Prompt-based Grouping Transformer for Nucleus Detection and Classification
-python=3.8
-pytorch=1.12.1+cu102
Install mmcv using mim
pip install -U openmim
mim install mmcv-full==1.6.1
Git clone acformer
git clone https://github.com/LL3RD/PGT.git
Install
cd PGT
cd thirdparty/mmdetection
python -m pip install -e .
cd ../..
python -m pip install -e .
Your can download 20x CoNSeP Dataset and Checkpoint from here.
Method | F1d | F1c | Model Weights | Config Files |
---|---|---|---|---|
PGT | 0.738 | 0.613 | Checkpoint | Config |
Your can download BRCA Dataset and Checkpoint from here.
Method | F1d | F1c | Model Weights | Config Files |
---|---|---|---|---|
PGT | 0.799 | 0.523 | Checkpoint | Config |
Your can download Original Lizard from the official website or Preprocessed Lizard and Checkpoint that is converted to hovernet consep format and split into patches.
Method | F1d | F1c | Model Weights | Config Files |
---|---|---|---|---|
PGT | 0.779 | 0.538 | Checkpoint | Config |
The training contains two phases, In the pre-tuning phase, modify your dataset path in configs/Swin_BRCA.py and run
CUDA_VISIBLE_DEVICES=0 bash tools/dist_train.sh configs/Swin_BRCA.py 1 --work-dir=Path_to_your_work_dir
Then modify the load_from path in configs/Swin_BRCA_PGT.py and run
CUDA_VISIBLE_DEVICES=0 bash tools/dist_train.sh configs/Swin_BRCA_PGT.py 1 --work-dir=Path_to_your_work_dir
Modify your dataset path and checkpoint path in tools/inference and run
python tools/inference/inference_CoNSeP_group.py
python tools/inference/inference_BRCA_group.py
python tools/inference/inference_Lizard_group.py
- PGT is built based on SoftTeacher and MMDetection.