onnx / onnx/models

batch size is zero in tiny_yolov2 model

Open
#212 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

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

Description

I got the following error when calling the import_onnx_model function. Thanks for the instruction on the modification.

ng_function = import_onnx_model(model.SerializeToString())
RuntimeError: Check '(batch_size.is_dynamic() || static_cast<size_t>(batch_size) > 0)' failed at /root/ng/src/ngraph/validation_util.cpp:316:
While validating node 'Convolution[Convolution_51](Add_50: float{0,3,416,416}, C onstant_2: float{16,3,3,3}) -> (??)':
Batch size is zero.

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

Start by reproducing the import_onnx_model call with the tiny_yolov2 model and inspect the serialized model's batch dimension. Confirm what causes the zero batch size and define done as importing the model without the reported validation error.

Written by the indexing model from the issue text.

Assessment

Domain
machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.