Lesson 1: Practical Deep Learning for Coders

Welcome to the first full lesson of Practical Deep Learning For Coders! Before you start this lesson, be sure to have completed setup of your deep learning server. See the AWS Lesson to learn how to do this, if you haven’t already.

Each lesson page includes links to course notes, forum discussion, and (most importantly) a wiki page. Nearly all the participants in the original in-person course said that they found these resources very important for successfully completing the course. So be sure to make the most of them! And be sure to carefully read the Getting Started page to find out how this course is designed and how to get the most out of it. (Also, apologies that the questions from the audience are hard to hear - we get a special audience mic from lesson 3 onwards which resolves that problem.)

SYNOPSIS

The 30 minute overview video introduces you to the course and explains how to get the most out of each lesson. We also pass on some tips from previous students.

The lesson video starts with a very brief overview of what deep learning is, and why it matters, and then discusses how to access the files for this lesson. However, note that for this MOOC you will probably find it easier to use git instead. The Getting Started page explains how. Then we show how to start, stop, and manage your AWS instance, how to copy data to it, and so forth (if you’re already familiar with AWS you can probably go through this part fairly quickly).

The next point discussed is how to the data for this lesson (and indeed all the computer vision projects we’ll tackle) needs to be structured. This is the most important step for you to complete—if your data is not structured correctly you will not be able to train any models.

[MatthewKleinsmith]

0:00 - Fast AI & the course
5:29 - Why Deep Learning is exciting
10:51 - Deep Learning setup
16:02 - Deep Learning trends and applications
20:06 - Starting your AWS instance
27:07 - Introduction to Jupyter Notebooks
33:43 - Introduction to Kaggle
41:14 - Introduction to tmux
52:57 - Kaggle Dogs vs. Cats data & general data structuring tips
1:01:01 - Introduction to Markdown
1:02:02 - Introduction to some scientific Python libraries
1:09:23 - Pre-trained models & ImageNet
1:15:15 - VGG model
1:17:08 - Implementing VGG
1:22:14 - Python stack being used
1:23:48 - Theano vs. TensorFlow
1:27:02 - Keras and Theano settings
1:30:20 - Batches
1:34:38 - Finetuning ImageNet VGG16 for Dogs vs. Cats

[tianhaowu]

Thank you Fast.AI for the awesome introduction to deep learning and guide through the tedious setup!

There were some really frustrating parts setting up AWS and I had to swap from a Windows computer to a Linux chromebook since Cygwin wasn't working right with / vs. \ and had issues with path.

I'm amazed at how fast tech has advanced in the last few years, its crazy to me that renting a 90 cents per hour box on Amazon allows you to label any image in the world with <10 lines of code.

Really appreciate your teaching methodology of focusing on showing the results first before diving into the theory and numbers to justify your outputs.

[skeller]

Useful tip in the video at 44:00 - If you want to avoid rerunning alias.sh, add the aliases to your ~/.bash_profile (create ~/.bash_profile if you don't have one). On a Mac, you can do this in either your .bashrc or your .bash_profile.

[safakozkan]

To get the 'dogscats.zip' file type

[IRSOG]

I finished Stanford's cs231n like long time ago it was cool but they way you explain is awesome besides
200$ is lots of money for me :(

[tonynicholas]

Thank yor this course Jeremy. I will have to ask everyone on my udacity DL Foundation nano degree to get onto fast.ai. You made all the years of hardwork worth it. Thanks alot for the clear explanations and the pace of teaching. However, i am not able to find the notebooks. I am not able to access the platform.ai

[gcm]

FYI, the setup_t2.sh script creates a t2.xlarge instance (which is billable outside the free plan) and not a t2.micro

[ToddHoff]

Could you please use a white background with black text. The text is nearly unreadable.

[ThankYouESM]

Would love to see the most basic neural algorithm written as to produce deepfake images in purely Python... meaning no third-party imports.

[RK-cwbj]

At 1:20:10 to 1:20:22, What is the 1st shortcoming that he's mentioning? I understand that the second one is that the model may get it wrong at times due to the image being unclear/ it calculates the probability of a 1000 different categories? Can someone please clarify?

[ramih]

How about using google compute engine, they have GPU available, and they give approval in 1 minute?

[nitingupta]

Hi, Can I learn using my local machine instead of using amazon cloud?

[donovankeating]

Can we do this course on Google Cloud Platform too?
Will it matter much in terms of the course material?

[danielnyeste]

I'm just curious, why did you used the Hungarian language as an example at the beginning, why not any other language? :)

[motiurrahman]

Is this an example of transfer learning?

[OttoFazzl]

How did you get a custom visual style for the Jupyter Notebook? It looks different by default.

[royunprofiled]

@ 00:06:00 Should it not be S(x)=1/(1+e^(-x)) ? Is it not a sigmoid function ?

[DimitriCHARLES]

How to switch between sessions in T-mux? I cannot find the command? Is it C-b O ?

[devildez]

How should I know if my Python skills are sufficient to get into this course? 'One year experience' is not really good enough since I could be coding for 1 hour a day or 15 hours a day for that one year. Is there any excersize that can check this?

[mcklcmv]

I found this video is extremely useful to me. As a beginner, I am confused that how did you upload the dataset file to the AWS server? Did you just upload those files by 'SCP' command? If anyone know the answer, please let me know. Thanks in advance!