[
DeepCV is mainly a collection of some current classical and popular networks in the field of computer vision, including target detection, image segmentation, image classification, etc.
The main goals of DeepCV:
Easy to use, newbies can get hands dirty with deep learning quickly Good performance with web-scale data Easy to extend, Modular architecture let you build your Neural network like playing LEGO! Let's Get Started!
| Model | Paper |
|---|---|
| faster rcnn | Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks (https://arxiv.org/abs/1506.01497) |
| Yolov3 | YOLOv3: An Incremental Improvement (https://pjreddie.com/media/files/papers/YOLOv3.pdf) |
| Yolov4 | YOLOv4: Optimal Speed and Accuracy of Object Detection (https://arxiv.org/abs/2004.10934) |
| Yolox | None |