Updating the SDK to use newer and updated dependencies, namely Holoscan SDK (Project-MONAI#481)

* Updated the SDK to use Holoscan SDK v1.0, and tested apps and Notebooks

Signed-off-by: M Q <[email protected]>

* Doc updates

Signed-off-by: M Q <[email protected]>

* Fix typo

Signed-off-by: M Q <[email protected]>

* Add Holoscan license file

Signed-off-by: M Q <[email protected]>

* Add release note and editorial changes

Signed-off-by: M Q <[email protected]>

* Update readme

Signed-off-by: M Q <[email protected]>

* Add missing packages in the example in the Readme

Signed-off-by: M Q <[email protected]>

* Add new package to make gen_docs work even just in Python 3.8 env

Signed-off-by: M Q <[email protected]>

* Updated user guide

Signed-off-by: M Q <[email protected]>

* Rerun the notebook to clear some warnings

Signed-off-by: M Q <[email protected]>

* rerun notebook

Signed-off-by: M Q <[email protected]>

* touch the file

Signed-off-by: M Q <[email protected]>

* touch the file

Signed-off-by: M Q <[email protected]>

* fix formatting complaints

Signed-off-by: M Q <[email protected]>

* ignore the complaint

Signed-off-by: M Q <[email protected]>

* touch file

Signed-off-by: M Q <[email protected]>

* touch the file

Signed-off-by: M Q <[email protected]>

* Successfully run after getting new clara-viz fix for Python 3.10+

Signed-off-by: M Q <[email protected]>

* specififies OS and CUDA requirements in the release note

Signed-off-by: M Q <[email protected]>

* Adding a note for doc building succeeding with Python3.8 only

Signed-off-by: M Q <[email protected]>

* Update docs and Notebooks

Signed-off-by: M Q <[email protected]>

* Explicitly specifying GPU and CUDA12 req.

Signed-off-by: M Q <[email protected]>

* Explicitly specifying GPU and CUDA12 req in README.

Signed-off-by: M Q <[email protected]>

* Add ref to MONAI guide per review commnents

Signed-off-by: M Q <[email protected]>

---------

Signed-off-by: M Q <[email protected]>
Signed-off-by: Simone Bendazzoli <[email protected]>

Author: MMelQin

CONTRIBUTING.md

@@ -138,7 +138,7 @@ MONAI Deploy App SDK's code coverage report is available at [CodeCov](https://co
 #### Building the documentation
 
 :::{note}
-Please note that the documentation builds successfully in Python 3.9 environment, but fails with Python 3.10.
+Please note that the documentation builds successfully in Python 3.8 environment, but fails with Python 3.10.
 :::
 
 MONAI's documentation is located at `docs/`.

README.md

@@ -15,7 +15,7 @@ MONAI Deploy App SDK offers a framework and associated tools to design, develop
 - Build medical imaging inference applications using a flexible, extensible & usable Pythonic API
 - Easy management of inference applications via programmable Directed Acyclic Graphs (DAGs)
 - Built-in operators to load DICOM data to be ingested in an inference app
-- Out-of-the-box support for in-proc PyTorch based inference, as well as remote inference via Triton Inference Server
+- Out-of-the-box support for in-proc PyTorch based inference
 - Easy incorporation of MONAI based pre and post transformations in the inference application
 - Package inference application with a single command into a portable MONAI Application Package
 - Locally run and debug your inference application using App Runner
@@ -24,31 +24,26 @@ MONAI Deploy App SDK offers a framework and associated tools to design, develop
 
 User guide is available at [docs.monai.io](https://docs.monai.io/projects/monai-deploy-app-sdk/en/stable/).
 
-## Citation
-
-If you have used MONAI in your research, please cite us! The citation can be exported from: [https://arxiv.org/abs/2212.14177](https://arxiv.org/abs/2212.14177).
-
 ## Installation
 
 To install [the current release](https://pypi.org/project/monai-deploy-app-sdk/), you can simply run:
 
 ```bash
-pip install monai-deploy-app-sdk
+pip install monai-deploy-app-sdk  # '--pre' to install a pre-release version.
 ```
 
