This site is built with fastpages, An easy to use blogging platform with extra features for Jupyter Notebooks.
fastpages automates the process of creating blog posts via GitHub Actions, so you don’t have to fuss with conversion scripts. A full list of features can be found on GitHub.
You can edit the index.html file to change this content.
Posts
Some basic processes may seem obvious for the most, but for me as a beginner, It takes some time and experiment to become familiar some topics. Image processing for Deep learning is one of them. This post is an attempt to understand the process of opening an image file converting to a tensor and after training process convert back into a image. My favorite library FastAi makes all these possible without a big effort but sometimes, especially when playing with the data, it is very useful to understand the basics.
Apr 27, 2022
This is from 2018, tutorials and trainings aside my first attempt for training a neural network. It does not have a traditional loss function or optimization method but it uses neuroevolution for training. I use p5.JS for the visualization and tensorflow.JS for the model.
Jan 15, 2022
This is my first attempt to implement a NN architecture from scratch. It took much more time than I expected, after three videos and this notebook I believe, I'm in a better position to understand the Resnets and CNNs in general. The purpose of this blog post and the companion videos are to document my learning process, get experience in coding and understand published papers. Please check my resources below. I believe it is the most important part of this notebook.
Dec 12, 2021
This chapter is not directly ML but mostly FastAi API costomizations. Looks great. At this point I think I need to use FastAI in at least a toy project. These files must be developed overtime. It a source for me.
Nov 2, 2021
Just notes not much added
Sep 25, 2021
Just notes for archiving
Sep 18, 2021
Mainly original notebook. Some notes added.
Sep 11, 2021
This is almost same with the original notebook.I took some notes but nothing added. It must be read from start to end.
Sep 4, 2021
Deep Learning For Coders with fastai & Pytorch- Collaborative Filtering Deep Dive - Recommender systems works differently than classic DL classifiers. They are mostly used for known data, no prediction expected based on previously unknown data like bear classifier do. Yes, there is a generalization process but still, all data is known by the model. What is not known is latent factors at the beginning of the training. The model learn these latent factors and the recommender is ready.
Sep 1, 2021
Deep Learning For Coders with fastai & Pytorch - Training a State-of-the-Art Model, this chapter is a bit different, it contains some technics that make the results better. My plan is taking some notes about this practical technics and come back later when I need them.
Aug 15, 2021
Deep Learning For Coders with fastai & Pytorch - Multi-Label Classification, Regression. In this notebook, I followed both Jeremy Howard's Lesson on fast.ai and Weigh and Biases reading group videos. Lots of notes added. .Click `open in colab` button at the right side to view as notebook.
Aug 2, 2021
Deep Learning For Coders with fastai & Pytorch - Image Classification, In this notebook I followed both Jeremy Howard's Lesson on fast.ai and Weigh and Biases reading group videos. Lots of notes added, some cell's order changed some are added to make the topic more understandable for me. (Check Manual calculation `log_softmax` + `nll_loss`). Click `open in colab` button at the right side to view as notebook.
Jul 22, 2021
Deep Learning For Coders with fastai & Pytorch - Under the Hood - Training a Digit Classifier. In this notebook. I add some cells for utility fuctions. `path`, `ls`, `untar`, `!`, `tree` usage, as usual I followed both Jeremy Howard's Lesson and Weights and Biases reading group videos. Click `open in colab` button at the right side to view as notebook.
Jul 16, 2021
