I am trying to implement the Faster RCNN on identifying the airplane from the image. I stuck at implementing Region Proposal Network(RPN). How can I implement RPN and train them to produce bounding box proposal using python script?
Asked
Active
Viewed 1,656 times
-1
-
Are you sure you want to re-implement it rather than using a `torchvision` model (or the `Keras` equivalent) like this: https://pytorch.org/tutorials/intermediate/torchvision_tutorial.html#finetuning-from-a-pretrained-model – TC Arlen Aug 11 '21 at 03:18
1 Answers
0
There are plenty of ready-to-use implementations of various neural networks including Faster RCNN. Consider using DL frameworks such as Pytorch or Keras. For example, see this Pytorch tutorial on fine-tuning the Mask R-CNN model.
Faster RCNN is a two-stage object detection model. Where the first stage is an RPN (Region Proposal Network), and the second is a classifier. For your task, you can ignore the second part if you don't need it.
Some implementations:
NesteruS
- 64
- 3