+
+
+
+
+
+## TODOs
+
+- [x] Paper released
+- [x] Code released
+- [x] Slide-SAM-B weights
+- [x] Slide-SAM-H weights
+
+
+
+## Models
+
+### Large scale Medical Image Pretrained Weights
+
+| name | resolution | Prompt | Weights |
+| :---------: | :--------: | :---------: | :----------------------------------------------------------: |
+| Slide-SAM-B | 1024x1024 | box & point | [ckpt](https://pan.baidu.com/s/1jvJ2W4MK24JdpZLwPqMIfA) [code：7be9] |
+| Slide-SAM-H | 224x224 | 78.6 | [ckpt](https://pan.baidu.com/s/1jnOwyWd-M1fBIauNi3IA4w) [code: 05dy] |
+
+
+
+## Getting Started
+
+### Install tutils tools
+
```
pip install trans-utils
```
-### prepare datasets
+### Prepare datasets
+
We recommend you to convert the dataset into the nnUNet format.
+
```
00_custom_dataset
imagesTr
@@ -24,39 +86,74 @@ We recommend you to convert the dataset into the nnUNet format.
xxx.nii.gz
...
```
-try to use the function ```organize_in_nnunet_style``` or ```organize_by_names``` to prepare your custom datasets.
-Then run
-```
+Try to use the function organize in [nnunet-style]([nnUNet/documentation/dataset_format.md at master · MIC-DKFZ/nnUNet (github.com)](https://github.com/MIC-DKFZ/nnUNet/blob/master/documentation/dataset_format.md)) or ```organize_by_names``` to prepare your custom datasets.
+
+Then run :
+
+```python
python -m datasets.generate_txt
```
A ```[example]_train.txt``` will be generated in ```./datasets/dataset_list/```
The content should be like below
+
```
01_BCV-Abdomen/Training/img/img0001.nii.gz 01_BCV-Abdomen/Training/label/label0001.nii.gz
01_BCV-Abdomen/Training/img/img0002.nii.gz 01_BCV-Abdomen/Training/label/label0002.nii.gz
01_BCV-Abdomen/Training/img/img0003.nii.gz 01_BCV-Abdomen/Training/label/label0003.nii.gz
```
-### cache 3d data into slices
+### Cache 3d volume into slices
+
After generating the ```[example]_train.txt``` file, check the config file ```configs/vit_b.yaml```.
Update the params in ```dataset``` by yours. And the ```dataset_list``` should be the name of the generated txt file ```[example]```.
Then run
+
```
python -m datasets.cache_dataset3d
```
-## Training
-run training
+
+
+## Start Training
+
+Run training on multi-GPU
+
```
CUDA_VISIBLE_DEVICES=0,1,2,3 python -m core.ddp --tag debug
```
-## Testing
+
+
+## Sliding Inference and Test
+
```
python -m core.volume_predictor
```
+
+
+
+
+
+