# Install Qualcomm® Neural Processing SDK for AI Source: [https://docs.qualcomm.com/doc/80-63195-1/topic/Install-Qualcomm-Neural-Processing-SDK-for-AI.html](https://docs.qualcomm.com/doc/80-63195-1/topic/Install-Qualcomm-Neural-Processing-SDK-for-AI.html) Install frameworks and dependencies for Qualcomm® Neural Processing SDK for AI. ## About this task These procedures have been verified on version 2.5.x. Qualcomm® Neural Processing SDK for AI is supported on Ubuntu 18.0.4. ## Procedure 1. Configurenameserver. echo "nameserver 8.8.8.8" | sudo tee /etc/resolv.conf > /dev/nullCopy to clipboard 2. Installpip and pip3. sudo apt-get update sudo apt install python-pip sudo apt install python3-pip pip3 install --upgrade pip sudo apt-get update Copy to clipboard 3. Set`python3.6`as the default python version. sudo update-alternatives --install /usr/bin/python python /usr/bin/ python2.7 1 sudo update-alternatives --install /usr/bin/python python /usr/bin/ python3.6 2 Copy to clipboard 4. Install DNN frameworks. Qualcomm® Neural Processing SDK has been tested only with certain versions of the AI Frameworks.So, it is recommended to use these versions. However other versions might work as well. Refer to the setup.html in the SDK for more details. Refer to Install frameworks for Qualcomm® Neural Processing SDK. 5. Install Android NDK. 1. Qualcomm® Neural Processing SDK is tested with Android NDK version r25c. It should be available for download from [https://github.com/android/ndk/wiki/Unsupported-Downloads#ndk-17c-downloads](https://github.com/android/ndk/wiki/Unsupported-Downloads#ndk-17c-downloads). Unzip the downloaded file and update the following environment variable. export ANDROID_NDK_ROOT=Copy to clipboard 2. Setup the Qualcomm® Neural Processing SDK. Extract the SNPE SDK to a directory. This directory is referred to as `$SNPE_ROOT`. Note the use of `X.Y.Z`inthis section. It refers to the release zip that is in use, e.g.`, snpe-1.0.0.zip`. unzip -X snpe-X.Y.Z.zipCopy to clipboard 3. Install dependencies. pip install numpy==1.18.5 pip install sphinx==2.2.1 pip install matplotlib==3.0.3 pip install scikit-image==0.15.0 pip install mako sudo apt install clang Copy to clipboard 4. Run the dependencies script to check the system for Ubuntu package dependencies. You will be prompted to install any missing dependencies. source snpe-X.Y.Z/bin/dependencies.shCopy to clipboard 5. Run the Python dependency checker to check the system for Python package dependencies. Install the missing packages. source snpe-X.Y.Z/bin/check_python_depends.shCopy to clipboard 6. Setup `SNPE_ROOT` environmentalvariable and add it to PATH. This step is taken care of when you run `bin/envsetup.sh` from the SDK root directory. 6. Set nstallation paths for the Frameworks using the following commands source bin/envsetup.sh --tflite /TFLite/Dir/ source bin/envsetup.sh -p /torch/Dir/ source bin/envsetup.sh -t /tensorflow/Dir source bin/envsetup.sh -o /onnx/Dir source bin/envsetup.sh -c /caffe/Dir source bin/envsetup.sh -f /caffe2/Dir Copy to clipboard Installation path of tensorflow can be obtained using “Pip show tensorflow”. Add “/ tensorflow” to the path obtained. - **[Install DNN frameworks](https://docs.qualcomm.com/doc/80-63195-1/topic/Install-DNN-frameworks.html)** Once you are done setting up the Qualcomm® Neural Processing SDK and relevant frameworks, you can proceed to converting your models to [DLC](https://docs.qualcomm.com/doc/80-63195-1/topic/Deep-Learning-Container--DLC-.html) format. **Parent Topic:** [Qualcomm Neural Processing SDK for AI](https://docs.qualcomm.com/doc/80-63195-1/topic/Qualcomm-Neural-Processing-SDK-for-AI.html) Last Published: May 16, 2024 [Previous Topic Qualcomm Neural Processing SDK for AI](https://docs.qualcomm.com/bundle/publicresource/80-63195-1/topics/Qualcomm-Neural-Processing-SDK-for-AI.md) [Next Topic Install DNN frameworks](https://docs.qualcomm.com/bundle/publicresource/80-63195-1/topics/Install-DNN-frameworks.md)