so i built a natural disaster classification model using transfer learning Renet50(tensor flow) got 98% accuracy and now instead of just classifying natural disaster lets say a cyclone appeared in the video, i want to draw a bounding box around it. i read that yolo and FRCNN are good for object detection but up on searching i found out that we have to train images again on yolo or FRCNN network and for that data set needs to have labels with bounding box coordinates.

so may i know that is it possible to draw bounding boxes using classification model i have built...? can i just classify images from my model and send it to yolo or FRCNN just to predict the bounding box coordinates... is it possible..? or is there any other algorithm...? and my data set only contains images and labels, so do i need to have box coordinates in the dataset for object detection...?


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.