Object detection using fastai v2

Part 1 (2019)
1

Hi All,

Can someone please point me to any resources regarding this?

Sincerely,
Vishal

3 Likes
2

Hi vahuja4 hope your having a fantastic day!

Obect detection in fastai2 is covered in the course below.

There is a notebook you can look at as well!

Hope this helps.

Cheers mrfabulous1 :smiley::smiley:

1 Like
3

Not quite :wink: I’ll update that notebook here in the next few weeks

1 Like
4

HI muellerzr
Oops! apologies just remembered fastai2 changes daily with braking changes.!
mrfabulous1 :smiley::smiley:

5

@vahuja4 give me a day or two and I’ll get a working example.

6

Hi!
I successfully ran your notebook for detection up to training, but I am struggling to get predictions on new images. Do you have a working example? Thanks!

7

I’m still working on inference for that notebook. Will be done by next Wednesday

8

Thanks a lot!

9

Good news, I played with the notebook a bit but couldn’t get show_results and mAP metrics working (I only spend an hour or so).

Let me know if I can help at all, I want to try the dilated xresnet I’m working on with object detection (in initial experiments dilation doesn’t improve segmentation with dynamic unet)

10

If you want to put a PR at the end showing it it’d be much appreciated! :slight_smile:

11

Hi @muellerzr thanks so much for the notebook. Just a quick question: why didn’t you use the get_annotations method? seems well suited for this and I currently struggle to get it working with the rest of your notebook. Is that why?

12

I did, you can see we build on this once we go into img2bbox

13

my bad, got it now. it looked like you used something custom.

really thanks for the notebook!

14

It’ll be explained in next weeks WWF2 :wink:

15

awesome, btw I was looking at lesson5 and it still says Waiting for Zachary Mueller February 12, 2020 at 11:00 PM

Is that delayed then? No worries :slight_smile:

16

Yes, if you check the most recent post life got busy, I posted when I’ll go live again for lesson 5 today :slight_smile:

17

Is the inference part ready yet??

18

@NavneetSajwan no, not fully. I have been busy with my college classes, the study group, and other responsibilities and could not get to it by last night. It’s partially working if you want to explore the code. It’s in inference.py. There will be bugs with it. And I’m unsure when exactly I will be able to work on it.

19

Thanks, I will look into inference.py

20

@NavneetSajwan Fair warning: I won’t be able to debug anything for a few days to assist with it at all until I get a few other things done. It’s low on my totem pole.