ONNX is great, but sometimes too complicated.

One day I wanted to export the following simple reshape operation to ONNX:

import torch


class JustReshape(torch.nn.Module):
    def __init__(self):
        super(JustReshape, self).__init__()

    def forward(self, x):
        return x.view((x.shape[0], x.shape[1], x.shape[3], x.shape[2]))


net = JustReshape()
model_name = 'just_reshape.onnx'
dummy_input = torch.randn(2, 3, 4, 5)
torch.onnx.export(net, dummy_input, model_name, input_names=['input'], output_names=['output'])

The input shape in this model is static, so what I expected is

However, I got the following complicated model instead:

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 (a.k.a. constant folding).

We have published ONNX Simplifier on convertmodel.com. It works out of the box and doesn't need any installation. Note that it runs in the browser locally and your model is completely safe.

pip3 install -U pip && pip3 install onnxsim

Then

onnxsim input_onnx_model output_onnx_model

For more advanced features, try the following command for help message

onnxsim -h

An overall comparison between a complicated model and its simplified version:

If you would like to embed ONNX simplifier python package in another script, it is just that simple.

import onnx
from onnxsim import simplify

# load your predefined ONNX model
model = onnx.load(filename)

# convert model
model_simp, check = simplify(model)

assert check, "Simplified ONNX model could not be validated"

# use model_simp as a standard ONNX model object

You can see more details of the API in onnxsim/onnx_simplifier.py

• MXNet
• MMDetection
• YOLOv5
• ncnn
• ...

We created a Chinese QQ group for ONNX!

ONNX QQ Group (Chinese): 1021964010, verification code: nndab. Welcome to join!

For English users, I'm active on the ONNX Slack. You can find and chat with me (daquexian) there.