Skip to content

Latest commit

 

History

History
338 lines (191 loc) · 9.03 KB

File metadata and controls

338 lines (191 loc) · 9.03 KB

Timelog

  • Investigating the Ability of CNNs to Count Visual Concepts
  • Fergus Steel
  • 2542391s
  • Dr. Paul Siebert

Guidance

  • This file contains the time log for your project. It will be submitted along with your final dissertation.
  • YOU MUST KEEP THIS UP TO DATE AND UNDER VERSION CONTROL.
  • This timelog should be filled out honestly, regularly (daily) and accurately. It is for your benefit.
  • Follow the structure provided, grouping time by weeks. Quantise time to the half hour.

Week 1

15 Sep 2023

  • 0.5 hours, made initial contact with supervisor.

16 Sep 2023

  • 1 hour Set up version control system, and customised template.
  • 1 hour Created meeting minutes template, and planned for meeting01 with supervisor.
  • 0.5 hour Filled out the "summer" document.

18 Sep 2023

  • 1 hour Finished "Counting and locating high-density objects using convolutional neural networks" and continued to develop ideas and plan for meeting.
  • 0.5 hours Researched relevant architectures (R-CNN, Fast R-CNN, YOLO)
  • 0.5 hours Read the RetinaNet paper and made notes.
  • 1.5 hours Read the survey of crowd counting techniques paper.

19 Sep 2023

  • 1 hour Read the DPSB paper + notes

21 Sep 2023

  • 2 hour Initial Meeting with Paul, Introductions and Advice.

22 Sep 2023

  • 0.5 hours Read Feature Pyramid Network Paper to develop understanding of feature extractors.
  • 2 hour Panoptic Segmentation Research, OneFormer, Mask2Former, K-Net and LPSNet investigations began reading papers.
  • 0.5 hours Began considering focussing on Attention Mechanisms and the role they may be able to perform?
  • 1 hour Attempting to install tf-models-official for the purpose of demonstration of models but encountered dependency clashes and had to reinstall several times, should really be using a virtual environment...

23 Sep 2023

  • 0.5 hours Initial plan for Semester 1

Week 2

24 Sep 2023

25 Sep 2023

  • 0.5 hours Read NARX paper (Lin et al. 1996)
  • 0.5 hours Read CNN-NARX paper (Jalal et al. 2019)
  • 1 hours Read MIST-RNN paper, did further NARX research.
  • 0.5 hours further temporal feature research (ConvLSTM);

26 Sep 2023

  • 2 hours Tried to fix NVIDIA Graphics Drivers on laptop (failure)
  • 1 hour drafted research direction ideas.

27 Sep 2023

  • 3 hours Reading existing Spatio-Temporal papers, understanding techniques used.

28 Sep 2023

  • 1.5 hours Further NARX reserach, read predicting Chaotic Time Series which goes into muhc more detail on the artchitectures of NARX networks
  • 0.5 hours Meeting 2 Prep
  • 2 hours Supervisor Meeting 2

30 Sep 2023

  • 1.16 hour Watched Geoffrey Hinton's "What is wrong with convoultional neural nets?"

Week 3

2 Oct 2023

  • 4 hours Spent all day researching then implementing a demonstration before I bricked my laptop and lost all progress from this day

3 Oct 2023

  • 0.5 hours watched Capsule networks - A survey by Dr. Yogesh Rawat, UCF
  • 3 hours Few-shot / Zero Shot Object counting research. - can we use capsule networks in exempler inspection?

4 Oct 2023

  • 1 hour further Zero Shot Research
  • 2 hours read more current literature on FSC (general class agnostic counting research)

5 Oct 2023

  • 1 hour Planning for meeting 3

6 Oct 2023

  • 2 hours planning and research for meeting 3
  • 2.5 hours Third Supervisor meeting

Week 4

9 Oct 2023

  • 0.5 hours Wrote up meeting minutes for third supervisor meeting.

10 Oct 2023

  • 1.5 hours Read some more Class Agnostic Counting papers thanks to connected papers graph
  • 1.5 hours Read some more Capsule Network papers and discovered crowding problem.

11 Oct 2023

  • 1 hour Started proposal

12 Oct 2023

  • 1 hour Meeting 4 Preperation

13 Oct 2023

  • 2 hours Meeting 4
  • 1 hour further proposal work

15 Oct 2023

  • 0.5 hours writing up meeting 4 notes
  • 1 hour finishing proposal.md document
  • 0.5 hour Read Joseph William's writing style essay before dissertation writing.

