General course chat

Hi, I’m following your course and thank you very much for explaining the core concepts of NN in a simple way. I’m currently following the graddesc excel file ( part 1 lecture 5) to understand the momentum and adam. I have a question on calculating the derivatives on “basic SGD” tab. Could you please explain how did you decide the following formulas for derivatives.

de/db=2(ax+b-y)
de/da=x*2(ax+b-y)

Cheers!

hello. I just joined and am using Google Colab. I’m finding that I’m able to use the current notebooks out of the box just fine with the exception of state getting lost whenever I close the notebook, meaning that I have to re-download the datasets to presumably some ephemeral drive. I was wondering if there’s any advice around this.

Also, I noticed that at least the first notebook seems to be completed with all the “answers” and I was wondering if there is any advice around using them in their current state. Thank you!

Hello,
I am doing a research project on post-disaster management.
I am not able to find audio data related to post-disaster management.
Can someone pls guide me where I can find audio data related to the disaster in any sense.

Hey guys,
I’m trying to solve this challenge.



I’m having a hard time creating the submission file.

I can’t seem to find a way to get the highest prediction and match it with it’s class.

Why does learn.get_preds() return a different value than using the parameters in learn.model.(i,u)_(bias,weight).weight?

hey there!
I am glad to join the Fast.ai community, looking forward to a lot exciting discussions.
i was going through the online course and im having trouble setting up the fastai on my machine.
my machine configs:
OS: Mac OSX - 10.15.3
installer - pip and pip3


i got this error with terminal command: pip install fastai and pip3 install fastai
kindly help !
Thanks for reading !:smiley:

Have you tried creating a virtual environment first with python 3? Doing that seemed to get me sorted out. I, personally, been primarily using colaboratory though.

as asked in the opening markdown cell in lecture 00 it asks to create a duplicate by clicking on a tick in a box.

there is no box to click

i tried saving the notebook to my drive but the cell

" Image.open(‘images/notebook_tutorial/cat_example.jpg’) " is showing an error as there is no images directory in my drive.

what is the solution? do i have to compulsarily create an images folder in my drive or download it locally or is there another solution ?

‘preds’ returns a tensor .
You have to find the argmax of each images’s class prediction probability ,

preds.argmax(1)

gives a tensor of all the position of the classes
Further,

for l in preds.argmax(1):
        print(learn.data.classes[l])

should give you the corresponding values . Append this into a list / dataframe and export it into a csv file . That should give you the desired output

1 Like

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