-### Prerequisites
+Please also note the following system requirements:
+- Ubuntu 22.04 on X86-64 is required, as this is the only X86 platform that the underlying Holoscan SDK has been tested to support as of now.
+- [CUDA 12](https://developer.nvidia.com/cuda-12-0-0-download-archive) is required along with a supported NVIDIA GPU with at least 8GB of video RAM. If AI inference is not used in the example application and a GPU is not installed, at least [CUDA 12 runtime](https://pypi.org/project/nvidia-cuda-runtime-cu12/) is required, as this is one of the requirements of Holoscan SDK, in addition, the `LIB_LIBRARY_PATH` must be set to include the installed shared library, e.g. in a Python 3.8 env, ```export LD_LIBRARY_PATH=`pwd`/.venv/lib/python3.8/site-packages/nvidia/cuda_runtime/lib:$LD_LIBRARY_PATH```
+
 
-- This SDK depends on [NVIDIA Holoscan SDK](https://pypi.org/project/holoscan/) for its core implementation as well as its CLI, hence inherits its prerequisites, e.g. Ubuntu 22.04 with glibc 2.35 on X86-64 and NVIDIA dGPU drivers version 535 or above.
-- [CUDA 12.2](https://developer.nvidia.com/cuda-12-2-0-download-archive) or above is required along with a supported NVIDIA GPU with at least 8GB of video RAM.
-- If inference is not used in an example application and a GPU is not installed, at least [CUDA 12 runtime](https://pypi.org/project/nvidia-cuda-runtime-cu12/) is required, as this is one of the requirements of Holoscan SDK. In addition, the `LIB_LIBRARY_PATH` must be set to include the installed shared library, e.g. in a Python 3.10 env, ```export LD_LIBRARY_PATH=`pwd`/.venv/lib/python3.10/site-packages/nvidia/cuda_runtime/lib:$LD_LIBRARY_PATH```
-- Python: 3.9 to 3.12
 
 ## Getting Started
 
 Getting started guide is available at [here](https://docs.monai.io/projects/monai-deploy-app-sdk/en/stable/getting_started/index.html).
 
 ```bash
-pip install monai-deploy-app-sdk
+pip install monai-deploy-app-sdk  # '--pre' to install a pre-release version.
 
 # Clone monai-deploy-app-sdk repository for accessing examples.
 git clone https://github.com/Project-MONAI/monai-deploy-app-sdk.git
@@ -58,16 +53,15 @@ cd monai-deploy-app-sdk
 pip install matplotlib Pillow scikit-image
 
 # Execute the app locally
-python examples/apps/simple_imaging_app/app.py -i examples/apps/simple_imaging_app/input/brain_mr_input.jpg -o output
+python examples/apps/simple_imaging_app/app.py -i examples/apps/simple_imaging_app/brain_mr_input.jpg -o output
 
 # Package app (creating MAP Docker image), using `-l DEBUG` option to see progress.
-# Also please note that postfix will be added to user supplied tag for identifying CPU architecture and GPU type etc.
-monai-deploy package examples/apps/simple_imaging_app -c examples/apps/simple_imaging_app/app.yaml -t simple_app:latest --platform x86_64 -l DEBUG
+monai-deploy package examples/apps/simple_imaging_app -c simple_imaging_app/app.yaml -t simple_app:latest --platform x64-workstation -l DEBUG
 
 # Run the app with docker image and an input file locally
 ## Copy a test input file to 'input' folder
 mkdir -p input && rm -rf input/*
-cp examples/apps/simple_imaging_app/input/brain_mr_input.jpg input/
+cp examples/apps/simple_imaging_app/brain_mr_input.jpg input/
 ## Launch the app
 monai-deploy run simple_app-x64-workstation-dgpu-linux-amd64:latest -i input -o output
 ```
@@ -86,7 +80,7 @@ YouTube Video (to be updated with the new version):
 
 ### [3) Creating a Segmentation app](https://docs.monai.io/projects/monai-deploy-app-sdk/en/stable/getting_started/tutorials/segmentation_app.html)
 
-YouTube Video (demonstrating the previous version of the App SDK):
+YouTube Video (to be updated with the new version):
 
 - [Spleen Organ Segmentation - Jupyter Notebook Tutorial](https://www.youtube.com/watch?v=cqDVxzYt9lY)
 - [Spleen Organ Segmentation - Deep Dive](https://www.youtube.com/watch?v=nivgfD4pwWE)
@@ -97,16 +91,14 @@ YouTube Video (demonstrating the previous version of the App SDK):
 
 ### [Examples](https://docs.monai.io/projects/monai-deploy-app-sdk/en/stable/getting_started/examples.html)
 
-<https://github.com/Project-MONAI/monai-deploy-app-sdk/tree/main/examples/apps> has example apps that you can see, to name but a few
+<https://github.com/Project-MONAI/monai-deploy-app-sdk/tree/main/examples/apps> has example apps that you can see.
 
