Hi everyone, model accuracy is heavily dependent on your epochs and learning rates. I’ve achieved 99.25% accuracy in my model after tweaking hyper-parameters a few times. I gave an attempt to explain why in my medium blog post here. You can also find my notebook here. I will probably experiment the use of neural networks on pneumonia image classification so stay tuned throughout the rest of the week.
EDIT: As stated below from @aakashns, there was a reference error in the dataloader. For anyone that reviewed my notebook and blog post, I apologize. I should’ve been a bit more unsettled since the model was showing the same accuracy for both training and testing. The new accuracy from my model is around 55% which is much more understandable since the model is only looking at each pixel rather than the full picture. I assume that this is why we have convolution networks. Again, I apologize for any misunderstandings. I’ve updated my notebook here and updated my blog post here.
I wrote my first ever Medium article. This class is amazing, even at the end of the 2nd week, I already learned so much! Here you can find my article on ocean water temperature prediction using 60 years of oceanographic data: https://medium.com/@bilgenurb/tackling-climate-crisis-with-machine-learning-d9426fe1f5a9 Feel free to give me feedback. Thank you all!
Hello everyone this is my notebook for assignment 2. there is a part where the printing of data after using the dataloader is showing error, but don’t worry that doesn’t affects the model in any ways and the loss is also quite low so here it is.
Assignment 2 notebook:
Hey everyone, here is the link to my linear-regression insurance model.
You can see all the details below here.
Just click on the link.
Everything has been thoroughly explained…
Just click it…
&
here is the link to the blog of the above linear-regression assignment…
Do Check it out…
If there’s anthing, Just let me know.
Share your Feedback soon…
Hi everyone. For the optional assignment, I decided to do one of the famous and simple classification dataset the iris-dataset. And i was really shocked to see that the validation and test accuracy score is 1.0. You can read my medium blog post about the topic or go through the jovian notebook
Hello people!
I have created blog post (link to blog) so check it out! I also embed link to my Jovian notebook (link to notebook) so check out if you are confused in blog post or just want to see it . Also, I have added my understanding, so if I am wrong in any way, please let me know and also I hope to clarify people’s confusion
Hello all! I’ve finished Assignment 2, although I haven’t implemented smooth_l1_loss yet and I wonder how much better the model can do with it.
At the meantime, I made another notebook on predicting League of Legends Matches with a logistic regression model, which is by far my favorite game since childhood! Here is also the blog post on medium with the notebook. Hope y’all enjoy!!
Hello everyone,
Here is My Second Week Assignment-2 :
Train Your First Model. My NoteBook
with My Medium Blog :
“ Introduction to Linear Regression & Train Your First Model.” by Ritesh Kumar
Do check it out. I hope you all Like, Share, and Claps.
So if you think it’s interesting.
Thank You