This is a Faster-RCNN with FPN and relation network based on Torchvision.
This folder contains the training scripts for object detection, Faster-RCNN with FPN model, Relation Network and evaluation scripts.
- add Relation Network between two fully connected layers in RoI head
- end to end train this model on COCO 2014
- evaluate mAP based on COCO evaluation tools
- replace NMS by Relation Network
- improve the performance (Current mAP: 36)
- Python 3.6
- Pytorch 1.4.1 and Torchvision
- The Python packages:
cython
pycocotools
matplotlib
Please download the COCO Dataset.
You must modify the following flags:
--data-path=/path/to/coco/dataset
--nproc_per_node=<number_of_gpus_available>
Data-path is the path of dataset.
nproc_per_node is the number of GPUs.
Train script is below, the backbone is Resnet 101:
python -m torch.distributed.launch --nproc_per_node=4 --use_env train.py\
--dataset coco --model fasterrcnn_resnet101_fpn --epochs 30\
--lr-steps 16 22 --aspect-ratio-group-factor 3
This model contains {1, 1} relation network between the fully connected layers in RoI head.