[pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

Author: pre-commit-ci[bot]

federated_learning/breast_density_challenge/.gitignore

@@ -10,4 +10,3 @@ logs
 
 # example data
 *preprocessed*
-

federated_learning/breast_density_challenge/README.md

@@ -1,6 +1,6 @@
 ## MammoFL_MICCAI2022
 
-Reference implementation for 
+Reference implementation for
 [ACR-NVIDIA-NCI Breast Density FL challenge](http://BreastDensityFL.acr.org).
 
 Held in conjunction with [MICCAI 2022](https://conferences.miccai.org/2022/en/).
@@ -14,13 +14,13 @@ We provide a minimal example of how to implement Federated Averaging using [NVFl
 
 ### 1.1 Download example data
 Follow the steps described in [./data/README.md](./data/README.md) to download an example breast density mammography dataset.
-Note, the data used in the actual challenge will be different. We do however follow the same preprocessing steps and 
+Note, the data used in the actual challenge will be different. We do however follow the same preprocessing steps and
 use the same four BI-RADS breast density classes for prediction.
 
 We provide a set of random data splits as `./data/dataset_blinded_site-*.json` which follows the same format as what
-will be used in the challenge. Please do not modify the data list filenames in the configs as they will be the same during the challenge. 
+will be used in the challenge. Please do not modify the data list filenames in the configs as they will be the same during the challenge.
 
-Note, the location of the dataset and data lists will be given by the system. 
+Note, the location of the dataset and data lists will be given by the system.
 Do not change the locations given in [config_fed_client.json](./code/configs/mammo_fedavg/config/config_fed_client.json):
 ```
   "DATASET_ROOT": "/data/preprocessed",
@@ -32,7 +32,7 @@ The argument specifies the FQDN of the FL server. Use `localhost` when simulatin
 ```
 ./build_docker.sh localhost
 ```
-Note, all code and pretrained models need to be included in the docker image. 
+Note, all code and pretrained models need to be included in the docker image.
 The virtual machines running the containers will not have public internet access during training.
 For an example, please see the `download_model.py` used to download ImageNet pretrained weights in this example.
 
@@ -44,7 +44,7 @@ Run all commands at once using. Note this will also create separate logs under `
 ```
 ./run_all_fl.sh
 ```
-Note, the GPU index to use for each client is specified inside `run_all_fl.sh`. 
+Note, the GPU index to use for each client is specified inside `run_all_fl.sh`.
 See the individual `run_docker_site-*.sh` commands described below.
 Note, the server script will automatically kill all running container used in this example
 and final results will be placed under `./result_server`.
@@ -64,10 +64,10 @@ After training completed, the training curves can be visualized using
 ```
 tensorboard --logdir=./result_server
 ```
-A visualization of the global accuracy and [Kappa](https://scikit-learn.org/stable/modules/generated/sklearn.metrics.cohen_kappa_score.html) validation scores for each site with the provided example data is shown below. 
+A visualization of the global accuracy and [Kappa](https://scikit-learn.org/stable/modules/generated/sklearn.metrics.cohen_kappa_score.html) validation scores for each site with the provided example data is shown below.
 The current setup runs on a machine with two NVIDIA GPUs with 12GB memory each.
 The runtime for this experiment is about 45 minutes.
-You can adjust the argument to the `run_docker_site-*.sh` scripts to specify different 
+You can adjust the argument to the `run_docker_site-*.sh` scripts to specify different
 GPU indices if needed in your environment.
 
 ![](./figs/example_data_val_global_acc_kappa.png)
@@ -84,10 +84,10 @@ docker kill server site-1 site-2 site-3
 
 You can modify and extend the provided example code under [./code/pt](./code/pt).
 
-You could use other components available at [NVFlare](https://github.com/NVIDIA/NVFlare) 
+You could use other components available at [NVFlare](https://github.com/NVIDIA/NVFlare)
 or enhance the training pipeline using your custom code or features of other libraries.
 
-See the [NVFlare examples](https://github.com/NVIDIA/NVFlare/tree/main/examples) for features that could be utilized in this challenge. 
+See the [NVFlare examples](https://github.com/NVIDIA/NVFlare/tree/main/examples) for features that could be utilized in this challenge.
 
 ### 2.1 Debugging the learning algorithm
 
@@ -157,7 +157,7 @@ for the global model (should be named `SRV_best_FL_global_model.pt`).
 				"probs": [0.005602597258985043, 0.7612965703010559, 0.23040543496608734, 0.0026953918859362602]
 			}, {
 			...
-    },			
+    },
 	"site-3": {
 		"SRV_best_FL_global_model.pt": {
             ...
@@ -166,5 +166,5 @@ for the global model (should be named `SRV_best_FL_global_model.pt`).
 				"probs": [0.005602597258985043, 0.7612965703010559, 0.23040543496608734, 0.0026953918859362602]
 			}, {
 			...
-    }		
+    }
 ```

