dl4eo/Oriented_R-CNN_pretrained_on_DOTA_1.0

Model Card for Oriented R-CNN pretrained on DOTA 1.0

The original paper is Oriented R-CNN for Object Detection.

This implementation of this model has been developed by OpenMMLab in the MMRotate framework.

The model has been trained on DOTA 1.0

The performance measured as mAP is 75.69.

• Developed by: OpenMMLab
• Model type: Object Detection model
• License: cc-by-nc-sa-4.0
• Resources for more information: More information needed
  • GitHub Repo
  • Associated Paper

How to Get Started with the Model

Use the code below to get started with the model.

from mmdet.apis import init_detector, inference_detector
import mmrotate

config_file = 'oriented_rcnn_r50_fpn_1x_dota_le90.py'
checkpoint_file = 'oriented_rcnn_r50_fpn_1x_dota_le90-6d2b2ce0.pth'
model = init_detector(config_file, checkpoint_file, device='cuda:0')
inference_detector(model, 'demo/demo.jpg')