pytorch / pytorch/vision

Can`t export mobilenetv3 model to onnx

Open
#3,463 8 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

module: onnx
Dominant language
Python
Stars
17.9k
Forks
7.3k
Avg merge
1d 15h
Merged PRs (30d)
13

Description

model = models.mobilenet_v3_small(pretrained=True) input_np = np.random.uniform(0, 1, (1, 3, 224, 224)) input_var = torch.FloatTensor(input_np) torch.onnx.export(model, args=(input_var), f="cnn.onnx", verbose=False, input_names=["input"], output_names=["output"])

Error: RuntimeError: Exporting the operator hardsigmoid to ONNX opset version 9 is not supported. Please feel free to request support or submit a pull request on PyTorch GitHub.

cc @neginraoof

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by reproducing the failure with the MobileNetV3 Small example and torch.onnx.export shown in the issue. Investigate the hardsigmoid operator under ONNX opset 9; done means the model exports successfully without the reported unsupported-operator error.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, pytorch
Domain
computer-vision, machine-learning
Issue type
Bug
Difficulty
3/5
Estimated time
1-2 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.