Week 5

16 Oct 2023

  • 1 hour draft reserach questions and collect opinions
  • 0.5 hours start to draft experimental plan (Hypothesis and Method)
  • 0.5 hours Revisited FSC Objecting Counting Research (You et al. (2022))
  • 1 hour Dissertation outline (Headings and further planning)

17 Oct 2023

  • 1 hour Research Design Writing
  • 1 hour fixing bibtex, begun writing dissertation

18 Oct 2023

  • 1 hour dataset decisions + alt. plan
  • 1 hours adapting proposal into dissertation (unfinsihed)

19 Oct 2023

20 Oct 2023

  • 0.75 hours slides for meeting 5
  • 2.5 hours Meeting 5

Week 6

23 Oct 2023

  • 2 hours Dataset Planning + Demo Implementation Start

24 Oct 2023

  • 3 hours Demo Dataset Generator Almost Completed

25 Oct 2023

  • 2 hours Finished Dataset Generator - could still add rotation and some usability features but needs to be adapted to python files anyway
  • 0.5 hours read Matrix Capsuyle Em routing appaer
  • 1 hour "Counting" reserach, reading about counting in organisms.

26 Oct 2023

  • 1 hour Meeting 6 Prep, planning pilot study.

27 Oct 2023

  • 0.5 hours Meeting 6 Prep

Week 7

1 Nov 2023

  • 2 hours Conversion to .npy files (this is a failure, because I used wrong data type and need to cast it to a smaller datatype and ensure that it stays as fine grained as I need it to)

2 Nov 2023

  • 1 hour began coding pilot study, using CNNs in order to counter and contrast.

3 Nov 2023

  • 2.5 hours Meeting 7

Week 8

6 Nov 2023

  • 2 hours pilot study coding, data preprocessing and initial model design

9 Nov 2023

  • 4 hours Remade pilot study, using UNET architecutre

Week 9

13 Nov 2023

  • 3 hours Dissertation writing, Capsule Network background

15 Nov 2023

  • 3 hours Pilot training, tweaking, why wont this work!

16 Nov 2023

  • 2 hours Pilot training debugged, its working suuiiiiiii! (now just need to tweak it)

Week 10

20 Nov 2023

  • 3 hours Remaking data set to include segmentation masks rather than gaussians

21 Nov 2023

  • 3 hours Retraining, tweaking, trying to get new mask network working

Week 11

27 Nov 2023

  • 2 hours started on cleaning repository and making code more readable

28 Nov 2023

  • 3 hours Visual system research, mainly dissertation readings

Week 12

  • NO WORK DONE, Exam break

Week 13

11 Dec 2023

  • 5 hours Adapting loss function to incorporate Multiscale Structural Simularity of each density map.

16 Dec 2023

  • 1.5 hours Wrote halfway report, planned out semester 2 work

17 Dec 2023

  • 2 hours Masking research, how to investigate capsule outputs?

Semester 2

Week 1

9 January 2024

  • 2 hours back to school, getting back into gear and figuring out where I am in the project

11 January 2024

  • 3 hours tweaking code to optimise the best-case performance.

Week 2

16 January 2024

  • 1 hour Panicking, trying to fix the "best-case" performance which is really not good enough
  • 3 Hours Making Network Larger and testing if this helps capture more complexity in outputs

Week 3

23 January 2024

  • 1 hour Started working onevalluation metrics, even if its not working I still need somethign to graph

Week 4

29 January 2024

  • 4 hours Added disjoint loss function to stop cautious guess, needs tweaking

31 January 2024

  • 1 hour Testing the effect of increasing model complexity
  • 0.5 hours Bug fixing, kernel size 1 bug

2 February 2024

  • 1 hour quick meeting with Paul to discuss dissertation tips

Week 5

5 February 2024

  • 3 horus Rough draft of introduction
  • 0.5 hours collating background info into background

6 February 2024

  • ALL DAY Reading through previous dissertation attempts of this subject

8 February 2024

  • 2 hours Exploring using simplified version of model for better results
  • 1 Hour Finished off first draft of the skeleton of the dissertation now I have some direction

9 February 2024

  • 1 hour Finally started looking into visualizing capsules (made a python file, barely got started)

Week 6

12 February 2024

  • 1 hour Writing some background on CNN reserach
  • 3 hours Exploring previous version of model, fixing bugs, testing
  • 0.5 Hours Backdating timelog with all the panic that has occured over last 3 weeks