ELEC0134- Assignment Solved

Assignment Description
Datasets
We provide two datasets which are designed specifically for this assignment and contains pre-processed subsets from the following datasets:

1.      CelebFaces Attributes Dataset (CelebA), a celebrity image dataset (S. Yang, P. Luo, C.

C. Loy, and X. Tang, "From facial parts responses to face detection: A Deep Learning

Approach", in IEEE International Conference on Computer Vision (ICCV), 2015)

2.      Cartoon Set, an image dataset of random cartoons/avatars (source: https://google.github.io/cartoonset/).

The datasets you are going to use in this assignment are:

1.      celeba: A sub-set of CelebA dataset. This dataset contains 5000 images. It is going to be used for task A1 and A2.

2.      cartoon_set: A subset of Cartoon Set. This dataset contains 10000 images. It is going to be used for task B1 and B2.

The datasets can be downloaded via following link: https://drive.google.com/file/d/1wGrq9r1fECIIEnNgI8RS-_kPCf8DVv0B/view?usp=sharing A separate test set will be provided one week before the deadline.

Tasks
The machine learning tasks include:

A.       Binary tasks (celeba dataset) 

                   A1:    Gender detection: male or female.

                   A2:    Emotion detection: smiling or not smiling.

B.        Multiclass tasks (cartoon_set dataset) 

                   B1:     Face shape recognition: 5 types of face shapes.

                   B2:    Eye color recognition: 5 types of eye colors.

You should design separate modes for each task and report training errors, validation errors, hyper-parameter tuning. You are allowed to use the same model/methodology for different tasks, but you must explain the reason behind choices. If you tried several models for one task, feel free to show them in your code and compare the results in the report.

Report and Code Format, and Marking Criteria
Report format and template
We provide both latex and MS word templates in AMLS_assignment_kit. The criteria for each part are detailed in the template. For beginners in latex, we recommend overleaf.com, which is a free online latex editor.

Your report should be no longer than 8 pages (including the reference). You are allowed to append an additional supplementation material to your report with no longer than 4 pages.  

Once you finish your report, please export it into a PDF document and name it with the following format (Using your SN number):

Report_AMLS_20-21 _SN12345678.pdf 

Code criteria
You should write your code in modules and organize them in the following fashion:

  

•      Keep ‘Dataset’ folder empty while submitting your code. Use this folder for your programming only. If you need to pre-process the dataset, do not save the intermediate results or pre-processed dataset. Your final submission must directly read the files we provided.  

•      When assessing your code, we will copy-paste the dataset into this folder. Then, your project should look like:

o AMLS_20-21_SN12345678

§  A1

§  A2

§  B1

§  B2

§  Datasets

•      cartoon_set

•      celeba

•      cartoon_set_test

•      celeba_test § main.py

§ README.md

•      The ‘A1’, ‘A2’, ‘B1’ and ‘B2’ folders should contain the code files for each task.

•      Pre-trained models (especially for deep learning models) are allowed to be saved in the folder for each task.

•      The README file should contain:

o a brief description of the organization of your project; o the role of each file; o the packages required to run your code (e.g. numpy, scipy, etc.).

The recommend format for README file is markdown (.md). .txt is acceptable too.

•      We should be able to run your project via ‘main.py’. An example structure of ‘main.py’ has been provided for your reference.

•      You are NOT going to upload your code and dataset to Moodle. Please refer to Submission session for more details.

Marking scheme
The mark will be decided based on both the report and corresponding code. In particular, we will mark based on following scheme:

REPORT 
 
60% 
CORRESPONDING CODE 
40% 
Abstract
 
5%
 
 
Introduction
 
7%
 
 
Literature survey
 
15%
 
 
Description of models (Use flow charts, figures, equations etc. to explain your models and justify your choices)
Task A1
2%
 
 
Task A2
2%
 
 
Task B1
2%
 
 
Task B2
2%
 
 
Implementation (the details of your implementation, explain key modules in your code.)
Task A1
3%
Correct implementation
7%
Task A2
3%
Correct implementation
7%
Task B1
3%
Correct implementation
7%
Task B2
3%
Correct implementation
7%
Experimental Results and Analysis
Task A1
2%
Reasonable results
3%
Task A2
2%
Reasonable results
3%
Task B1
2%
Reasonable results
3%
Task B2
2%
Reasonable results
3%
Conclusion
 
5%
 
 


It should be noted that – whereas we expect students to develop machine learning models delivering reasonable performance on tasks A1, A2, B1 and B2 – the assessment will not be based on the exact performance of the models. Instead, the assessment will predominantly concentrate on how you articulate about the choice of models, how you develop/train/validate these models, and how you report/discuss/analyse the results.