Hi https://forums.fast.ai/u/learningML89 hope your day is going well!
The videos are older than your current version of fastai, if you are using v3. Use the video as your guide but stick with the code in your notebooks as this is the most current and definitely works.
Cheers mrfabulous1 
@jeremy
How do i get started with fast.ai deep learning course from zero to hero ??
I know some deep learning courses, i have some experience on deep learning but not all, I have knowledge on programming and python. Except certificate i dont have any on github projects .
How do i get into this fast.ai deep learning course step by step from Zero to Hero to capstone project on github ?
Thanks for the course for free for humanity,I am Hoping to make something benifit for our humans,
Hey , how to set the Oxford 102 Flowers Dataset DataBunch . I just started the course so i’m new to this.
I have a question regarding lesson 2.
When grabbing URLs for photos in our dataset, do we have to use the “url_class.txt” format or can we just name it “class.txt”? If not, why?
Hi,
I have been trying to work on the camvid data set of lesson 2, but I wanted to change the dataset to only have 11 classes not 32 does any one know how this can be done.
Thanks,
Aly
I’m working on the camvid notebook for lesson 3, and would like to try segmentation with another dataset. Up to this point, I’ve only used the method in lesson 2 with google images.
I see in the notebook, it’s looking for URLs.CAMVID. Where is that stored in the notebook, and if I were to download another dataset, is there a tutorial for how to upload it so I can access that in the same way?
URLs. CAMVID is just the variable for a link to a download for the CamVid data set. Untar_data just fetches the file and then untar’s it locally so you can access the data.
If you want to try things out on a different dataset you will need to download a dataset to your practice environment and then use the same methods he uses to put the data into a DataBunch and add the masks.
I just did a quick search but here is a list of other image segmentation datasets, although they all appear to be the same type of data as the CamVid stuff.
(https://blog.playment.io/self-driving-car-datasets-semantic-segmentation/)
It is not a course with a capstone… You learn what they teach and try to apply it to an area you already know a lot about. You should then spread the news in your industry. Or you practice a lot of past kaggle competitions.
After the model is trained, its output is always one of the pre-defined categories. Wondering how the model can generate an “I don’t know output”. For example if we give it a picture of chicken or fish (while the model is trained to give us the cat/dog breeds), it could generate an output saying that it cannot find a suitable category among the predefined ones rather than giving us a wrong dog/cat type.
Or perhaps we should train the model differently. Appreciate some help on this.
Hi everyone! Slowly but surely making my way through the course. If anyone has any other areas that I can chat with people, let me know! Trying to find my AI/DL tribe!
try this one: Part 1, online study group
and there are other active study groups, just search in the forum. Good luck!
Oh awesome! Thanks Christian!
Fastai mainly focuses on deep learning and neural nets. Is it possible to use Fast.ai API for other ML methods such SVM, K-means, SGboost, etc?
Thanks fast.ai (@sgugger, @rachel, @jeremy) for your work on these lectures (and the library of course). Just wrapped up Part 1 of the course and my notes are here: https://sites.google.com/view/raybellwaves/courses/fast-ai
Heya I’m an enterprise sales rep interested in ML. I’ve never done any coding, and I’m wondering: what is the best way to get the 1 year required experience for Fast.ai?
Thanks!
Hi Jeremy/all,
I would like to what’s the average training time for the course projects and whether it would be necessary to use TPUs?
I am working to collect a list of projects that suffer from long training times and technique toward accelerating them.
Best,
Mahdi
Hi WeWalk hope you are well!
The above link has many free tutorials. If I were in your position I would complete two of the tutorials/courses typing in the code by hand absolutely no cutting and pasting. I would especially choose a course that has a web part where you deploy an app online.
Once I have competed the above I would create my own app and deploy it using GitHub and Docker.
When all the above was complete I would start the fastai course.
Jeremy recommends typing all the notebooks by hand when you start and checking how much you can remember especially the main stages.
One of the many people who inspire me on this site is the person who wrote this post. How do you... learn? (and study) - #6 by Brainkite
His output is prolific.
If you do most of the above I am sure you will find the whole course/journey inspiring.
Cheers mrfabulous1 
Hi Everyone,
I just needed a clarification on how we should run our jupyter notebook when we have a bigproject, for example currently I have to run my code again from the beginning each time I start the notebook.
I am currently at the lesson 2 and trying with my own dataset, I have been working on it for a few days, but everytime I need to start from beginning like downloading the urls. Is there any thing that I can do about this?
I am new in deep learning, hope I come out better from this course!
Happy new year everyone!
I am so pumped up right now after listening to first lecture. I have couple projects in my mind. Wish me good luck to make it happen.
love u
