enhance data preprocess script and readme file

README.md

@@ -18,13 +18,13 @@ The datasets used in this work were provided by [Activ Surgical](https://www.act
 We've provided a [link](https://github.com/Project-MONAI/MONAI-extra-test-data/releases/download/0.8.1/inbody_outbody_samples.zip) of 20 samples (10 in-body and 10 out-body) to show what this dataset looks like.
 
 ### Preprocessing
-After downloading this dataset, python script in `scripts` folder naming `data_process` can be used to get label json files by running the command below and replacing datapath and outpath parameters.
+After downloading this dataset, python script in `scripts` folder named `data_process` can be used to generate label json files by running the command below and modifying `datapath` to path of unziped downloaded data. Generated label json files will be stored in `label` folder under the bundle path.
 
 ```
-python scripts/data_process.py --datapath /path/to/data/root --outpath /path/to/label/folder
+python scripts/data_process.py --datapath /path/to/data/root
 ```
 
-After generating label files, please modify the `dataset_dir` parameter specified in `configs/train.json` and `configs/inference.json` to reflect where label files are.
+By default, label path parameter in `train.json` and `inference.json` of this bundle is point to the generated `label` folder under bundle path. If you move these generated label files to another place, please modify the `train_json`, `val_json` and `test_json` parameters specified in `configs/train.json` and `configs/inference.json` to where these label files are.
 
 The input label json should be a list made up by dicts which includes `image` and `label` keys. An example format is shown below.
 
@@ -116,6 +116,7 @@ python -m monai.bundle run evaluating \
     --config_file configs/inference.json \
     --logging_file configs/logging.conf
 ```
+The classification result of every images in `test.json` will be printed to the screen.
 
 #### Export checkpoint to TorchScript file:
 

configs/inference.json

@@ -5,9 +5,8 @@
         "$import torch"
     ],
     "bundle_root": "/workspace/bundle/endoscopic_inbody_classification",
-    "output_dir": "$@bundle_root + '/eval'",
     "dataset_dir": "/workspace/data/endoscopic_inbody_classification",
-    "test_json": "$@dataset_dir+'/test.json'",
+    "test_json": "$@bundle_root+'/label/test_samples.json'",
     "test_fp": "$open(@test_json,'r', encoding='utf8')",
     "test_dict": "$json.load(@test_fp)",
     "test_close": "$@test_fp.close()",

configs/metadata.json

@@ -1,7 +1,8 @@
 {
     "schema": "https://github.com/Project-MONAI/MONAI-extra-test-data/releases/download/0.8.1/meta_schema_20220324.json",
-    "version": "0.3.2",
+    "version": "0.3.3",
     "changelog": {
+        "0.3.3": "enhance data preprocess script and readme file",
         "0.3.2": "restructure readme to match updated template",
         "0.3.1": "add workflow, train loss and validation accuracy figures",
         "0.3.0": "update dataset processing",

configs/train.json

@@ -8,8 +8,8 @@
     "ckpt_dir": "$@bundle_root + '/models'",
     "output_dir": "$@bundle_root + '/eval'",
     "dataset_dir": "/workspace/data/endoscopic_inbody_classification",
-    "train_json": "$@dataset_dir+'/train.json'",
-    "val_json": "$@dataset_dir+'/val.json'",
+    "train_json": "$@bundle_root+'/label/train_samples.json'",
+    "val_json": "$@bundle_root+'/label/val_samples.json'",
     "train_fp": "$open(@train_json,'r', encoding='utf8')",
     "train_dict": "$json.load(@train_fp)",
     "train_close": "$@train_fp.close()",

docs/README.md

@@ -11,13 +11,13 @@ The datasets used in this work were provided by [Activ Surgical](https://www.act
 We've provided a [link](https://github.com/Project-MONAI/MONAI-extra-test-data/releases/download/0.8.1/inbody_outbody_samples.zip) of 20 samples (10 in-body and 10 out-body) to show what this dataset looks like.
 
 ### Preprocessing
-After downloading this dataset, python script in `scripts` folder naming `data_process` can be used to get label json files by running the command below and replacing datapath and outpath parameters.
+After downloading this dataset, python script in `scripts` folder named `data_process` can be used to generate label json files by running the command below and modifying `datapath` to path of unziped downloaded data. Generated label json files will be stored in `label` folder under the bundle path.
 
 ```
-python scripts/data_process.py --datapath /path/to/data/root --outpath /path/to/label/folder
+python scripts/data_process.py --datapath /path/to/data/root
 ```
 
-After generating label files, please modify the `dataset_dir` parameter specified in `configs/train.json` and `configs/inference.json` to reflect where label files are.
+By default, label path parameter in `train.json` and `inference.json` of this bundle is point to the generated `label` folder under bundle path. If you move these generated label files to another place, please modify the `train_json`, `val_json` and `test_json` parameters specified in `configs/train.json` and `configs/inference.json` to where these label files are.
 
 The input label json should be a list made up by dicts which includes `image` and `label` keys. An example format is shown below.
 
@@ -109,6 +109,7 @@ python -m monai.bundle run evaluating \
     --config_file configs/inference.json \
     --logging_file configs/logging.conf
 ```
+The classification result of every images in `test.json` will be printed to the screen.
 
 #### Export checkpoint to TorchScript file:
 

scripts/data_process.py

@@ -42,9 +42,9 @@ def generate_labels(data_path, output_path):
     train_list = inbody_train_list + outbody_train_list
     val_list = inbody_val_list + outbody_val_list
     test_list = inbody_test_list + outbody_test_list
-    save_json(train_list, out_path, "train.json")
-    save_json(val_list, out_path, "val.json")
-    save_json(test_list, out_path, "test.json")
+    save_json(train_list, out_path, "train_samples.json")
+    save_json(val_list, out_path, "val_samples.json")
+    save_json(test_list, out_path, "test_samples.json")
 
 
 if __name__ == "__main__":
@@ -58,12 +58,7 @@ if __name__ == "__main__":
     )
 
     # path to save label json.
-    parser.add_argument(
-        "--outpath",
-        type=str,
-        default=r"/workspace/data/endoscopic_inbody_classification",
-        help="A path to save the onnx model.",
-    )
+    parser.add_argument("--outpath", type=str, default=r"./label", help="A path to save the onnx model.")
 
     args = parser.parse_args()
     data_path = args.datapath