Annotated notes to Fast.ai's lesson on Image Classification
zerotosingularity.com
Annotated notes to Fast.ai's lesson on Image Classification
1–10 of 15 posts
Re: Annotated notes to Fast.ai's lesson on Image Classification
#2I'm taking this course now. Your annotations explaining each command are very useful. Thanks for sharing them
Re: Annotated notes to Fast.ai's lesson on Image Classification
#3I'm taking this course now. Your annotations explaining each command are very useful. Thanks for sharing them
Here (https://medium.com/@hiromi_suenaga/deep-learning-2-part-1-le...) is another set of really detailed notes. There is one for every video and they are also very good.
Re: Annotated notes to Fast.ai's lesson on Image Classification
#4I'm taking this course now. Your annotations explaining each command are very useful. Thanks for sharing them
Hope they help in understanding... Enjoy!
Re: Annotated notes to Fast.ai's lesson on Image Classification
#5I'm taking this course now. Your annotations explaining each command are very useful. Thanks for sharing them
Here ( https://medium.com/@hiromi_suenaga/deep-learning-2-part-1-le... ) is another set of really detailed notes. There is one for every video and they are also very good.
These notes are also really good, and ahead of what I have written up so far... :)
My take on these is adding somethings I picked up along the way to add another perspective and some additional info.
Re: Annotated notes to Fast.ai's lesson on Image Classification
#6A coworker has insisted on Fast.ai do you think its preferable over Keras/TFLearn?
Re: Annotated notes to Fast.ai's lesson on Image Classification
#7> build a world-class image classifier in three lines of Python
How is that learning how to build something, as opposed to simply using a system someone else built?
Re: Annotated notes to Fast.ai's lesson on Image Classification
#8A coworker has insisted on Fast.ai do you think its preferable over Keras/TFLearn?
I found/find fast.ai to be incredibly useful for its practicality, good results, and top-down approach, however, it is sometimes hard to reproduce the results as well as clearly distilling what it is you can actually learn from each lesson. Writing this post blew my socks off as to what was taught in the video, yet it took me quite some time to get it all. So I hope the posts help people with that aspect of the course.
At the moment, I'm learning fast.ai/PyTorch in parallel with Keras/Tensorflow, so at this point, I have no definitive answer to your question which one is preferable. It will probably depend and they will most likely have their own benefits (I know that the boring answer, but I need to get more experience to give you a better answer).
As an exercise I'm trying to write the fast.ai notebooks in Keras, to see how they stack up. Might need to do a post on that as well.
I hope to answer your question better in the future. Could you tell me more about what you want to achieve, I might be of more assistance?
Re: Annotated notes to Fast.ai's lesson on Image Classification
#9> build a world-class image classifier in three lines of Python How is that learning how to build something, as opposed to simply using a system someone else built?
Fast.ai's courses start at a high level with working code right off the bat. Then they break it down and show you how the parts work. It's much more motivating when you don't have to wait a long time to see any results. [Edit: and you know you're going to get something good instead of putting a lot of work in and getting something mediocre or plain not working.]
See this paragraph in the article: https://www.zerotosingularity.com/blog/fast-ai-part-1-course...
Re: Annotated notes to Fast.ai's lesson on Image Classification
#10> build a world-class image classifier in three lines of Python How is that learning how to build something, as opposed to simply using a system someone else built?
I guess titles are meant to attract and provoke a little at the same time...
Fast.ai uses a top-down approach, allowing students to get awesome results with a minimal set of instructions, and start to dig deeper from there. If you look at the takeaways from the first lesson, you can see it's more than just three lines of Python and you're done, It's a solid and fresh approach to learn some actual practical deep learning.
Additionally, it kind of depends on what you want to do, we are all using things other people built, depending on the level of abstraction we care for or are willing to deal with...