: Assignment 2 – Autumn 2019 Page 2 of 4
   Tasks:
   Description:
2. Customize AlexNet/GoogleNet/ResNet and reduce/increase the layers. Train
   and test on image classification.
3. Implement a custom CNN architecture for object detection and localization.
4. Train and test the custom architecture on a given dataset for detection of
   multiple Objects, using Faster RCNN or YOLO object detection methods.
   Training, validation and testing datasets will be provided.
   Write a short report on the implementation, linking the concepts and methods
   learned in class, and also provide assumptions/intuitions considered to create the
   custom CNNs. Provide diagrams for the CNNs architecture where required for
   better illustrations. Provide the model summary, such as input and output
   parameters, etc. Discuss the results clearly and explain the different
   situations/constraints for the better understanding of the results obtained.
   Dataset to be used: Provided separately.
   Report Structure (suggestion only):
   The report may include the following sections:
5. Introduction: Provide a brief outline of the report and also briefly explain
   the baseline CNN architectures used to create the custom CNNs for image
   classification and object detection.
6. Dataset: Provide a brief description of the dataset used with some sample
   images of each class.
7. Proposed CNN architecture for Image classification:
   a. Baseline architecture used.
   b. Customized architecture
   c. Assumptions/intuitions
   d. Model summary
8. Proposed CNN architecture for Object Detection and localization:
   a. Baseline architecture used.
   b. Customized architecture
   c. Assumptions/intuitions
   d. Model summary
9. Experimental results and discussion:
   a. Experimental settings:
   i. Image classification
   ii. Object detection
   b. Experimental Results:
   i. Image classification
   ii. Object detection
   iii. Discussion: Provide your understanding of the performance
   and accuracy obtained. You may also include some image
   samples which were wrongly classified.
   42028: Assignment 2 – Autumn 2019 Page 3 of 4
10. Conclusion: Provide a short paragraph detailing your understanding of the
    experiments and results.
    Deliverables:
11. Project Report (10 pages max)
12. Google Colab or Ipython notebook, with the code
    Additional Information:
    Assessment Submission
    Submission of your assignment is in two parts. You must upload a zip file of the
    Ipython/Colab notebooks and Report to UTS Online. This must be done by the Due
    Date. You may submit as many times as you like until the due date. The final
    submission you make is the one that will be marked. If you have not uploaded your zip
    file within 7 days of the Due Date, or it cannot be run in the lab, then your assignment
    will receive a zeromark. Additionally, the result achieved and shown in the
    ipython/Colab notebooks should match the report. Penalties apply if there are
    inconsistencies in the experimental results and the report.
    PLEASE NOTE 1: It is your responsibility to make sure you have thoroughly tested your
    program to make sure it is working correctly.
    PLEASE NOTE 2: Your final submission to UTS Online is the one that is marked. It does
    not matter if earlier submissions were working; they will be ignored. Download your
    submission from UTS Online and test it thoroughly in your assigned laboratory.
    Return of Assessed Assignment
    It is expected that marks will be made available 2 weeks after the submission via UTS
    Online. You will be given a copy of the marking sheet showing a breakdown of the marks.
    Queries
    If you have a problem such as illness which will affect your assignment submission
    contact the subject coordinator as soon as possible.
    Dr. Nabin Sharma
    Room: CB11.07.124
    Phone: 9514 1835
    Email: Nabin.S[email protected]
    If you have a question about the assignment, please post it to the UTS Online forum
    for this subject so that everyone can see the response.
    If serious problems are discovered the class will be informed via an announcement on UTS
    Online. It is your responsibility to make sure you frequently check UTS Online.
    42028: Assignment 2 – Autumn 2019 Page 4 of 4
    PLEASE NOTE: If the answer to your questions can be found directly in any of the
    following
    Subject outline
    Assignmentspecification
    UTS Online FAQ
    UTS Online discussion board
    You will be directed to these locations rather than given a direct answer.
    Extensions and Special Consideration
    In alignment with Faculty policies, assignments that are submitted after the Due Date
    will lose 10% of the received grade for each day, or part thereof, that the assignment
    is late. Assignments will not be accepted after 5 days after the Due Date.
    When, due to extenuating circumstances, you are unable to submit or present an
    assessment task on time, please contact your subject coordinator before the
    assessment task is due to discuss an extension. Extensions may be granted up to a
    maximum of 5 days (120 hours). In all cases, you should have extensions confirmed in
    writing.
    If you believe your performance in an assessment item or exam has been adversely
    affected by circumstances beyond your control, such as a serious illness, loss or
    bereavement, hardship, trauma, or exceptional employment demands, you may be
    eligible to apply for Special Consideration (https://www.uts.edu.au/curren...).
    Academic Standards and Late Penalties
    Please refer to subject outline.
    WX：codehelp