A set of simple tools for splitting, merging, OP deletion, size compression, rewriting attributes and constants, OP generation, change opset, change to the specified input order, addition of OP, RGB to BGR conversion, change batch size, batch rename of OP, and JSON convertion for ONNX models.
# (1) Minimum configuration installation with no dependent packages installed $ pip install -U simple-onnx-processing-tools \ && pip install -U onnx \ && python3 -m pip install -U onnx_graphsurgeon --index-url https://pypi.ngc.nvidia.com or # (2) When installing all dependent packages such as onnx-simplifier, onnxruntime, numpy, etc... $ pip install -U simple-onnx-processing-tools[full] \ && pip install -U onnx \ && python3 -m pip install -U onnx_graphsurgeon --index-url https://pypi.ngc.nvidia.com
$ docker run --rm -it \
-v `pwd`:/workdir \
-w /workdir \
ghcr.io/pinto0309/simple-onnx-processing-tools:1.1.31| No. | Tool Name | Tags | Summary |
|---|---|---|---|
| 1 | snc4onnx snc |
PyPI snc | Simple tool to combine(merge) onnx models. Simple Network Combine Tool for ONNX. |
| 2 | sne4onnx image |
PyPI sne | A very simple tool for situations where optimization with onnx-simplifier would exceed the Protocol Buffers upper file size limit of 2GB, or simply to separate onnx files to any size you want. Simple Network Extraction for ONNX. |
| 3 | snd4onnx snd |
PyPI snd | Simple node deletion tool for onnx. Simple Node Deletion for ONNX. |
| 4 | scs4onnx scs |
PyPI scs | 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. |
| 5 | sog4onnx sog |
PyPI sog | Simple ONNX operation generator. Simple Operation Generator for ONNX. |
| 6 | sam4onnx sam |
PyPI sam | A very simple tool to rewrite parameters such as attributes and constants for OPs in ONNX models. Simple Attribute and Constant Modifier for ONNX. |
| 7 | soc4onnx soc |
PyPI sam | A very simple tool that forces a change in the opset of an ONNX graph. Simple Opset Changer for ONNX. |
| 8 | scc4onnx scc |
PyPI sam | Very simple NCHW and NHWC conversion tool for ONNX. Change to the specified input order for each and every input OP. Also, change the channel order of RGB and BGR. Simple Channel Converter for ONNX. |
| 9 | sna4onnx sna |
PyPI sog | Simple node addition tool for onnx. Simple Node Addition for ONNX. |
| 10 | sbi4onnx sbi |
PyPI sbi4onnx | A very simple script that only initializes the batch size of ONNX. Simple Batchsize Initialization for ONNX. |
| 11 | sor4onnx sor |
PyPI sor4onnx | Simple OP Renamer for ONNX. |
| 12 | soa4onnx soa |
PyPI soa4onnx | Simple model Output OP Additional tools for ONNX. |
| 13 | sod4onnx sod |
PyPI sod4onnx | Simple model Output OP Deletion tools for ONNX. |
| 14 | ssi4onnx ssi |
PyPI ssi4onnx | Simple Shape Inference tool for ONNX. |
| 15 | sit4onnx sit |
PyPI sit4onnx | Tools for simple inference testing using TensorRT, CUDA and OpenVINO CPU/GPU and CPU providers. Simple Inference Test for ONNX. |
| 16 | onnx2json onnx2json |
PyPI onnx2json | Exports the ONNX file to a JSON file. |
| 17 | json2onnx json2onnx |
PyPI sog | Converts a JSON file to an ONNX file. |
| 18 | sed4onnx sed |
PyPI sog | Simple ONNX constant encoder/decoder. Since the constant values in the JSON files generated by onnx2json are Base64-encoded values, ASCII <-> Base64 conversion is required when rewriting JSON constant values. |
| 19 | ssc4onnx ssc |
PyPI sog | Checker with simple ONNX model structure. Simple Structure Checker for ONNX. Analyzes and displays the structure of huge size models that cannot be displayed by Netron. |
| 20 | sio4onnx image |
PyPI sio | Simple tool to change the INPUT and OUTPUT shape of ONNX. |
| 21 | svs4onnx image |
PyPI sio | A very simple tool to swap connections between output and input variables in an ONNX graph. Simple Variable Switch for ONNX. |
| 22 | onnx2tf image |
PyPI onnx2tf | Self-Created Tools to convert ONNX files (NCHW) to TensorFlow format (NHWC). The purpose of this tool is to solve the massive Transpose extrapolation problem in onnx-tensorflow (onnx-tf). |
| 23 | sng4onnx image |
PyPI sng4onnx | A simple tool that automatically generates and assigns an OP name to each OP in an old format ONNX file. |
| 24 | sde4onnx sde4onnx_icon |
PyPI sde4onnx | Simple doc_string eraser for ONNX. |
| 25 | spo4onnx spo4onnx_icon |
PyPI spo4onnx | Simple tool for partial optimization of ONNX. Further optimize some models that cannot be optimized with onnx-optimizer and onnxsim by several tens of percent. In particular, models containing Einsum and OneHot. |
| 26 | components_of_onnx components_of_onnx |
[WIP]PyPI sog | ONNX parts yard. The various operations described in Operator Schemas are converted in advance into OP stand-alone ONNX files. |
| No. | Tool Name | Author | Tags | Summary |
|---|---|---|---|---|
| 1 | OnnxGraphQt onnx_graph_qt |
fateshelled | OnnxGraphQt | ONNX model visualizer. Model structure can be edited on the visualization tool.image image |
| 2 | onnx-modifier image |
ZhangGe6 | onnx-modifier | To edit an ONNX model, One common way is to visualize the model graph, and edit it using ONNX Python API.image |
| 3 | onnx-simplifier | daquexian | PyPI onnxsim | ONNX Simplifier is presented to simplify the ONNX model. It infers the whole computation graph and then replaces the redundant operators with their constant outputs. |
| 4 | Sparsify image |
neuralmagic | PyPI sparsify | Easy-to-use UI for automatically sparsifying neural networks and creating sparsification recipes for better inference performance and a smaller footprint.image |
| 5 | DeepSparse Engine image |
neuralmagic | PyPI deepsparse | Sparsity-aware neural network inference engine for GPU-class performance on CPUs.image image |
| 6 | Sparsebit | megvii-research | PyPI Sparsebit | Sparsebit is a toolkit with pruning and quantization capabilities. It is designed to help researchers compress and accelerate neural network models by modifying only a few codes in existing pytorch project. |
| 7 | onnion | Idein | PyPI onnion | onnion project. compile onnx to python. runtime depends only numpy. |
git clone https://github.com/fateshelled/OnnxGraphQt cd OnnxGraphQt # build docker image ./docker/build.bash # run ./docker/run.bash