FAQ, resources, and official course updates ✅

Part 1 (2019)
1

Welcome to deep learning part 1 v3! This thread will be updated with any important changes to the course, so please keep a close eye on it. Only admins are able to reply to this thread, so please subscribe to topic notifications to ensure you don’t miss anything. Click “none” in the sub-forum list at the top of the category to hide all the local discussions, if you want to reduce the amount of topics you see. Use the “Advanced” sub-forum for any discussions not accessible to deep learning beginners (i.e anything not covered yet but a lesson in this course).

Important links :white_check_mark:

Lessons
Lesson 1 Resources and updates Chat
Lesson 2 Resources and updates Chat Further Discussion
Lesson 3 Resources and updates Chat Advanced Discussion
Lesson 4 Resources and updates Chat Advanced Discussion
Lesson 5 Resources and updates Chat Advanced Discussion
Lesson 6 Resources and updates Chat Advanced Discussion
Lesson 7 Resources and updates Chat Advanced Discussion
Special Leslie Smith Interview

Platforms
Gradient Setup Discussion
Colab Setup Discussion
Crestle Setup Discussion
FloydHub Setup Discussion
GCP Setup Discussion
Azure Setup Discussion
Sagemaker Setup Discussion
AWS EC2 (DLAMI) Setup Discussion

Deployment platforms

Platform Guide Discussion
Render Guide Discussion
AWS Elastic BeanStalk Guide
Google App Engine Guide

Other topics

Etiquette for Posting to Forums

  1. If you like a post, it’s better to “like” it with the :heart: rather than commenting. It saves traffic in the Forums and makes it easier for everyone to find posts.
  2. Please be mindful of looking to see if a topic exists before starting a new thread.
  3. Do a quick search of the forums to see if your question is already under discussion.
  4. Do not @ people if you are not referencing them for a specific reason that requires the attention of that forum member. Be specially mindful in mentioning Jeremy and Rachel.
  5. Regional Study Group discussions should be posted in the relevant category related to timezones.

FAQ :question:

  1. I am getting untar_data not defined / AttributeError: module ‘fastai.vision.models’ has no attribute ‘resnet34 / name 'error_rate' not defined / name ‘download_images’ is not defined what’s wrong?

    Most probably you do not have the latest version of the library installed.

    • If using conda please try:

      conda update conda -y
      conda update -c fastai fastai

    • If using pip please try:

      pip install fastai --upgrade

    • To check everything worked well use:

      conda list

      or

      pip show

      You should see that the fastai package is version 1.0.11 or later.

  2. I am running the lessons notebooks in Google Colab and am getting this error: RuntimeError: DataLoader worker (pid 137) is killed by signal: Bus error, what’s wrong?

    This is a PyTorch issue with shared memory. See this thread for more information.

Policies

  • Video links: videos should not be shared until the MOOC is officially released in early 2019
  • Blog Posts: Blog posts are welcome and recommended, but they mustn’t include the video until after the MOOC is released next year. Therefore, the blog posts need to stand alone and be useful without the video.

Local categories

Therefore, I’ve created 11 (approximate) local categories for fast.ai students. Obviously I can’t list every time zone and country - the idea is that you can decide which of those groups seems closest to a group of people that are likely to be up and chatting at a similar time to you, and that you are most likely to share a language and cultural understanding with. Feel free to join other groups too of course! :smiley: To remove region-specific posts from the main category, simply choose ‘none’ in the subcategory list on the topic list page.

Other information

Introductions Thread

If you want to find out more about your fellow students, check out the introductions thread - and maybe add a bit about yourself there too!

How to Ask for Help

Here is advice on how to ask for help in a way that maximizes the chances someone else will be able to provide a helpful answer.

145 Likes