[DLMED] update bundle tutorial (Project-MONAI#741)

Signed-off-by: Nic Ma <[email protected]>

Author: Nic-Ma

modules/bundle/get_started.ipynb

@@ -13,9 +13,10 @@
     "This notebook is a step-by-step tutorial to help get started to develop a bundle package, which contains a config file to construct the training pipeline and also has a `metadata.json` file to define the metadata information.\n",
     "\n",
     "This notebook mainly contains the below sections:\n",
-    "- Define a training config with `JSON` or `YAML` format\n",
-    "- Execute training based on bundle scripts and configs\n",
-    "- Hybrid programming with config and python code\n",
+    "- Define a training config with `JSON` or `YAML` format.\n",
+    "- Execute training based on bundle scripts and configs.\n",
+    "- Execute other scripts for bundle functionalities.\n",
+    "- Hybrid programming with config and python code.\n",
     "\n",
     "You can find the usage examples of MONAI bundle key features and syntax in this tutorial, like:\n",
     "- Instantiate a python object from a dictionary config with `_target_` indicating class or function name or module path.\n",
@@ -511,9 +512,7 @@
    "source": [
     "## Execute training with bundle script - `run`\n",
     "\n",
-    "There are several predefined scripts in MONAI bundle module to help execute `regular training`, `metadata verification base on schema`, `network input / output verification`, `export to TorchScript model`, etc.\n",
-    "\n",
-    "Here we leverage the `run` script and specify the ID of trainer in the config.\n",
+    "There are several predefined scripts in MONAI bundle module, here we leverage the `run` script and specify the ID of trainer in the config.\n",
     "\n",
     "Just define the entry point expressions in the config to execute in order, and specify the `runner_id` in CLI script."
    ]
@@ -535,7 +534,9 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "`python -m monai.bundle run training --config_file configs/train.json`"
+    "```shell\n",
+    "python -m monai.bundle run training --config_file configs/train.json\n",
+    "```"
    ]
   },
   {
@@ -546,28 +547,52 @@
     "\n",
     "To override some config items at runtime, users can specify the target `id` and `value` at command line, or override the `id` with some content in another config file. Here we set the device to `cuda:1` at runtime.\n",
     "\n",
-    "Please note that \"#\" and \"$\" may be meaningful syntax for some `shell` and `CLI` tools, so may need to add escape character or quotes for them in the command line, like: `\"\\$torch.device('cuda:1')\"`. For more details: https://github.com/google/python-fire/blob/v0.4.0/fire/parser.py#L60."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "`python -m monai.bundle run training --config_file configs/train.json --device \"\\$torch.device('cuda:1')\"`"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Override content from another config file."
+    "Please note that \"#\" and \"$\" may be meaningful syntax for some `shell` and `CLI` tools, so may need to add escape character or quotes for them in the command line, like: `\"\\$torch.device('cuda:1')\"`. For more details: https://github.com/google/python-fire/blob/v0.4.0/fire/parser.py#L60.\n",
+    "```shell\n",
+    "python -m monai.bundle run training --config_file configs/train.json --device \"\\$torch.device('cuda:1')\"\n",
+    "```\n",
+    "Override content from another config file.\n",
+    "```shell\n",
+    "python -m monai.bundle run training --config_file configs/train.json --network \"%configs/test.json#network\"\n",
+    "```"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "`python -m monai.bundle run training --config_file configs/train.json --network \"%configs/test.json#network\"`"
+    "## Execute other bundle scripts\n",
+    "\n",
+    "Besides `run`, there are also many other scripts for bundle functionalities. All the scripts are available at: https://docs.monai.io/en/latest/bundle.html#scripts.\n",
+    "\n",
+    "Here is some typical examples:\n",
+    "\n",
+    "1. Initialize a bundle directory based on the template and pretrained checkpoint weights.\n",
+    "```shell\n",
+    "python -m monai.bundle init_bundle --bundle_dir <target dir> --ckpt_file <checkpoint path>\n",
+    "```\n",
+    "\n",
+    "2. Export the model checkpoint to a `TorchScript` model at the given filepath with metadata and config included as JSON files.\n",
+    "```shell\n",
+    "python -m monai.bundle ckpt_export network --filepath <export path> --ckpt_file <checkpoint path> --config_file <config path>\n",
+    "```\n",
+    "\n",
+    "3. Verify the format of provided `metadata` file based on the predefined `schema`.\n",
+    "```shell\n",
+    "python -m monai.bundle verify_metadata --meta_file <meta path>\n",
+    "```\n",
+    "\n",
+    "4. Verify the input and output data shape and data type of network defined in the metadata. It will test with fake Tensor data according to the required data shape in `metadata`.\n",
+    "```shell\n",
+    "python -m monai.bundle verify_net_in_out network --meta_file <metadata path> --config_file <config path>\n",
+    "```\n",
+    "The acceptable data shape in the metadata can support `\"*\"` for any size, or use an expression with Python mathematical operators and one character variables to represent dependence on an unknown quantity, for example, `\"2**p\"` represents a size which must be a power of 2, `\"2**p*n\"` must be a multiple of a power of 2. `\"spatial_shape\": [ \"32 * n\", \"2 ** p * n\", \"*\"]`.\n",
+    "\n",
+    "\n",
+    "5. Download a bundle from Github release or URL.\n",
+    "```shell\n",
+    "python -m monai.bundle download --name <bundle_name>\n",
+    "```"
    ]
   },
   {