-- simple_imaging_app
 - ai_livertumor_seg_app
 - ai_spleen_seg_app
 - ai_unetr_seg_app
 - dicom_series_to_image_app
 - mednist_classifier_monaideploy
-- ai_remote_infer_app
-
+- simple_imaging_app
 
 ## Contributing
 

docs/requirements.txt

@@ -1,8 +1,12 @@
 Sphinx==4.1.2
 sphinx-autobuild==2021.3.14
-myst-nb==0.17.2  # this version is fine in python 3.9 and avoids pulling in multiple nbformat packages
-myst-parser==0.18.0
-lxml_html_clean  # needed by myst-nb
+myst-parser==0.15.2
+numpy>=1.21.6
+matplotlib==3.3.4
+ipywidgets==7.6.4
+pandas==1.1.5
+nbclient==0.5.4
+myst-nb==0.13.0
 linkify-it-py==1.0.1  # https://myst-parser.readthedocs.io/en/latest/syntax/optional.html?highlight=linkify#linkify
 sphinx-togglebutton==0.2.3
 sphinx-copybutton==0.4.0
@@ -14,7 +18,17 @@ ablog==0.10.19
 docutils==0.16  # 0.17 causes error. https://github.com/executablebooks/MyST-Parser/issues/343
 pydata_sphinx_theme==0.6.3
 sphinxemoji==0.1.8
+scipy
+scikit-image>=0.17.2
+plotly
+nibabel>=3.2.1
+monai>=1.0.0
 torch>=1.12.0
+numpy-stl>=2.12.0
+trimesh>=3.8.11
+pydicom
+PyPDF2>=2.11.1
+highdicom>=0.18.2
 sphinx-autodoc-typehints==1.12.0
 sphinxcontrib-applehelp==1.0.2
 sphinxcontrib-devhelp==1.0.2
@@ -23,3 +37,4 @@ sphinxcontrib-jsmath==1.0.1
 sphinxcontrib-qthelp==1.0.3
 sphinxcontrib-serializinghtml==1.1.5
 sphinxcontrib-mermaid==0.7.1
+lxml_html_clean

docs/source/getting_started/tutorials/mednist_app.md

@@ -5,9 +5,9 @@ This tutorial demos the process of packaging up a trained model using MONAI Depl
 ## Setup
 
 ```bash
-# Create a virtual environment with Python 3.9.
+# Create a virtual environment with Python 3.8.
 # Skip if you are already in a virtual environment.
-conda create -n mednist python=3.9 pytorch jupyterlab cudatoolkit=12.2 -c pytorch -c conda-forge
+conda create -n mednist python=3.8 pytorch jupyterlab cudatoolkit=12.2 -c pytorch -c conda-forge
 conda activate mednist
 
 # Launch JupyterLab if you want to work on Jupyter Notebook
@@ -42,7 +42,7 @@ jupyter-lab
 <div style="text-align: center;">
     <iframe width="560" height="315" src="https://www.youtube.com/embed/WwjilJFHuU4" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" allowfullscreen></iframe>
 
-    <p>Video may show the use of previous SDK version.</p>
+    <p>Video may show the use of previous SDK verson.</p>
 </div>
 ```
 
