Can`t export mobilenetv3 model to onnx
Nobody has claimed this yet.
- 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
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- 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