[Day 36] Intro to PyTorch

 안녕하세요?
오늘은 Day 36입니다!



Tesla autopilot and ChatGPT apparently use PyTorch, so for some time I have been wanting to see what PyTorch is like. Given that I wanna go deeper into computer vision and self-driving cars, I wanted to "get my hands dirty". 


1) IBM's DL with PyTorch

I did IBM's DL with PyTorch and it was good, but not very practical. It assumes I have no DL knowledge, but it was not that bad, just a refresher on loss, activations, back and forward prop, gradient descent, etc. 


파이토치의 라이브러리는 텐서플로보다 더 직접적으로 다 정의해야 하는 것이다. 어떤 단순한 것에 적용해야지 ~ 라고 생각했다


2) PyTorch Project: Handwritten Digit Recognition

그래서 이 분의 튜터리얼 프로젝트를 딸랐다

사실 이 2023년 여름에 머신러닝 처음 공부했을 때 이 분의 채널은 도움이 굉장히 되었다. knn, linear regression, logistic regression, 의사결정나무 등등 초보자 위한 튜터리얼 프로젝트들이 너무 좋다 ~ 

텐서플로와 차이점

You have to load data with the DataLoader 

Explicitly define the model, and each layer. (forward prop)

훈련 때, backprop 직접 정의해야 한다. 또, model.train()으로 모델이 훈련 상태로 바꿔야 한다 (나중에 test/eval 할 때 model.eval())

손실 계산하고 print으로 손실과 정확도 표현해야 한다

그 다음에

3) Facial Expression Recognition with PyTorch 및 Deep Learning with PyTorch : Object Localization

여기에서는 transfer learning으로 모델을 만들어 봤다. 두 번째 프로젝트는 야채나 사과의 bounding box 모델 구성했다. 첫 번째 모델이 좀 더 재미있었다. 이 두 가지 프로젝트는 이미 구성된 모델을 사용했는데 훈련과 검증을 파이토치로 어떻게 하는지 조금이나마 더 깊게 이해했다

얼굴 표현 모델이 다음과 같은 데이터를 사용했다


여기선 data augmentation도 했다 (transforms.Compose으로)
(아이 재미있는 사진 ㅎㅎ)


또한, 데이터를 DataLoader으로 로드했다

이미지 사이즈를 확인하려면 다음과 같은 코드로 할 수 있다
모델 클래스 구조에 init와 forward 함수 꼭 포함해야 한다

훈련 다음과 같다

결과를 보면 각 이미지의 class의 probability 볼 수 있다



오늘의 공부한 내용이 재미있는데 내일, 다른 데이터로 제가 직접 파이토치 모델을 만들어 보겠습니다!



오늘은 여기까지입니다!

내일 뵐게요 ~

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