Anh Nguyen

huh, you need around 6.xx GB ram for testing this full AffordanceNet. I'll release a smaller version soon. You can also use CPU to test some images. It's just slower...

The segmentation groundtruth from Pascal dataset is only binary. If you don't care about the object parts/affordances, then you can simply just treat all masks equally. In this case, it...

If you don't care about the object parts, then in your mask groundtruth, you'll have only 2 classes (background + foreground). If you prepare your data correctly, then AffordanceNet code...

There are two kind of groundtruths in our system: - The object bounding box: defined as a rectangle with top-left (xmin, ymin) and bottom-right (xmax, ymax) coordinates. - The multiclass...

Hi, 1. In general, the results of Label Me (or any tools such as [this one](https://github.com/wkentaro/labelme)) will be saved in a particular format. You should check the Readme of each...

Great to hear that!

The object class and the affordance class are not the same since they're defined separately. The object categories refer to the whole object (e.g., _pan_, _bottle_, _hammer_), while the affordace...

The process looks ok to me. But maybe something wrong in one of your step. 1. Make sure you have the **correct** label ID in the PNG file (you can...

You can download the original version of the [IIT-AFF dataset](https://sites.google.com/site/iitaffdataset/). The IDs are in the ReadMe file.

Yes, you can do it if you want. I think "uint16" will work fine too.