Complete deep learning assignment 2 - #2
Open
AyeshaAzizProva wants to merge 2 commits into
Open
Conversation
tianyi21
suggested changes
Jul 20, 2026
tianyi21
left a comment
tianyi21
left a comment
There was a problem hiding this comment.
Hi Ayesha Aziz,
Thank you for submitting your DL week 2 assessment. Please find my comments attached to each file. Please re-run the lab4 notebook and include all results in your submission.
Thanks,
Tianyi [LS]
There was a problem hiding this comment.
💬 1. Loading the Fashion-MNIST Dataset: The code cell where you defined the dataset and loader was not executed. Further, the following code cell should display only a batch of (16) images.
✅ A2 complete.
There was a problem hiding this comment.
Owner
Author
|
Okay
…On Mon, Jul 20, 2026 at 4:33 PM Tianyi Liu ***@***.***> wrote:
***@***.**** requested changes on this pull request.
Hi Ayesha Aziz,
Thank you for submitting your DL week 2 assessment. Please find my
comments attached to each file. Please re-run the lab4 notebook and
include all results in your submission.
Thanks,
Tianyi [LS]
------------------------------
On 01_materials/labs/lab_5.ipynb
<#2 (comment)>
:
✅ Lab5 complete.
------------------------------
On 01_materials/labs/lab_6.ipynb
<#2 (comment)>
:
✅ Lab6 complete.
------------------------------
On 02_activities/assignments/assignment_2.ipynb
<#2 (comment)>
:
💬 1. Loading the Fashion-MNIST Dataset: The code cell where you defined
the dataset and loader was not executed. Further, the following code cell
should display only a batch of (16) images.
✅ A2 complete.
------------------------------
On 01_materials/labs/lab_4.ipynb
<#2 (comment)>
:
|
Owner
Author
|
Hi Tianyi,
Thank you for your feedback. I have rerun Lab 4 and included all outputs
and results. I also executed the Fashion-MNIST dataset and loader cell and
updated the display to show one batch of 16 images in Assignment 2. The
existing pull request has been updated.
Thanks,
Ayesha Aziz Prova
…On Mon, Jul 20, 2026 at 4:33 PM Tianyi Liu ***@***.***> wrote:
***@***.**** requested changes on this pull request.
Hi Ayesha Aziz,
Thank you for submitting your DL week 2 assessment. Please find my
comments attached to each file. Please re-run the lab4 notebook and
include all results in your submission.
Thanks,
Tianyi [LS]
------------------------------
On 01_materials/labs/lab_5.ipynb
<#2 (comment)>
:
✅ Lab5 complete.
------------------------------
On 01_materials/labs/lab_6.ipynb
<#2 (comment)>
:
✅ Lab6 complete.
------------------------------
On 02_activities/assignments/assignment_2.ipynb
<#2 (comment)>
:
💬 1. Loading the Fashion-MNIST Dataset: The code cell where you defined
the dataset and loader was not executed. Further, the following code cell
should display only a batch of (16) images.
✅ A2 complete.
------------------------------
On 01_materials/labs/lab_4.ipynb
<#2 (comment)>
:
|
tianyi21
approved these changes
Jul 22, 2026
tianyi21
left a comment
tianyi21
left a comment
There was a problem hiding this comment.
Hi Ayesha Aziz,
Thank you for revising your submission.
🎉 Your week 2 assessment is now complete!
🎊 All your DL assessments are now complete! Thank you for your participation, and I wish you the best of luck in your future endeavours!
Thanks,
Tianyi [LS]
Owner
Author
|
Hi Tianyi,
Thank you for reviewing my revised submission and confirming that all my
Deep Learning assessments are complete. I truly appreciate your guidance
and feedback throughout the course.
Best regards,
Ayesha Aziz Prova
…On Wed, Jul 22, 2026 at 2:29 PM Tianyi Liu ***@***.***> wrote:
***@***.**** approved this pull request.
Hi Ayesha Aziz,
Thank you for revising your submission.
🎉 Your week 2 assessment is now complete!
🎊 All your DL assessments are now complete! Thank you for your
participation, and I wish you the best of luck in your future endeavours!
Thanks,
Tianyi [LS]
------------------------------
On 01_materials/labs/lab_4.ipynb
<#2 (comment)>
:
✅ Lab4 complete.
—
Reply to this email directly, view it on GitHub
<#2?email_source=notifications&email_token=BGGHE534SQFFUV42AQWHSM35GEBXLA5CNFSNUABKM5UWIORPF5TWS5BNNB2WEL2QOVWGYUTFOF2WK43UKJSXM2LFO4XTINZVG42TANJTGA32M4TFMFZW63VGMF2XI2DPOKSWK5TFNZ2KYZTPN52GK4S7MNWGSY3L#pullrequestreview-4757505307>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/BGGHE57HVGATFHM6C2GMRGL5GEBXLAVCNFSNUABGKJSXA33TNF2G64TZHMYTEOBVGIYDAMBWGA5US43TOVSTWNBZGI2TMNJSG44DFILWAI>
.
Triage notifications, keep track of coding agent tasks and review pull
requests on the go with GitHub Mobile for iOS
<https://github.com/notifications/mobile/ios/BGGHE53ISG374YZB5YZI2ZT5GEBXLA5CNFSNUABKM5UWIORPF5TWS5BNNB2WEL2QOVWGYUTFOF2WK43UKJSXM2LFO4XTINZVG42TANJTGA32M4TFMFZW63VGMF2XI2DPOKSWK5TFNZ2KUZTPN52GK4S7NFXXG>
and Android
<https://github.com/notifications/mobile/android/BGGHE53DSNEREOOKYP22VBT5GEBXLA5CNFSNUABKM5UWIORPF5TWS5BNNB2WEL2QOVWGYUTFOF2WK43UKJSXM2LFO4XTINZVG42TANJTGA32M4TFMFZW63VGMF2XI2DPOKSWK5TFNZ2K4ZTPN52GK4S7MFXGI4TPNFSA>.
Download it today!
You are receiving this because you authored the thread.Message ID:
***@***.***>
|
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What changes are you trying to make? (e.g. Adding or removing code, refactoring existing code, adding reports)
I completed Assignment 2 and Labs 4, 5, and 6. In Assignment 2, I implemented zero-shot Fashion-MNIST classification using CLIP, evaluated baseline and improved prompts, visualized image embeddings using UMAP, and conducted a multiple-description classification experiment. I also added the required reflections and short report.
What did you learn from the changes you have made?
I learned how CLIP performs zero-shot image classification by comparing normalized image and text embeddings using cosine similarity. I also learned that prompt wording affects classification accuracy and that adding more prompts does not always improve performance. The UMAP visualization helped me understand how CLIP separates distinctive classes and struggles with visually similar clothing classes.
Was there another approach you were thinking about making? If so, what approach(es) were you thinking of?
I considered using a different CLIP model or evaluating top-k accuracy. I selected multiple-description classification to investigate whether providing several descriptions for each class would improve performance.
Were there any challenges? If so, what issue(s) did you face? How did you overcome it?
The main challenge was the long inference time because CLIP processed 10,000 images on the CPU. I added progress updates and reused previously calculated image embeddings in the mini-experiment to avoid unnecessary repeated inference.
How were these changes tested?
I restarted the kernel and executed the notebook cells. I evaluated the models using accuracy and confusion matrices. The baseline achieved 62.40% accuracy, the improved prompts achieved 64.81%, and the multiple-description experiment achieved 59.59%. I also verified that the UMAP visualization and all notebook outputs were generated successfully.
A reference to a related issue in your repository (if applicable)
N/A
Checklist