Implementation of top-down bottom-up attentional modules on top of Swin Transformer object detection network.
Single image test
python -m swin_td_bu_att demo.jpg configs/td_bu_attention/topdown_bottomup_attentional_swin.py swin_tiny_patch4_window7_224.pth --device cuda --out-file result.jpg
Evaluate all test set:
python swin_td_bu_att/eval.py
python swin_td_bu_att/train.py
- Implement modules
- Implement functioning test code
- Fix training parameters in config file
- Implement missing training functionality
- Decrease the training loss