Real-time Instance Segmentation with Discriminative Orientation Maps
OrienMask
This repository implements the framework OrienMask for real-time instance segmentation.
It achieves 34.8 mask AP on COCO test-dev at the speed of 42.7 FPS evaluated with a single RTX 2080Ti. (log)
Paper: Real-time Instance Segmentation with Discriminative Orientation Maps
Installation
Please see INSTALL.md to prepare the environment and dataset.
Usage
Place the pre-trained backbone (link) and trained model (link) as follows for convenience (otherwise update the corresponding path in configurations):
├── checkpoints
│ ├── pretrained
│ │ ├──pretrained_darknet53.pth
│ ├── OrienMaskAnchor4FPNPlus
│ │ ├──orienmask_yolo.pth
train
Three items should be noticed when deploying different number of GPUs: n_gpu, batch_size, accumulate. Keep in mind that the approximate batch size equals to n_gpu * batch_size * accumulate.
# multi-gpu train (n_gpu=2, batch_size=8, accumulate=1)
#