General course chat

Thank you so much.

Thanks Concentric, making venv and installing there worked for me as well
:slight_smile:

Try to attach you google drive with colab. This will save time when you will restart the colab session.

Hi guys I am new here, and I must confess I am a bit lost with everything going on. I have been going through different threads already but I still have a couple of questions.
A bit of a background I have been using gcloud for my virtual machine on a mac os. I wanted to know

  1. I have been using jupyter through the instance, but I keep seeing that we can use the fastai repo for everything. I do not understand what would be the advantage or use of using the fastai through github rather than cloning a jupyter notebook and doing everything from there instead?
  2. I am never able to get the conda command on the terminal.
    sudo /opt/anaconda3/bin/conda install -c fastai fastai
    conda install -c pytorch -c fastai fastai
    Both these commands yield: conda: command not found
    Thank you, everyone :slight_smile:

Heya! New to the course. Started this week.

I managed to get everything working, so I decided to try the steps out on a small dataset. Currently I’m looking at about four categories of ~100-200 images each.

I went through once and had an error of approximately 50%. No big deal. I didn’t bother with any kind of image cleaning or anything.

After cleaning I’m down to around 30% error. So clearly it had an affect, but I’m missing some other kind of secret sauce.

My question is more of one of scale. I plan to go through and clean the images out again, but is it a case where I would just need more images? I figured that my dataset was pretty dang small, but I kind of want to have an idea of how many I should be aiming for with resnet34 and resnet50. Are we looking at 10^3? 10^4? Higher than that? Do we get diminishing returns after a certain point?

Thanks for any tips!

Hello! I’m new to this course, I’ve just started and watched the first lesson and I can say… I’m extremely lost, I feel like most of it goes over my head and I wonder why. My first thought is that I haven’t worked with python before and my programming background is hard to determine -I’ve done some little things but probably not the level necessary. So my question is should I try going through the lesson once more or should I first look through some python code and exercises?

Hi AID hope you are having a wonderful day!

This link How to do fastai - Study plans & Learning strategies has some wonderful strategies for learning python.
I think you should follow the advice Jeremy gives in the video and try to answer the questionnaire first. This link describes a nice strategy How to do fastai - Study plans & Learning strategies.

If you have very little programming experience, you may need to learn python at the the same time. I have found the strategy of doing the steps in the 2nd link the most effective for me.

I also have to practice what I learn by trying to build something using the lesson material to keep it fresh in my mind.

Keep a python reference that you find really easy to understand close by. I have found the best reference is not what others say is the best, but one you can most easily and quickly understand and use to achieve your goals sometimes its books, tutorials or this forum, or other websites.

Hope this helps

Cheers mrfabulous1 :smiley: :smiley:

1 Like

Thanks a lot for the replay!

I see the strategies suggest reviewing the lectures at least once which I was going to do too, so I’m on the right path.

I started reading a whirwind tour of python, which seems like a good way to pick up the language from.

One last thing do you know exactly where the questionnaire after the lesson is? I can’t seem to find it for some reason

Hi AID hope your having a fun day today!

I have watched some videos 10 times to get it in my head (in bed just before I fall asleep) lol! :smiley:

Unfortunately in the part 1 2019 course there is no questionnaire, I was thinking about another course.

If I were you I would make a glossary/cheat sheet of my own by using the docs https://docs.fast.ai/
and using the search transcript function of the lesson video’s when you access them through https://course.fast.ai/videos/?lesson=1

If you search this forum for something like “lesson notes” some people have summarized the lessons.

Hope this helps

Cheers mrfabulous1 :smiley: :smiley:

1 Like

Thanks a lot again!
This was of great help. I feel like I know what I’m doing a little bit more now!
I’m still not sure if this is the part of AI I want to pursue, but I will give it a try, the experience look valuable.

