I write this subject, about transformer for image detection, to obtain some information. I would like to apply transformers architecture to classify some images considering only two targets (0 and 1). Already I have dataset classified manually. I have read some article about VIT and I have seen some script, but also I have seen also DETR and DETECTRON. Maybe there is some lecture most precision about this theme. Someone have other tips/suggestions because there are some part not clearer for me.
Asked
Active
Viewed 20 times
