Category: Transformer

In this article, we carry out the pretraining of the Faster RCNN ViT detection model on the Pascal VOC object detection dataset. ...

In this article, we train Vision Transformer on a simple malaria classification dataset, run inference, and visualize attention maps. ...

In this article, we fine fine DETR (Detection Transformer) models on a custom aquarium dataset. After training, we also run inference on the test dataset and unseen videos. ...

In this article, we explore the DETR model for object detection. Along with a short discussion of the model architecture, we also carry out inference on videos. ...