@@ -56,8 +56,6 @@ jupyter-lab
 
 ## Executing from Shell
 
-**_Note:_** Data files are now access controlled. Please first request permission to access the [shared folder on Google Drive](https://drive.google.com/drive/folders/1EONJsrwbGsS30td0hs8zl4WKjihew1Z3?usp=sharing). Please download zip file, `mednist_classifier_data.zip` in the `medmist_classifier_app` folder, to the same folder as the notebook example.
-
 ```bash
 # Clone the github project (the latest version of the main branch only)
 git clone --branch main --depth 1 https://github.com/Project-MONAI/monai-deploy-app-sdk.git
@@ -69,8 +67,11 @@ pip install monai-deploy-app-sdk
 
 # Download/Extract mednist_classifier_data.zip from https://drive.google.com/file/d/1yJ4P-xMNEfN6lIOq_u6x1eMAq1_MJu-E/view?usp=sharing
 
+# Download mednist_classifier_data.zip
+pip install gdown
+gdown https://drive.google.com/uc?id=1yJ4P-xMNEfN6lIOq_u6x1eMAq1_MJu-E
 
-# After having downloaded mednist_classifier_data.zip from the web browser or using gdown
+# After downloading mednist_classifier_data.zip from the web browser or using gdown
 unzip -o mednist_classifier_data.zip
 
 # Install necessary packages required by the app
@@ -98,7 +99,7 @@ monai-deploy package examples/apps/mednist_classifier_monaideploy/mednist_classi
     --config examples/apps/mednist_classifier_monaideploy/app.yaml \
     --tag mednist_app:latest \
     --models mednist_model/classifier.zip \
-    --platform x86_64 \
+    --platform x64-workstation \
     -l DEBUG
 
 # Note: for AMD GPUs, nvidia-docker is not required, but the dependency of the App SDK, namely Holoscan SDK

docs/source/getting_started/tutorials/monai_bundle_app.md

@@ -5,9 +5,9 @@ This tutorial shows how to create an organ segmentation application for a PyTorc
 ## Setup
 
 ```bash
-# Create a virtual environment with Python 3.9.
+# Create a virtual environment with Python 3.8.
 # Skip if you are already in a virtual environment.
-conda create -n monai python=3.9 pytorch torchvision jupyterlab cudatoolkit=12.2 -c pytorch -c conda-forge
+conda create -n monai python=3.8 pytorch torchvision jupyterlab cudatoolkit=12.2 -c pytorch -c conda-forge
 conda activate monai
 
 # Launch JupyterLab if you want to work on Jupyter Notebook
@@ -32,22 +32,20 @@ jupyter-lab
 <div style="text-align: center;">
     <iframe width="560" height="315" src="https://www.youtube.com/embed/nivgfD4pwWE" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" allowfullscreen></iframe>
 
-    <p>Video may show the use of previous SDK version.</p>
+    <p>Video may show the use of previous SDK verson.</p>
 </div>
 ```
 
 ```{raw} html
 <p style="text-align: center;">
-    <a class="sphinx-bs btn text-wrap btn-outline-primary col-md-6 reference external" href="../../_static/notebooks/tutorials/04_monai_bundle_app.ipynb">
+    <a class="sphinx-bs btn text-wrap btn-outline-primary col-md-6 reference external" href="../../_static/notebooks/tutorials/05_monai_bundle_app.ipynb">
         <span>Download 04_monai_bundle_app.ipynb</span>
     </a>
 </p>
 ```
 
 ## Executing from Shell
 
-**_Note:_** Data files are now access controlled. Please first request permission to access the [shared folder on Google Drive](https://drive.google.com/drive/folders/1EONJsrwbGsS30td0hs8zl4WKjihew1Z3?usp=sharing). Please download zip file, `mednist_classifieai_spleen_seg_bundle_data.zip` in the `ai_spleen_seg_app` folder, to the same folder as the notebook example.
-
 ```bash
 # Clone the github project (the latest version of main branch only)
 git clone --branch main --depth 1 https://github.com/Project-MONAI/monai-deploy-app-sdk.git
@@ -59,7 +57,10 @@ pip install --upgrade monai-deploy-app-sdk
 
 # Download/Extract ai_spleen_bundle_data zip file from https://drive.google.com/file/d/1cJq0iQh_yzYIxVElSlVa141aEmHZADJh/view?usp=sharing
 
-# Download the zip file containing both the model and test data.
+# Download the zip file containing both the model and test data
+pip install gdown
+gdown https://drive.google.com/uc?id=1Uds8mEvdGNYUuvFpTtCQ8gNU97bAPCaQ
+
 # After downloading it using gdown, unzip the zip file saved by gdown and
 # copy the model file into a folder structure that is required by CLI Packager
 rm -rf dcm
@@ -86,7 +87,7 @@ monai-deploy package examples/apps/ai_spleen_seg_app \
     --config examples/apps/ai_spleen_seg_app/app.yaml \
     --tag seg_app:latest \
     --models spleen_model/model.ts \
-    --platform x86_64 \
+    --platform x64-workstation \
     -l DEBUG
 
