A very simple tool that compresses the overall size of the ONNX model by aggregating duplicate constant values as much as possible. Simple Constant value Shrink for ONNX.
Project description
scs4onnx
A very simple tool that compresses the overall size of the ONNX model by aggregating duplicate constant values as much as possible. Simple Constant value Shrink for ONNX.
Key concept
- If the same constant tensor is found by scanning the entire graph for Constant values, it is aggregated into a single constant tensor.
- Ignore scalar values.
- Ignore variables.
1. Setup
### option
$ echo export PATH="~/.local/bin:$PATH" >> ~/.bashrc \
&& source ~/.bashrc
### run
$ pip install -U onnx \
&& python3 -m pip install -U onnx_graphsurgeon --index-url https://pypi.ngc.nvidia.com \
&& pip install -U scs4onnx
2. Usage
$ scs4onnx -h
usage: scs4onnx [-h] onnx_file_path {shrink,npy}
positional arguments:
onnx_file_path Input onnx file path.
{shrink,npy} Constant Value Compression Mode.
shrink: Share constant values inside the model as much as possible.
The model size is slightly larger because some shared constant values
remain inside the model, but performance is maximized.
npy: Outputs constant values used repeatedly in the model to an external
file .npy. Instead of the smallest model body size, the file loading
overhead is greater.
Default: shrink
optional arguments:
-h, --help show this help message and exit
3. Execution
$ scs4onnx input.onnx shrink
4. Sample
4-1. shrink
mode sample
-
297.8MB -> 67.4MB
4-2. npy
mode sample
-
297.8MB -> 21.3MB
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
scs4onnx-1.0.0.tar.gz
(5.1 kB
view hashes)