Commit
·
686cf88
1
Parent(s):
0db6a31
Update README.md
Browse files
README.md
CHANGED
|
@@ -6,7 +6,7 @@ license: mit
|
|
| 6 |
|
| 7 |
## Method 1: Run Inference using `nnunet_predict.py`
|
| 8 |
|
| 9 |
-
1. Install
|
| 10 |
|
| 11 |
```shell
|
| 12 |
user@machine:~/ascites_segmentation$ pip install torch torchvision torchaudio nnunet matplotlib
|
|
@@ -45,50 +45,13 @@ N.B.
|
|
| 45 |
|
| 46 |
## Method 2: Run Inference using `nnUNet_predict` from shell
|
| 47 |
|
| 48 |
-
1. Install
|
| 49 |
|
| 50 |
```shell
|
| 51 |
user@machine:~/ascites_segmentation$ pip install torch torchvision torchaudio nnunet matplotlib
|
| 52 |
```
|
| 53 |
|
| 54 |
-
2.
|
| 55 |
-
|
| 56 |
-
```shell
|
| 57 |
-
user@machine:~/ascites_segmentation$ tree .
|
| 58 |
-
.
|
| 59 |
-
├── nnUNet_preprocessed
|
| 60 |
-
├── nnUNet_raw_data_base
|
| 61 |
-
└── nnUNet_trained_models
|
| 62 |
-
└── nnUNet
|
| 63 |
-
└── 3d_fullres
|
| 64 |
-
└── Task505_TCGA-OV
|
| 65 |
-
└── nnUNetTrainerV2__nnUNetPlansv2.1
|
| 66 |
-
├── fold_0
|
| 67 |
-
│ ├── debug.json
|
| 68 |
-
│ ├── model_final_checkpoint.model
|
| 69 |
-
│ ├── model_final_checkpoint.model.pkl
|
| 70 |
-
│ └── progress.png
|
| 71 |
-
├── fold_1
|
| 72 |
-
│ ├── debug.json
|
| 73 |
-
│ ├── model_final_checkpoint.model
|
| 74 |
-
│ ├── model_final_checkpoint.model.pkl
|
| 75 |
-
│ └── progress.png
|
| 76 |
-
├── fold_2
|
| 77 |
-
│ ├── model_final_checkpoint.model
|
| 78 |
-
│ ├── model_final_checkpoint.model.pkl
|
| 79 |
-
│ └── progress.png
|
| 80 |
-
├── fold_3
|
| 81 |
-
│ ├── model_final_checkpoint.model
|
| 82 |
-
│ ├── model_final_checkpoint.model.pkl
|
| 83 |
-
│ └── progress.png
|
| 84 |
-
├── fold_4
|
| 85 |
-
│ ├── model_final_checkpoint.model
|
| 86 |
-
│ ├── model_final_checkpoint.model.pkl
|
| 87 |
-
│ └── progress.png
|
| 88 |
-
└── plans.pkl
|
| 89 |
-
```
|
| 90 |
-
|
| 91 |
-
3. Setup environment variables so that nnU-Net knows where to find trained models:
|
| 92 |
|
| 93 |
```shell
|
| 94 |
user@machine:~/ascites_segmentation$ export nnUNet_raw_data_base="/absolute/path/to/nnUNet_raw_data_base"
|
|
@@ -96,7 +59,7 @@ user@machine:~/ascites_segmentation$ export nnUNet_preprocessed="/absolute/path/
|
|
| 96 |
user@machine:~/ascites_segmentation$ export RESULTS_FOLDER="/absolute/path/to/nnUNet_trained_models"
|
| 97 |
```
|
| 98 |
|
| 99 |
-
|
| 100 |
|
| 101 |
```shell
|
| 102 |
user@machine:~/ascites_segmentation$ nnUNet_predict -i INPUT_FOLDER -o OUTPUT_FOLDER -t 505 -m 3d_fullres -f N --save_npz
|
|
|
|
| 6 |
|
| 7 |
## Method 1: Run Inference using `nnunet_predict.py`
|
| 8 |
|
| 9 |
+
1. Install [nnUNet_v1](https://github.com/MIC-DKFZ/nnUNet/tree/nnunetv1#installation) and [PyTorch](https://pytorch.org/get-started/locally/).
|
| 10 |
|
| 11 |
```shell
|
| 12 |
user@machine:~/ascites_segmentation$ pip install torch torchvision torchaudio nnunet matplotlib
|
|
|
|
| 45 |
|
| 46 |
## Method 2: Run Inference using `nnUNet_predict` from shell
|
| 47 |
|
| 48 |
+
1. Install [nnUNet_v1](https://github.com/MIC-DKFZ/nnUNet/tree/nnunetv1#installation) and [PyTorch](https://pytorch.org/get-started/locally/).
|
| 49 |
|
| 50 |
```shell
|
| 51 |
user@machine:~/ascites_segmentation$ pip install torch torchvision torchaudio nnunet matplotlib
|
| 52 |
```
|
| 53 |
|
| 54 |
+
2. Setup environment variables so that nnU-Net knows where to find trained models:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 55 |
|
| 56 |
```shell
|
| 57 |
user@machine:~/ascites_segmentation$ export nnUNet_raw_data_base="/absolute/path/to/nnUNet_raw_data_base"
|
|
|
|
| 59 |
user@machine:~/ascites_segmentation$ export RESULTS_FOLDER="/absolute/path/to/nnUNet_trained_models"
|
| 60 |
```
|
| 61 |
|
| 62 |
+
3. Run inference with command:
|
| 63 |
|
| 64 |
```shell
|
| 65 |
user@machine:~/ascites_segmentation$ nnUNet_predict -i INPUT_FOLDER -o OUTPUT_FOLDER -t 505 -m 3d_fullres -f N --save_npz
|