📝 Deep Learning Lesson 1 Notes

I tried to download thOxford-IIIT Pet Dataset and it was 714 MB. So how does it gets downloaded into our jupyter notebook in seconds?

Because that is hosted on Amazon S3 on AWS. High speed cloud data storage. :slight_smile:
There is link in notes.

Also check fastai datasets

2 Likes

so when that data gets transferred from aws to our cloud environment it doesn’t uses our internet speed :thinking:. Anyways ur notes are very helpful, thanks a lot

1 Like

Correct. It uses the internet speed of wherever your cloud environment is hosted.

For example:

If you’re using GCP then the speed is determined by the connection between your cloud machine and the AWS network.

So when you try to download the dataset on your own laptop the speed is determined by the connection speed of your network

1 Like

So, does that mean that size 224 x 224 gives better result than other sizes?

If you are using fastai version 1.0.15 and above, we need to renamed ConvLearner to create_cnn. I have edited the notes for this change.

6 Likes

Yes if using pretrained weights.

1 Like

Does anyone has a change to look into the create_cnn (extracted from learner.py line 61 below)? Is it appropriated to have a space between if and none?

body = create_body(arch(pretrained), ifnone(cut,meta['cut']))

No. Because it’s a fastai function in core.py

2 Likes

Thanks a lot. I am still trying to get myself familiar with the new library. :blush:

Probably most important thing for your learning of the code is to ensure you’ve set up your editor to allow you to click on words in your code to jump to their definition and popup their summary. Once you’ve got that working, everything will be far easier! :slight_smile:

6 Likes

Does anyone know a easy way to download these notes?

I like goto functionality in Atom editor.

Pasting my Lesson 1 notes here too, in case the thread is converted into wiki:

It already is a wiki.

2 Likes

question in regard to show_batch

What exactly does the method use to be able to center crop the image?

In the lesson is said that it grab the middle bit, but I quite don’t understand what bit stands for in this context…

Thank you!

I did a mindmap of Lesson 1

The goal is to create a mindmap of each lesson.

I also did a mindmap on RegEx

Hope it will be helpful to somebody…

Enjoy :slight_smile:

19 Likes

@leovcld thanks for these nice mindmaps.Which software / tool did you use for creating these?

1 Like

Xmind Zen, i suppose

Is learn.save stores the best model obtained during training?