Installation
Tutorial video
Requirements
We recommend using a conda environment manager.
System requirements:
Python>=3.8
- CUDA (run
nvidia-smi
command and ensure it shows your available GPUs)
Optional requirements
Graph visualization
If you wish to visualize the model architecture graph before and after the compression process you can install the dependencies graphviz
and pydot
using:
conda install graphviz
pip install pydot
Once the dependencies are installed, two .svg
files containing the visualizations of the original model and the quantized model will be generated in the outputs
folder when running CLIKA Compression Operation (CCO).
For more information, see graph visualization.
Monitoring integration
If you wish to monitor your training using TensorBoard you must install tensorboard package using the following line:
pip install tensorboard
For more information, see Monitoring Integration on the CLIKA usage instructions page.
CLIKA Compression Installation
Installing clika-compression
is like installing any other Python package using the pip
package manager; the only special requirement is to add the license key to gain access to CLIKA's PIP index.
You can install the package using the following lines:
# set your license key as a environment varialbe
export CC_LICENSE_KEY=YOUR_LICENSE_KEY
pip install --force "clika-compression" --extra-index-url \
https://license:$CC_LICENSE_KEY@license.clika.io/simple
Making the license key globally available
Since every usage of the clika-compression
package requires the availability of a valid license key, we will provide clika-compression
access to the license key within your system.
Execute the following command from any directory:
clika-init-license
and insert your license key when prompted.
This process will generate a file containing your license key in ~/.clika/.cc_license
, which can be accessed by the clika-compression
package, facilitating its usage whenever required.
Congratulations! you can now start using the clika-compression
python package.
(Optional) An alternative option to keep your license key globally available is to set it as a permanent environment variable instead of using the clika-init-license
command
If you wish to add clika-compression
to a requirements.txt
file, you may add the following lines to it:
--extra-index-url https://license:$CC_LICENSE_KEY@license.clika.io/simple
clika-compression
Common issues
CUDA-related issues
In the case of CUDA related issues we recommend to perform the following steps.
Verify CUDA installation
Validate CUDA installation using:
nvcc --version
Expected output:
- Installed CUDA version printed out on your screen (the latest available CUDA version is recommended).
If the command does not work as expected please refer to the CUDA installation guide before using the SDK.
Verify PyTorch installation
Test if the GPU is accessible to PyTorch using:
python3 -c "import torch; print(torch.cuda.is_available())"
Expected output:
>>> True
If the output is False
please refer to the PyTorch installation guide
and CUDA installation guide before using the SDK.