Added Development info in README
Browse files
README.md
CHANGED
|
@@ -69,10 +69,39 @@ To access the live demo, click on the `Hugging Face` badge above. Below is a sna
|
|
| 69 |
|
| 70 |
<img width="1794" alt="Screenshot 2023-10-21 at 21 49 17" src="https://github.com/jpdefrutos/DDMR/assets/29090665/8d16160b-416d-40ed-a7d6-619c7360c696">
|
| 71 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 72 |
|
| 73 |
## 🏋️♂️ Training
|
| 74 |
|
| 75 |
-
Use the "MultiTrain" scripts to launch the trainings, providing the neccesary parameters. Those in the COMET folder accepts a
|
| 76 |
|
| 77 |
For instance:
|
| 78 |
```
|
|
@@ -81,7 +110,7 @@ python TrainingScripts/Train_3d.py
|
|
| 81 |
|
| 82 |
## 🔍 Evaluate
|
| 83 |
|
| 84 |
-
Use Evaluate_network to test the trained models. On the Brain folder, use
|
| 85 |
|
| 86 |
For instance:
|
| 87 |
```
|
|
|
|
| 69 |
|
| 70 |
<img width="1794" alt="Screenshot 2023-10-21 at 21 49 17" src="https://github.com/jpdefrutos/DDMR/assets/29090665/8d16160b-416d-40ed-a7d6-619c7360c696">
|
| 71 |
|
| 72 |
+
<details>
|
| 73 |
+
<summary>
|
| 74 |
+
|
| 75 |
+
### Development</summary>
|
| 76 |
+
|
| 77 |
+
To develop the Gradio app locally, you can use either Python or Docker.
|
| 78 |
+
|
| 79 |
+
#### Python
|
| 80 |
+
|
| 81 |
+
You can run the app locally by:
|
| 82 |
+
|
| 83 |
+
```
|
| 84 |
+
python demo/app.py --cwd ./ --share 0
|
| 85 |
+
```
|
| 86 |
+
|
| 87 |
+
Then open `http://127.0.0.1:7860` in your favourite internet browser to view the demo.
|
| 88 |
+
|
| 89 |
+
#### Docker
|
| 90 |
+
|
| 91 |
+
Alternatively, you can use docker:
|
| 92 |
+
|
| 93 |
+
```
|
| 94 |
+
docker build -t ddmr .
|
| 95 |
+
docker run -it -p 7860:7860 ddmr
|
| 96 |
+
```
|
| 97 |
+
|
| 98 |
+
Then open `http://127.0.0.1:7860` in your favourite internet browser to view the demo.
|
| 99 |
+
|
| 100 |
+
</details>
|
| 101 |
|
| 102 |
## 🏋️♂️ Training
|
| 103 |
|
| 104 |
+
Use the "MultiTrain" scripts to launch the trainings, providing the neccesary parameters. Those in the COMET folder accepts a `.ini` configuration file (see `COMET/train_config_files/` for example configurations).
|
| 105 |
|
| 106 |
For instance:
|
| 107 |
```
|
|
|
|
| 110 |
|
| 111 |
## 🔍 Evaluate
|
| 112 |
|
| 113 |
+
Use Evaluate_network to test the trained models. On the Brain folder, use `Evaluate_network__test_fixed.py` instead.
|
| 114 |
|
| 115 |
For instance:
|
| 116 |
```
|