-
Notifications
You must be signed in to change notification settings - Fork 397
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Comp3710 Pranay Premdas - Vision Transformer Task 6 - 46444675 #462
base: master
Are you sure you want to change the base?
Conversation
patch_size. Accuracy is yet to be tested. NOTE: more references n eed to be added to each code block to avoid plagarism penalty.
…_accuracy is still aprroximately 0.72
…d epochs to 50. Average accuaracy is still 63%
Also added a sigmoid layer at the end as suggested by tutor.
…oes not improove the model. Model accuracy is stuck on 0.48.
it is diverging to infinity. Further, accuracy remains on 0.48
changes for adding legend in the plot. Also edited spelling error in comment for modules.py
…nitially on my cluster copy and forgot to copy it over
Hi, I seem to have forgotten to add two changes in my code I hope this does not affect my mark.
|
This is an initial inspection, no action is required at this point There is no README file provided which you will need to explain your model and present your results. Commit log: Great |
HI, I seem to have forgotten to upload the read me on here. I have however submitted it on blackboard. I hope this does not affect my mark. To make it easier I have pushed the read me on here. |
All good, I can see it now. :) |
Good Practice (Design/Commenting, TF/Torch Usage)Adequate use and implementation Recognition ProblemSolves problem (low performance) -1 Commit LogMeaningful commit messages DocumentationReadMe OK, but needs architecture diagram and more info/background -2 Pull RequestSuccessful Pull Request (Working Algorithm Delivered on Time in Correct Branch) |
Created pull request for the algorithm implemented. This pull request attempts to solve Task 6 of the report. Student Number: 46444675, Pranay Premdas