monai
medical
katielink commited on
Commit
c0c50b7
1 Parent(s): dd84920

unify dataset dir in different configs

Browse files
README.md CHANGED
@@ -27,11 +27,7 @@ An example result from inference is shown below:
27
  **This is a demonstration network meant to just show the training process for this sort of network with MONAI. To achieve better performance, users need to use larger dataset like [Brats 2021](https://www.synapse.org/#!Synapse:syn25829067/wiki/610865) and have GPU with memory larger than 32G to enable larger networks and attention layers.**
28
 
29
  ## MONAI Generative Model Dependencies
30
- [MONAI generative models](https://github.com/Project-MONAI/GenerativeModels) can be installed by
31
- ```
32
- pip install lpips==0.1.4
33
- pip install git+https://github.com/Project-MONAI/GenerativeModels.git@0.2.1
34
- ```
35
 
36
  ## Data
37
  The training data is BraTS 2016 and 2017 from the Medical Segmentation Decathalon. Users can find more details on the dataset (`Task01_BrainTumour`) at http://medicaldecathlon.com/.
 
27
  **This is a demonstration network meant to just show the training process for this sort of network with MONAI. To achieve better performance, users need to use larger dataset like [Brats 2021](https://www.synapse.org/#!Synapse:syn25829067/wiki/610865) and have GPU with memory larger than 32G to enable larger networks and attention layers.**
28
 
29
  ## MONAI Generative Model Dependencies
30
+ This bundle requires to install [MONAI generative models](https://github.com/Project-MONAI/GenerativeModels).
 
 
 
 
31
 
32
  ## Data
33
  The training data is BraTS 2016 and 2017 from the Medical Segmentation Decathalon. Users can find more details on the dataset (`Task01_BrainTumour`) at http://medicaldecathlon.com/.
configs/inference_autoencoder.json CHANGED
@@ -6,7 +6,7 @@
6
  ],
7
  "bundle_root": ".",
8
  "model_dir": "$@bundle_root + '/models'",
9
- "dataset_dir": "@bundle_root",
10
  "output_dir": "$@bundle_root + '/output'",
11
  "create_output_dir": "$Path(@output_dir).mkdir(exist_ok=True)",
12
  "device": "$torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')",
 
6
  ],
7
  "bundle_root": ".",
8
  "model_dir": "$@bundle_root + '/models'",
9
+ "dataset_dir": "/workspace/data/medical",
10
  "output_dir": "$@bundle_root + '/output'",
11
  "create_output_dir": "$Path(@output_dir).mkdir(exist_ok=True)",
12
  "device": "$torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')",
configs/metadata.json CHANGED
@@ -1,7 +1,8 @@
1
  {
2
  "schema": "https://github.com/Project-MONAI/MONAI-extra-test-data/releases/download/0.8.1/meta_schema_generator_ldm_20230507.json",
3
- "version": "1.0.1",
4
  "changelog": {
 
5
  "1.0.1": "update dependency, update trained model weights",
6
  "1.0.0": "Initial release"
7
  },
 
1
  {
2
  "schema": "https://github.com/Project-MONAI/MONAI-extra-test-data/releases/download/0.8.1/meta_schema_generator_ldm_20230507.json",
3
+ "version": "1.0.2",
4
  "changelog": {
5
+ "1.0.2": "unify dataset dir in different configs",
6
  "1.0.1": "update dependency, update trained model weights",
7
  "1.0.0": "Initial release"
8
  },
docs/README.md CHANGED
@@ -20,11 +20,7 @@ An example result from inference is shown below:
20
  **This is a demonstration network meant to just show the training process for this sort of network with MONAI. To achieve better performance, users need to use larger dataset like [Brats 2021](https://www.synapse.org/#!Synapse:syn25829067/wiki/610865) and have GPU with memory larger than 32G to enable larger networks and attention layers.**
21
 
22
  ## MONAI Generative Model Dependencies
23
- [MONAI generative models](https://github.com/Project-MONAI/GenerativeModels) can be installed by
24
- ```
25
- pip install lpips==0.1.4
26
- pip install git+https://github.com/Project-MONAI/GenerativeModels.git@0.2.1
27
- ```
28
 
29
  ## Data
30
  The training data is BraTS 2016 and 2017 from the Medical Segmentation Decathalon. Users can find more details on the dataset (`Task01_BrainTumour`) at http://medicaldecathlon.com/.
 
20
  **This is a demonstration network meant to just show the training process for this sort of network with MONAI. To achieve better performance, users need to use larger dataset like [Brats 2021](https://www.synapse.org/#!Synapse:syn25829067/wiki/610865) and have GPU with memory larger than 32G to enable larger networks and attention layers.**
21
 
22
  ## MONAI Generative Model Dependencies
23
+ This bundle requires to install [MONAI generative models](https://github.com/Project-MONAI/GenerativeModels).
 
 
 
 
24
 
25
  ## Data
26
  The training data is BraTS 2016 and 2017 from the Medical Segmentation Decathalon. Users can find more details on the dataset (`Task01_BrainTumour`) at http://medicaldecathlon.com/.