Good to see Époisses there - you better add Pont-l’Évêque and Langres too now! 
2 Likes
Would be cool to extend with an artificial nose. https://www.microsoft.com/en-us/ai/ai-lab-artificial-nose
I’m sure it would do better than the poor old Cheeseoid robot.
Hi again!
I wrote out the process i used to create the blog.
Let me know if there’s anything there that doesn’t make sense.
Hope it helps!
8 Likes
This is perfect! Thanks for sharing this. I will try to set it up and let you know.
2 Likes
Fantastic! Thanks so much for sharing.
2 Likes
Just finished playing with lesson 1 notebooks, and I realized I had a real use case for what I learned so far: I’ve recently installed a trail camera near where I live, and going through literally thousands of photos each week to see if there’s an animal got boring really fast. I tried my luck with training a model to recognize when photos were interesting (ie: they contain an animal), and got pretty good results!
The model was so good it even found animals I had missed!
Looking forward to trying the model with a new batch of photos next time I go look for the camera’s photos!
extra:
I then tried the model with two pictures outside of the dataset: photos I took myself with my phone. The results were correct! (in one case it detected my dog, in the other, no animals were present)
----
I’m really excited to get results on my first week, looking forward to continuing to improve the model as I learn more stuff!! Amazing course
extra 2:
For some reason, I couldn’t get ImageClassifierCleaner to work on Paperspace. When I changed values with the dropdown, nothing changed on the interface. Any ideas on what I could be doing wrong? I tried it both on the “vanilla” JupyterLab interface and on the modern Paperspace interface with no luck. Thanks in advance!
update! Nevermind, I fixed it by adding import ipywidgets as widgets, as @jeffbiss explains here: Name 'widgets' is not defined & taking lot of time to run the fastbook ch-1 on colab - #8 by jeffbiss
9 Likes
Yayyyyyyyyy…I did it 
!
Here it is. Thanks so much. The guide was so smooth.
PS: Some pages are empty, yet to work on the content and other stuff, Will put on the main thread once it is done.
Thanks again 
.
4 Likes
Wow that looks amazing!
Great work!
1 Like
I was just thinking of picking up a surface laptop.
Hi all 
!
I have created my website using Quarto. Here it is.
I am sharing my notes from it:
Few thoughts:
- Writing these notes have pushed me to complete the lesson 100%. I thought I had finished Lesson 1 in my “head” a few days ago. It was not until I started to write these notes, I realized some important bits were missing and I had not grasped it fully.
- I got stuck a lot in the whole process- issues with installing, Quarto, etc. I asked for help on the forums, (here and on Quarto’s). I was surprised to find how supporting the community is. I heard Jeremy say this, but I experienced it myself. It developed a deep sense of gratitude towards all of them. I intend to give back by helping others a few months from now.
Special thanks to @afshan22 for helping in publishing the website. This blog helped me!
7 Likes
This is really cool I had heard several people talking about using nbdev and Quarto to blog and to show results from experiments etc. but it’s great to see that in action. I’m kind of leaning towards trying this myself and/or somehow integrating this approach with my existing blog. Seeing your blog made me want to look into this further …
Also, kudos on wanting to pass it on. Can’t say how much I appreciate that attitude!
3 Likes
Created an image classifier to detect if fruit is rotten or fresh, based on what I learned from Week 1. Here is a link to a blog post I wrote about it.
Just finished watching the lecture videos for Week 2. There’s so much that I want to try out and write about, or use to build my own little projects. The course is amazing till now.
4 Likes
I am currently undertaking Practical Deep Learning for Coders by fastai . I finished Lesson 1 and built a face mask detector model suitable for surveillance and health safety. Model worked pretty well!
I needed to apply minor tweaks to the standard template. I increased the size of the dataset to lower variance . Also choosing a good phrase for the image search terms was a little tricky! I tried many parameters but most of the standard ones provided by Jeremy worked very well
The testing images are all challenging. I challenged the model using side images. People with dense facial hair. A low quality hooded image and even different coloured face masks. The model with reasonable accuracy was able to work through everything and predict correctly
^^ for full blog on it. Many testing examples given
5 Likes
Yayyyy…
I deployed my first DL model using concepts taught in Lesson 2. Here it is. It classifies the 3 fastest creatures on the planet.
Learnt so much in the last few days .
I love this course 
! fast.ai rocks!!
6 Likes
Even my website runs on quarto. https://aayushmnit.com/
Code you can find the here - GitHub - aayushmnit/aayushmnit.github.io: Code for my website.
Feel free to copy the style settings if that is helpful. I found looking at open source code of other websites built on quarto useful to customize my own.
4 Likes
Thanks @aayushmnit Much appreciated! Will take a look next weekend (hopefully). The trouble with doing Stable Diffusion stuff (at least for me) is that that seems to consume all my time …
1 Like
Hey!
I have created an image classifier which tells you the breed of your dog. Wanted to host on web. Don’t know web-dev so used Anvil, got stuck hence just sharing the link of the Kaggle notebook.
1 Like
can this library be used for object detection models too?
Also, I can’t find any GRADCAM implementation of the object detection model in fastai.
It would be constructive if anyone knows any relevant code for implementing the same.
Here is my Alien vs. Ghost classifier.
This could have been very good if I did it before the Halloween, but it is here at last.
It was very fun to create this, and I may try to make an actual website using the API and Javascript. Maybe.
5 Likes