Add weight downloading in swinunetr_finetune notebook (#1390)

Fixes #1389 .

### Description

- Download weights in the notebook

### Checks
<!--- Put an `x` in all the boxes that apply, and remove the not
applicable items -->
- [x] Avoid including large-size files in the PR.
- [x] Clean up long text outputs from code cells in the notebook.
- [x] For security purposes, please check the contents and remove any
sensitive info such as user names and private key.
- [x] Ensure (1) hyperlinks and markdown anchors are working (2) use
relative paths for tutorial repo files (3) put figure and graphs in the
`./figure` folder
- [ ] Notebook runs automatically `./runner.sh -t <path to .ipynb file>`

---------

Signed-off-by: Mingxin <[email protected]>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

Author: mingxin-zheng

self_supervised_pretraining/swinunetr_pretrained/README.md

@@ -6,9 +6,8 @@ Benchmark on BTCV with using the pre-trained weights as compared to random initi
 
 ### Steps to run the tutorial
 1. Download the dataset [BTCV](https://www.synapse.org/#!Synapse:syn3193805/wiki/217789) (More detail is provided in the Data section)
-2. Download the pretrained SwinUNETR weights on the 50,000 3D volumes from the following [link](https://github.com/Project-MONAI/MONAI-extra-test-data/releases/download/0.8.1/ssl_pretrained_weights.pth). More information about the dataset and training is provided below
-3. Modify the paths for pretrained_path, data_root, json_path & logdir in swinunetr_finetune.ipynb
-4. Run the 'swinunetr_finetune.ipynb'
+1. Modify the paths for pretrained_path, data_root, json_path & logdir in [swinunetr_finetune.ipynb](swinunetr_finetune.ipynb)
+1. Run the [swinunetr_finetune.ipynb](swinunetr_finetune.ipynb)
 
 ### 1. Data
 Pre-training Dataset: Datasets from multiple sources has been used. Below is a list of all the different datasets that were utilized for training the SwinUNETR network architecture:

self_supervised_pretraining/swinunetr_pretrained/swinunetr_finetune.ipynb

@@ -64,6 +64,7 @@
     "import matplotlib.pyplot as plt\n",
     "from collections import OrderedDict\n",
     "\n",
+    "from monai.apps import download_url\n",
     "from monai.utils import set_determinism\n",
     "from monai.losses import DiceCELoss\n",
     "from monai.inferers import sliding_window_inference\n",
@@ -104,7 +105,7 @@
    "metadata": {},
    "source": [
     "##### Note:\n",
-    "[Beyond the cranial vault](https://www.synapse.org/#!Synapse:syn3193805/wiki/217789) abdominal segmentation multi-class dataset needs to be downloaded for the execution of this notebook. Downloading data to the `data_root` path defined variable is optimal, if data is downloaded at another location please change the path `data_root` accordingly. Please make sure to download the pre-trained weights from [here](https://github.com/Project-MONAI/MONAI-extra-test-data/releases/download/0.8.1/ssl_pretrained_weights.pth) to use them in this notebook, the path to the downloaded pre-trained weights needs to be set.\n",
+    "[Beyond the cranial vault](https://www.synapse.org/#!Synapse:syn3193805/wiki/217789) abdominal segmentation multi-class dataset needs to be downloaded for the execution of this notebook. Downloading data to the `data_root` path defined variable is optimal, if data is downloaded at another location please change the path `data_root` accordingly.\n",
     "\n",
     "Please see the Readme for more details about the dataset. Multiple data splits have already been provided in subsets of 3, 5, 7, 12 and 24 (full data) with consistent validation splits."
    ]
@@ -152,7 +153,14 @@
    "outputs": [],
    "source": [
     "use_pretrained = True\n",
-    "pretrained_path = os.path.normpath(\"to/be/defined\")"
+    "\n",
+    "if use_pretrained:\n",
+    "    resource = (\n",
+    "        \"https://github.com/Project-MONAI/MONAI-extra-test-data/releases/download/0.8.1/ssl_pretrained_weights.pth\"\n",
+    "    )\n",
+    "    dst = \"./ssl_pretrained_weights.pth\"\n",
+    "    download_url(resource, dst)\n",
+    "    pretrained_path = os.path.normpath(dst)"
    ]
   },
   {
@@ -537,7 +545,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.8.15"
+   "version": "3.8.10"
   }
  },
  "nbformat": 4,