Deep Learning with OpenMMLab
OpenMMLab builds the most influential open-source computer vision algorithm system in the deep learning era. Based on PyTorch, OpenMMLab develops MMEngine to provide universal training and evaluation engine, and MMCV to provide neural network operators and data transforms, which serves as a foundation of the whole project. Since the initial release in October 2018, OpenMMLab has released 30+ vision libraries, has implemented 300+ algorithms, and contains 2000+ pre-trained models.
Detect and Classify
MMDetection is an open source object detection toolbox based on PyTorch. It is a part of the OpenMMLab project.Now, pre-trained weights for MM-Grounding-DINO Swin-B and Swin-L have been released.
Go to MMDetection
Mask-RCNN
The method, called Mask R-CNN, extends Faster R-CNN by adding a branch for predicting an object mask in parallel with the existing branch for bounding box recognition. Mask R-CNN is simple to train and adds only a small overhead to Faster R-CNN, running at 5 fps. Moreover, Mask R-CNN is easy to generalize to other tasks, e.g., allowing us to estimate human poses in the same framework. We show top results in all three tracks of the COCO suite of challenges, including instance segmentation, bounding-box object detection, and person keypoint detection.
Go to Mask-RCNN
MMSegmentation
MMSegmentation is an open source semantic segmentation toolbox based on PyTorch. It is a part of the OpenMMLab project. MMSegmentation v1.x brings remarkable improvements over the 0.x release, offering a more flexible and feature-packed experience.
Go to MMSegmentation