[Day 61] Stanford CS224N (NLP with DL): Machine translation, seq2seq + a side CDCGAN mini project

 Hello :)
Today is Day 61!


A quick summary of today:
  • Covered Lecture 7: machine translation, seq2seq, attention from Stanford CS224N
  • Tried to make a conditional DCGAN to generate MNIST numbers (colab) (kaggle)


I will first cover the GAN story

(then will share my notes from the lecture)

So... while watching and taking notes today, I started thinking, what if I can use my notes as data to a model and afterwards, when I want, I can give it raw string text and it will output text in the format of my notes (with my handwriting).

Well I started looking around and actually the first model architecture that came to my mind was the GAN (specifically conditional GAN) - I remembered there was a GAN architecture that alongside the pictures, we can give it the labels, and then on-demand generate. In retrospect, there are of course others, but I decided to go with GAN. 

For maybe 2 hours I busted my head trying to make a simple model with the EMNIST dataset (english characters), and I kept getting weird input size issues. And after a bit I read online that the num of classes for the EMNIST from PyTorch is a bit weird (i.e.). What is more, I saw this: 

This image with handwritten text is generated with a conditional deep conv GAN (repo link). And my mind was hooked on the idea -> I want to do it too. But firstly, I wanted to do it with just numbers, a bit more simple (and not having to struggle with loading the EMNIST dataset). 

Thanks to Aladdin Persson's youtube channel, I got reminded how GAN's architecture works and I had a simple model, and started training in my google colab. After a few hours of adjusting params to optimize training and lower loss, and also doing inference - producing new number images, I had a working model. I was so happy. This felt soo long, at first with the EMNIST problems, and then just getting a conditional DCGAN to work. Aaaand... my colab gpu free time finished in a middle of a run and all was lost because I had not saved any weights :/ I did not even take a screenshot of the generated output numbers I got - and they were amazing, human-like. 
Right now as I am writing this, in the colab, there is no output, but hopefully later if someone reads this, you will be able to see sample results (I will rerun it when I get my free gpu hours). 
But also, I am running it on kaggle right now, will get a generated output pic and go to sleep because it is almost 2am.

So, this is the result. Not too bad. But in colab I could use tensorboard (there is a way in Kaggle too, but it gives me an error :/ ) (Link to the kaggle notebook)


As for my notes for the lecture 7:


That is all for today, tomorrow we continue with CS224N! :)



That is all for today!

See you tomorrow :)

Popular posts from this blog

[Day 198] Transactions Data Streaming Pipeline Porject [v1 completed]

Image
 Hello :) Today is Day 198! A quick summary of today: data streaming pipeline project [v1 done] Here is a link to the project's repo. Well ... I did not know I can do it in a day (~14 hours) after yesterday's issues but here we are. Turns out in order to insert the full (~70 variables with nested/list structure), I need the proper pyspark schema. And yesterday I did not have that and that is why when I was reading data in the kafka producer I was getting NULL in the columns - my schema was wrong. Well today I not only fixed the schema for the 4 variables I had yesterday, but included *all* the variables that come from the Stripe API ~ 70 (for completeness).  When I run docker-compose, the data streams and is input into the postgres db (and is still running). Unfortunately, the free Stripe API for creating realistic transactions has a limit of 25, so every 3 seconds, 25 new transactions are sent to the db. It has been running half the day (since I got that set up) and as I am wr
Read more

[Day 107] Transforming natural language to charts

Image
 Hello :) Today is Day 107! A quick summary of today: created text2chart - transforming natural language to charts [ github ] [ webapp ] I am super sick, but in the around 3 hours of my fever not being high, I managed to study a bit. I was again thinking about creating some nlp project but was stuck on the idea of how to host a model. After looking around I found this article where they create a similar app called chat2vis  and they use codellama. I know codellama is an open source model that I can get from huggingface and I wondered, how did they host it. Turns out - they ask the user to input a huggingface api key, which then allows for querying and generating content. (AWESOME! this is applicable to some of the other PDF chat apps that I have, but I will look to make an app of them later).  My fever eased a bit, and I sat on my chair to do some work ^^ Here is a breakdown of the app. I used streamlit. Also, 2 default datasets during dev: Financial Statements of Major Companies(2009-
Read more

[Day 54] I became a backprop ninja! (woohoo)

Image
 Hello :) Today is Day 54! A quick summary of today: Read through cs231n's neural network lectures [1] [2] [3] Spent 8 hours going over Andrej Karpathy's backprop ninja tutorial After yesterday's confidence boost in doing backprop, I came in today with the intention of becoming of, as Andrej Karpathy calls it, a backprop ninja.  The cs231n NN lectures were the usual about how NN became to be, param initialization, activation functions, loss functions, regularization and optimizers. Nothing out of the ordinary, but still was good to reassure myself of that knowledge. But that was definitely not the main even of today. As I mentioned, I wanted to become (or at least attempt to become) a backprop ninja today. I have watched that particular tutorial twice, the 1st time I had no idea what is going on, the 2nd time I could follow, and now it was the 3rd time - and now, I wanted to participate and actually see the why and the how of the things we have to do, when we do manual back
Read more