onnx-tool 0.3.3

A tool for ONNX model:Shape inference, MACs(FLOPs) counting for each layer, Extract subgraph from ONNX model, or do inplace op fusion, and any operation you can image with ONNX.

onnx-tool

A tool for ONNX model:

• Shape inference.
• MACs(FLOPs) counting for each layer.
• Extract subgraph from ONNX model, or do inplace op fusion. ...
  and any operation you can image with ONNX.

New:

• Sparse Models are initially supported in v0.3.1 release. view Sparse Model
• Quantized models are initially supported in v0.3.0 release.
• 4 onnx models of Stable Diffusion are supported in v0.2.14 release. view results
• Memory usage of each layer is valid in v0.2.10 release.
• Pytorch models are also valid if torch.onnx.export succeeded.

---

Shape inference

how to use: data/Profile.md.
pytorch usage: data/PytorchUsage.md.

---

MACs counting for each layer (FLOPs=2*MACs)

Float MultipleAdd Count, Memory Usage(in bytes), Parameters(elements number)

Sparse Pattern, Sparse Block Ratio, Sparse Element Ratio

how to use: data/Profile.md.
pytorch usage: data/PytorchUsage.md.

---

Extract subgraph from ONNX model

how to use: data/Subgraph.md.

---

Inplace op fusion

how to use: data/Subgraph.md.

---

Add any hidden tensors to model's outputs

how to use: data/Profile.md.

---

Tensor operations

• Export weight tensors to files
• Simplify tensor and node names, convert name from a long string to a short string
• Remove unused tensors, models like vgg19-7.onnx set its static weight tensors as its input tensors
• Set custom input and output tensors' name and dimension, change model from fixed input to dynamic input
  how to use: data/Tensors.md.

---

How to install

pip install onnx-tool

OR

pip install --upgrade git+https://github.com/ThanatosShinji/onnx-tool.git

python>=3.6

If pip install onnx-tool failed by onnx's installation, you may try pip install onnx==1.8.1 (a lower version like this) first.
Then pip install onnx-tool again.

---

Known Issues

• Loop op is not supported

---

Results of ONNX Model Zoo and SOTA models

Some models have dynamic input shapes. The MACs varies from input shapes. The input shapes used in these results are writen to data/public/config.py. These onnx models with all tensors' shape can be downloaded: baidu drive(code: p91k) google drive

Model Params(M) MACs(M) text_encoder 123.13 6,782 UNet2DCondition 859.52 888,870 VAE_encoder 34.16 566,371 VAE_decoder 49.49 1,271,959 SqueezeNet 1.0 1.23 351 VGG 19 143.66 19,643 AlexNet 60.96 665 GoogleNet 6.99 1,606 googlenet_age_adience 5.98 1,605 LResNet100E-IR 65.22 12,102 BERT-Squad 113.61 22,767 BiDAF 18.08 9.87 EfficientNet-Lite4 12.96 1,361 Emotion FERPlus 12.95 877 Mask R-CNN R-50-FPN-fp32 46.77 92,077

Model Params(M) MACs(M) rvm_mobilenetv3_fp32.onnx 3.73 4,289 yolov4 64.33 3,319 ConvNeXt-L 229.79 34,872 edgenext_small 5.58 1,357 SSD 19.98 216,598 RealESRGAN_x4plus.pth 16.69 73,551 ShuffleNet-v2-fp32 2.29 146 GPT-2 137.02 1,103 T5-encoder 109.62 686 T5-decoder-with-lm-head 162.62 1,113 RoBERTa-BASE 124.64 688 Faster R-CNN R-50-FPN-fp32 44.10 46,018 FCN ResNet-50 35.29 37,056 MobileNet v2-1.0-fp32 3.3 300 ResNet50_fp32 25 3,868