FastAI beats academic research performance in Indoor Scene Recognition?
For Lesson 01, I took the indoorCVPR dataset (A. Quattoni, and A.Torralba. Recognizing Indoor Scenes. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2009.) which tries to classify among 67 indoor scenes.
This is my first time reading through an academic research paper on this topic. But it looks like their best performance was 73.4% accuracy. After applying the Lesson 01, I was able to get an accuracy of 77.0%! If I’m misinterpreting the paper, please let me know!
I posted my notebook on GitHub and I would greatly appreciate any peer-review with how I set it up. I would be grateful to learn from your experience!
Also, although I was happy that the performance was better than the reported performance in the paper, I was a bit disappointed that I was not able to achieve the same type of accuracy as Jeremy showed in the lecture. I really wanted the error_rate to be in the single digits percentage. But looking at the error_rate plot, it seems to start to level out around 0.2. I suppose this is due to the nature of the dataset. However, if you notice anything that I can improve on, I would be happy to hear!
Well, it’s better, but you are comparing with a 2009 paper, before the spread of CNNs, which gave a general boost to classification performance. To have an idea of the state-of-the-art, I would search for more recent papers citing this one. E.g., in https://arxiv.org/pdf/1801.06867.pdf 86% is reached, however you have to read details to understand if it is fully comparable with the original paper.
Improved version but not enough.
It is recoloring image from black and white.
Input Black and White,----------------------------Output color,----------------------------Correct Color
Below is before imrpoving, so we can see it solved the fuzz eyes problem. (or it can be fixed by training with more epos, I am not sure. If it can, plz tell me because I can only train with very few epos on colab)
In addition, if you look below, it can not recolor those bow-knot and
hair accessories before improvement. Or I don’t call a improvement. It should be a trick from a dum guy.
Before I try to improve it with no large data set it can not color hair accessories, bow-knot, and more. But now it can improve bow-knot. It seems it does not really need to use larger data set to color smaller items. I can select what object to be colored. But it is still unable to recognize many objects other than people.
I think I will stop this project for a monument because I won’t have time for this.
Just wanted to share a blog post about an app my team members and I worked on at a hackathon this past weekend. Our project uses fastai to detect whether or not you are getting distracted while studying using your webcam feed.
Badminton or Tennis Image Classification with 50 images
Hi Friends!
I have made an image dataset by collecting 50 images each of Tennis & Badminton game in action by downloading images from google and created an image classification model using chapter 1. The accuracy of my classification model is 85%.
The images which it did not predict correctly are as below:
I created a classifier to classify between a passenger aircraft and fighter jet following lesson-2 notebook and deployed it to azure container instance.
Only able to get it to 80% accuracy, and fine tuning does not improve the score, but still, this is pretty good since a human wouldn’t be able to do it this well.
I am loving this fast ai course by Jermy I have made my own Drone classifier using fast ai and have deployed it on render.Drone Classifier Please take a look int it
My Drone Classifier take in drone image and classifies whether it is
1)Singlerotor Drone
2)Multirotor Drone
3)Fixedwing Drone
And Outputs the class of the Drone
I had a look at your app and really like the way you have designed an app with a little privacy in mind. It makes a refreshing change from the majority of apps that are in reallity nothing but data gathering apps!
Taking inspiration from the part-1 course I have tried to explain the high level structure of a CNN in a beginner friendly way. I have tried not to delve into all the minute technical details of a CNN. The blog can be found here
I have created a model using fast ai for plant disease detection. With just fine tuning the learning rate i achieved an accuracy of 99.1 percent while the state of art is 97 %. I did not even use the deeper networks like resnet 50. i just used resent 34.
Btw do you know how can I get access to plant village dataset I came to know it’s no longer public . I mailed them regarding the dataset but no reply yet .it would be helpful if you can point me to the dataset