 # Note: for AMD GPUs, nvidia-docker is not required, but the dependency of the App SDK, namely Holoscan SDK

docs/source/getting_started/tutorials/multi_model_app.md

@@ -7,9 +7,9 @@ The models used in this example are trained with MONAI, and are packaged in the
 ## Setup
 
 ```bash
-# Create a virtual environment with Python 3.9.
+# Create a virtual environment with Python 3.8.
 # Skip if you are already in a virtual environment.
-conda create -n monai python=3.9 pytorch torchvision jupyterlab cudatoolkit=12.2 -c pytorch -c conda-forge
+conda create -n monai python=3.8 pytorch torchvision jupyterlab cudatoolkit=12.2 -c pytorch -c conda-forge
 conda activate monai
 
 # Launch JupyterLab if you want to work on Jupyter Notebook
@@ -34,8 +34,6 @@ jupyter-lab
 
 ## Executing from Shell
 
-**_Note:_** Data files are now access controlled. Please first request permission to access the [shared folder on Google Drive](https://drive.google.com/drive/folders/1EONJsrwbGsS30td0hs8zl4WKjihew1Z3?usp=sharing). Please download zip file, `ai_multi_model_bundle_data.zip` in the `ai_multi_ai_app` folder, to the same folder as the notebook example.
-
 ```bash
 # Clone the github project (the latest version of main branch only)
 git clone --branch main --depth 1 https://github.com/Project-MONAI/monai-deploy-app-sdk.git
@@ -45,7 +43,10 @@ cd monai-deploy-app-sdk
 # Install monai-deploy-app-sdk package
 pip install --upgrade monai-deploy-app-sdk
 
-# Download the zip file containing both the model and test data.
+# Download the zip file containing both the model and test data
+pip install gdown
+gdown https://drive.google.com/uc?id=1llJ4NGNTjY187RLX4MtlmHYhfGxBNWmd
+
 # After downloading it using gdown, unzip the zip file saved by gdown
 rm -rf dcm && rm -rf multi_models
 unzip -o ai_multi_model_bundle_data.zip
@@ -70,7 +71,7 @@ monai-deploy package examples/apps/ai_multi_ai_app \
     --tag multi_model_app:latest \
     --config examples/apps/ai_multi_ai_app/app.yaml \
     --models multi_models \
-    --platform x86_64 \
+    --platform x64-workstation \
     -l DEBUG
 
 # Note: for AMD GPUs, nvidia-docker is not required, but the dependency of the App SDK, namely Holoscan SDK

docs/source/getting_started/tutorials/segmentation_app.md

@@ -7,9 +7,9 @@ Please note that the following steps are for demonstration purpose. The code pul
 ## Setup
 
 ```bash
-# Create a virtual environment with Python 3.9.
+# Create a virtual environment with Python 3.8.
 # Skip if you are already in a virtual environment.
-conda create -n monai python=3.9 pytorch torchvision jupyterlab cudatoolkit=12.2 -c pytorch -c conda-forge
+conda create -n monai python=3.8 pytorch torchvision jupyterlab cudatoolkit=12.2 -c pytorch -c conda-forge
 conda activate monai
 
 # Launch JupyterLab if you want to work on Jupyter Notebook
@@ -33,9 +33,7 @@ jupyter-lab
 ```
 
