autowebcompat

autowebcompat copied to clipboard

Label dataset

21

The labeling can be performed using the **label.py** script. This script will show you a couple of images, and then you can press 'y' to label them as being compatible,...

marco-c

This might be a future enhancement.

marco-c

Analysing false predictions

7

After trying different models, we should be able to analyze which screenshots were falsely classified. With this we might be able to find some pattern or see some models which...

sagarvijaygupta

Create final bounding_box.json file from bounding boxes of different users

9

To create final `bounding_box.json` file, I am thinking of having IOU as the basic criteria with some defined threshold with at least 50% `bounding_box.json` from the `label_persons` directory agreeing with...

sagarvijaygupta

Add other browsers

10

The more browsers we have, the more screenshots we can collect

marco-c

Tracking issue for the results of different network architectures

36

We will use this issue to track the results of the different network architectures and training methodologies. Add a comment in this issue when you are working on one of...

marco-c

label.py opens windows that are overlapping

6

There should be at least some distance between them, right now they are overlapping so I can't see the entire image.

marco-c

As considered in #227 we can discuss how to implement this idea for training here.

sagarvijaygupta

Implementing Object Segmentation networks for bounding box annotations

1

We have started work on collecting bounding box annotations for our dataset, while our bounding-box labeled dataset maybe small. I think we should start thinking about implementing Object segmentation networks...

Shashi456

https://github.com/marco-c/autowebcompat/issues/264 is about trying to train a (shallow) network on the output of a DOM-based tool. This issue is about augmenting the CNN with data from the DOM-based tool.

marco-c