update doc

Signed-off-by: Yiheng Wang <[email protected]>

models/vista2d/configs/hyper_parameters.yaml

@@ -27,8 +27,8 @@ pretrained_ckpt_name: null
 pretrained_ckpt_path: null
 
 # for commandline setting of a single dataset
-datalist: datalists/tissuenet_skin_mibi_datalist.json
-basedir: /data/tissuenet
+datalist: datalists/cellpose_datalist.json
+basedir: /cellpose_dataset
 data_list_files:
   - {datalist: "@datalist", basedir: "@basedir"}
 

models/vista2d/configs/inference.json

@@ -11,7 +11,7 @@
         256,
         256
     ],
-    "input_dict": "${'image': '/cellpose_dataset/test/001_img.png'}",
+    "input_dict": "${'image': '/home/venn/Desktop/data/medical/cellpose_dataset/test/001_img.png'}",
     "device": "$torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')",
     "sam_ckpt_path": "$@ckpt_dir + '/sam_vit_b_01ec64.pth'",
     "pretrained_ckpt_path": "$@ckpt_dir + '/model.pt'",

models/vista2d/docs/README.md

@@ -33,11 +33,23 @@ pip install git+https://github.com/facebookresearch/segment-anything.git
 pip install mlflow psutil pynvml #optional for MLFlow support
 ```
 
+### Prepare Data Lists and Datasets
+
+The default dataset for training, validation, and inference is the [Cellpose](https://www.cellpose.org/) dataset. Please follow the [tutorial](../download_preprocessor/) to prepare the dataset before executing any commands below.
+
+Additionally, all data lists are available in the `datalists.zip` file located in the root directory of the bundle. Extract the contents of the `.zip` file to access the data lists.
+
 ### Execute training
 ```bash
 python -m monai.bundle run_workflow "scripts.workflow.VistaCell" --config_file configs/hyper_parameters.yaml
 ```
 
+You can override the `basedir` to specify a different dataset directory by using the following command:
+
+```bash
+python -m monai.bundle run_workflow "scripts.workflow.VistaCell" --config_file configs/hyper_parameters.yaml --basedir <actual dataset ditectory>
+```
+
 #### Quick run with a few data points
 ```bash
 python -m monai.bundle run_workflow "scripts.workflow.VistaCell" --config_file configs/hyper_parameters.yaml --quick True --train#trainer#max_epochs 3
@@ -64,6 +76,8 @@ torchrun --nproc_per_node=gpu -m monai.bundle run_workflow "scripts.workflow.Vis
 python -m monai.bundle run --config_file configs/inference.json
 ```
 
+Please note that the data used in the config file is: "/cellpose_dataset/test/001_img.png", if the dataset path is different or you want to do inference on another file, please modify in `configs/inference.json` accordingly.
+
 ### Execute multi-GPU inference
 ```bash
 torchrun --nproc_per_node=gpu -m monai.bundle run_workflow "scripts.workflow.VistaCell" --config_file configs/hyper_parameters.yaml --mode infer --pretrained_ckpt_name model.pt

models/vista2d/download_preprocessor/readme.md

@@ -66,7 +66,6 @@ To execute VISTA-2D training pipeline, some datasets require label conversion. P
 `python generate_json.py --data_root provide_the_same_root_data_path`
 
 ### Generation of Json data lists (Optional)
-All data lists are provided in the `datalists.zip` file located in the root directory of the bundle. Please extract the contents of the `.zip` file to access the data lists.
 If one desires to generate JSON files from scratch, `generate_json.py` script performs both processing and creation of JSON files.
 To execute VISTA-2D training pipeline, some datasets require label conversion and then a json file list which the VISTA-2D training uses a format.
 Creating the json lists from the raw dataset sources, please use the `root_data_path` as the input to the script, example command to execute the script is given below: