2.2. User Installation
This guide covers the quick installation method for users who want to use Tiny ML Tensorlab without modifying the source code.
Note
This installation method provides read-only access to the toolchain. If you need to customize models or add new features, use Developer Installation instead.
2.2.1. Quick Install
Install Tiny ML Tensorlab directly from GitHub:
pip install git+https://github.com/TexasInstruments/tinyml-tensorlab.git@main#subdirectory=tinyml-modelmaker
This installs:
tinyml-modelmaker- The main orchestration tooltinyml-tinyverse- Core training infrastructuretinyml-modelzoo- Model definitionstinyml-modeloptimization- Quantization toolkit
2.2.2. Running Your First Example
After installation, you can run the hello world example:
# Clone just the examples
git clone --depth 1 https://github.com/TexasInstruments/tinyml-tensorlab.git
cd tinyml-tensorlab/tinyml-modelzoo
# Run the example
python -m tinyml_modelmaker examples/generic_timeseries_classification/config.yaml
Output will be saved to ../tinyml-modelmaker/data/projects/.
2.2.3. Verifying Installation
Verify the installation by importing the packages:
import tinyml_modelmaker
import tinyml_tinyverse
import tinyml_modelzoo
import tinyml_torchmodelopt
print("Installation successful!")
2.2.4. Updating
To update to the latest version:
pip install --upgrade git+https://github.com/TexasInstruments/tinyml-tensorlab.git@main#subdirectory=tinyml-modelmaker
2.2.5. Uninstalling
To remove Tiny ML Tensorlab:
pip uninstall tinyml-modelmaker tinyml-tinyverse tinyml-modelzoo tinyml-torchmodelopt
2.2.6. Limitations of User Install
The pip install method has some limitations:
Cannot modify model architectures
Cannot add custom feature extractors
Cannot debug training scripts
Updates require reinstallation
For full access, use Developer Installation.
2.2.7. Troubleshooting
“No module named tinyml_modelmaker”
Ensure you’re using the correct Python environment:
which python # Should point to your Python 3.10 installation
python --version # Should show 3.10.x
Version conflicts
If you have dependency conflicts, try installing in a virtual environment:
python -m venv tensorlab_env
source tensorlab_env/bin/activate # Linux
# or: tensorlab_env\Scripts\activate # Windows
pip install git+https://github.com/TexasInstruments/tinyml-tensorlab.git@main#subdirectory=tinyml-modelmaker
2.2.8. Next Steps
Quickstart - Train your first model
Environment Variables - Configure compilation tools
Developer Installation - Full installation for customization