onnx / onnx/models

Convert ONNX to PyTorch and Train

Open
#576 3 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

question
Dominant language
Jupyter Notebook
Stars
9.8k
Forks
1.6k
PR merge metrics
No merged PRs in 30d

Description

I converted your ONNX model to PyTorch, and now I am trying to Train it.
When I converted to PyTorch, it only accepts this tensor size: [1, 3, 224, 224], and does not accept other batch sizes.

How can I train the converted model with various batch sizes (4, 8, 16, etc)?

In addition, is it possible to train this model, as its type is <class 'torch.fx.graph_module.GraphModule.new..GraphModuleImpl'>?

Contributor guide

No contributing guide indexed for this repository

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

The issue names no repository files, tests, or entry points. Start by reproducing the reported fixed [1, 3, 224, 224] input constraint and inspecting the converted model; done means determining whether batch sizes 4, 8, and 16 are supported and whether the reported GraphModule can be trained.

Written by the indexing model from the issue text.

Assessment

Tech stack
pytorch
Domain
machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.