Hi @yurpmyguy

The firt :one: is confusing, but in regards to the :two: -nd: have you tried activating anaconda env first?
Usually source ~/anaconda3/bin/activate than call on conda
You can go with conda config --set auto_activate_base True for convenience

1 Like

In my experience, playing around and seeing what works s great. Also, make sure you follow the course’s tips on fine tuning, like the right learning rate and epoch, as well as looking for the steepest part of the recorder plot.

Hi all, does anybody know how to deploy a NN locally? I’m having trouble with what’s posted on the FastAI website:

python app/server.py serve.
Go to http://localhost:8080/ to test your app.

Any help is greatly appreciated!

@stoops_ML have replied in the thread you created! Hope we can sort your issue :slight_smile:

Thank you @hutnic so much

Has anyone worked through a way of setting up self-hosted orchestration for distributed ML-based jobs?

Re: making web apps with models from lecture homeworks

I’d like to make a collection of web apps from each lesson’s homework. I think it would be fun to share with friends and family, and would help get a feel for what it’s like to do things outside the “sandbox”. Unfortunately I’m a horribly slow beginner and it looks like I need a baseline level of knowledge:

  1. A framework like Flask or Django
  2. Basic JavaScript
  3. CSS
  4. HTML
  5. Template Engines

Am I missing something that will allow me to skip learning 3 new languages and 2 new software tools? For a total beginner like me, that’s a pretty intimidating list of skill-sets.

Of course, I’m not afraid of learning new things, but I am afraid of getting bogged down and distracted from the coursework.

Hi wcneill hope you are having a wonderful day!

Having been on this forum for over a year now, I have yet to see any solution that has not required learning new skills and software libraries.

Many of of the automated frameworks that say make things easy often have learning curves which are as steep as some programming languages, less flexible and when they break are seriously difficult to fix.

If I were in your position, I would try and build the teddy bear classifier, many total beginners have built this application.

See the links below for guidance
https://fastai-v3.onrender.com. - Working starter app using CSS, Javascript, HTML, Docker and Starlette.

https://course.fast.ai/deployment_render.html - instructions for deploying on render and using Docker once done this can be used locally or on any server platform in the universe that supports docker.

Share you work here - highlights - Wonderful ideas and applications that people have created.

Deployment Platform: Render ✅ - Solutions to many of the problems you may encounter while trying to deploy your app.

You do not have to learn the whole framework or language just the bits you need to make your program work.

If you do find a flexible framework or strategy that requires no learning of new skills etc. please share it on this forum we’d all love it.

ps. It took me about 5 weeks to deploy my first app once I started it, but now I can build a simple app in hours or a day.

Hope this helps

Cheers mrfabulous1 :smiley: :smiley:

@mrfabulous1 Thank you so much for the thoughtful response.

I have to admit to having a small panic attack when I saw the steep learning curve for writing an app (Jeremy said try to do it “this week even if you’ve never written a web app before” in one of the recorded lectures).

It took me 3 years to finish a 2 year master’s program because I’m not the brightest student. In the year since then, I’ve been working 8-12 hours a day both applying for jobs and trying to learn the skill-sets to get a job (because a master’s in math turned out to be useless). I think all of the frustration came to a head when I wrote that post.

Let’s just say I really appreciate your response. Sometimes it feels like no one is out there on these forums. I’m gonna get to work looking at the resources you provided :slight_smile:

Cheers,
Wes

1 Like

Hi wcneill Hi hope your having a wonderful evening!

You may think you are slow but I may be slower. I would really like you to get your first app going. If you look at this thread Deployment Platform: Render ✅ you will see I have helped many people get their first app going.

Building the app may be a challenge but if you try to build an app and you have a problem and you at least try and fix it yourself and you post a question with the error message and a short description of what you tried, I and others will try and help.

Building the app lets you learn every step required to deploy an app.

If you are confident and you remember the steps, I am sure if you went for an interview, you would be in a better position than if you hadn’t built one.
Also, even if you didn’t get the job as “chief systems designer of machine learning systems”, you would be in better position to get a junior support role, to get your foot in the door.

I am looking forward to your first app!

Cheers mrfabulous1 :smiley: :smiley: :smiley:

1 Like