federated_learning/breast_density_challenge/code/fl_project.yml

@@ -43,17 +43,17 @@ builders:
           - relaxed
       roles:
         super: super user of system
-      groups: 
-        relaxed: 
+      groups:
+        relaxed:
           desc: org group with relaxed policies
-          rules: 
+          rules:
             allow_byoc: true
             allow_custom_datalist: true
       disabled: false
   - path: nvflare.lighter.impl.cert.CertBuilder
   - path: nvflare.lighter.impl.he.HEBuilder
     args:
-      poly_modulus_degree: 8192 
+      poly_modulus_degree: 8192
       coeff_mod_bit_sizes: [60, 40, 40]
       scale_bits: 40
       scheme: CKKS

federated_learning/breast_density_challenge/code/run_fl.sh

@@ -27,4 +27,3 @@ python3 ./run_fl.py --port=8003 --admin_dir="./${workspace}/${admin_username}" \
 # sleep for FL system to shut down, so a new run can be started automatically
 sleep 30
 echo "TRAINING ENDED"
-

federated_learning/breast_density_challenge/data/README.md

@@ -6,7 +6,7 @@ Extract here.
 ## Data source
 This example data is based on [CBIS-DDSM](https://wiki.cancerimagingarchive.net/display/Public/CBIS-DDSM) from [TCIA](https://wiki.cancerimagingarchive.net/) [1].
 
-We preprocessed all files using `code/pt/utils/preprocess_dicomdir.py` and generated train/val splits for each client 
+We preprocessed all files using `code/pt/utils/preprocess_dicomdir.py` and generated train/val splits for each client
 and separate testing split.
 
 For more details on this example data, see [2,3].

federated_learning/breast_density_challenge/data/dataset_blinded_phase2_site-1.json

@@ -4452,4 +4452,4 @@
             "image": "Mass-Training_P_00630_LEFT_MLO.npy"
         }
     ]
-}
+}

federated_learning/breast_density_challenge/data/dataset_blinded_phase2_site-2.json

@@ -4317,4 +4317,4 @@
             "image": "Calc-Test_P_01303_LEFT_CC.npy"
         }
     ]
-}
+}

federated_learning/breast_density_challenge/data/dataset_blinded_phase2_site-3.json

@@ -4406,4 +4406,4 @@
             "image": "Calc-Training_P_02563_RIGHT_MLO.npy"
         }
     ]
-}
+}

federated_learning/breast_density_challenge/data/dataset_blinded_site-1.json

@@ -3464,4 +3464,4 @@
             "image": "Mass-Test_P_00612_RIGHT_MLO.npy"
         }
     ]
-}
+}

federated_learning/breast_density_challenge/data/dataset_blinded_site-2.json

@@ -3233,4 +3233,4 @@
             "image": "Calc-Training_P_01300_LEFT_MLO.npy"
         }
     ]
-}
+}

federated_learning/breast_density_challenge/data/dataset_blinded_site-3.json

@@ -3378,4 +3378,4 @@
             "image": "Calc-Training_P_02437_LEFT_MLO.npy"
         }
     ]
-}
+}

federated_learning/breast_density_challenge/data/dataset_site-1.json

@@ -5265,4 +5265,4 @@
             "label": 1
         }
     ]
-}
+}

federated_learning/breast_density_challenge/data/dataset_site-2.json

@@ -5100,4 +5100,4 @@
             "label": 3
         }
     ]
-}
+}

federated_learning/breast_density_challenge/data/dataset_site-3.json

@@ -5145,4 +5145,4 @@
             "label": 2
         }
     ]
-}
+}