 ## Executing from Shell
-
-**_Note:_** Data files are now access controlled. Please first request permission to access the [shared folder on Google Drive](https://drive.google.com/drive/folders/1EONJsrwbGsS30td0hs8zl4WKjihew1Z3?usp=sharing). Please download zip file, `ai_spleen_seg_bundle_data.zip` in the `ai_spleen_seg_app` folder, to the same folder as the notebook example.
-
+Please note that this part of the example uses the latest application source code on Github, as well as the corresponding test data.
 ```bash
 # Clone the github project (the latest version of main branch only)
 git clone --branch main --depth 1 https://github.com/Project-MONAI/monai-deploy-app-sdk.git
@@ -45,7 +43,12 @@ cd monai-deploy-app-sdk
 # Install monai-deploy-app-sdk package
 pip install --upgrade monai-deploy-app-sdk
 
-# Download the zip file containing both the model and test data.
+# Download/Extract ai_spleen_bundle_data zip file from https://drive.google.com/file/d/1cJq0iQh_yzYIxVElSlVa141aEmHZADJh/view?usp=sharing
+
+# Download the zip file containing both the model and test data
+pip install gdown
+gdown https://drive.google.com/uc?id=1Uds8mEvdGNYUuvFpTtCQ8gNU97bAPCaQ
+
 # After downloading it using gdown, unzip the zip file saved by gdown and
 # copy the model file into a folder structure that is required by CLI Packager
 rm -rf dcm
@@ -72,7 +75,7 @@ monai-deploy package examples/apps/ai_spleen_seg_app \
     --config examples/apps/ai_spleen_seg_app/app.yaml \
     --tag seg_app:latest \
     --models spleen_model/model.ts \
-    --platform x86_64 \
+    --platform x64-workstation \
     -l DEBUG
 
 # Note: for AMD GPUs, nvidia-docker is not required, but the dependency of the App SDK, namely Holoscan SDK

docs/source/getting_started/tutorials/segmentation_clara-viz_app.md

@@ -5,9 +5,9 @@ This tutorial shows how to create an organ segmentation application for a PyTorc
 ## Setup
 
 ```bash
-# Create a virtual environment with Python 3.9.
+# Create a virtual environment with Python 3.8.
 # Skip if you are already in a virtual environment.
-conda create -n monai python=3.9 pytorch torchvision jupyterlab cudatoolkit=12.2 -c pytorch -c conda-forge
+conda create -n monai python=3.8 pytorch torchvision jupyterlab cudatoolkit=12.2 -c pytorch -c conda-forge
 conda activate monai
 
 # Launch JupyterLab if you want to work on Jupyter Notebook

docs/source/getting_started/tutorials/simple_app.md

@@ -5,9 +5,9 @@ This tutorial shows how a simple image processing application can be created wit
 ## Setup
 
 ```bash
-# Create a virtual environment with Python 3.9.
+# Create a virtual environment with Python 3.8.
 # Skip if you are already in a virtual environment.
-conda create -n monai python=3.9 pytorch torchvision jupyterlab cudatoolkit=12.2 -c pytorch -c conda-forge
+conda create -n monai python=3.8 pytorch torchvision jupyterlab cudatoolkit=12.2 -c pytorch -c conda-forge
 conda activate monai
 
 # Launch JupyterLab if you want to work on Jupyter Notebook
@@ -53,12 +53,6 @@ pip install scikit-image, setuptools, Pillow, matplotlib
 # See the input file exists in the default `input`` folder in the current working directory
 ls examples/apps/simple_imaging_app/input/
 
-# Set the environment variable for the input, with relative path in this example.
-export HOLOSCAN_INPUT_PATH="./examples/apps/simple_imaging_app/input"
-
-# Env var can also be used to direct the output instead of using the default folder as in the following steps
-export HOLOSCAN_OUTPUT_PATH="./output_simple_imaging"
-
 # Local execution of the app with output file in the `output` folder in the current working directory
 python examples/apps/simple_imaging_app/app.py
 
@@ -69,7 +63,7 @@ ls output
 # This assumes that nvidia docker is installed in the local machine.
 # Please see https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/install-guide.html#docker to install nvidia-docker2.
 
-monai-deploy package examples/apps/simple_imaging_app -c examples/apps/simple_imaging_app/app.yaml -t simple_app:latest --platform x86_64 -l DEBUG
+monai-deploy package examples/apps/simple_imaging_app -c examples/apps/simple_imaging_app/app.yaml -t simple_app:latest --platform x64-workstation -l DEBUG
 
 # Show the application and package manifest files of the MONAI Application Package
 
@@ -78,7 +72,7 @@ docker run --rm simple_app-x64-workstation-dgpu-linux-amd64:latest show
 
 # Run the MAP container image with MONAI Deploy MAP Runner, with a cleaned output folder
 rm -rf output
-monai-deploy run simple_app-x64-workstation-dgpu-linux-amd64:latest -i $HOLOSCAN_INPUT_PATH -o output
+monai-deploy run simple_app-x64-workstation-dgpu-linux-amd64:latest -i input -o output
 
 # Check the output file
 ls output