onnx / onnx/models

Pre-trained Mask-RCNN model has no weights

Open
#316 0 comments 1 reaction 0 assignees View on GitHub

Nobody has claimed this yet.

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

Description

My understanding of a pre-trained model is that it will not only contain the structure but also the weights. However, the Mask-RCNN pre-trained model you provide does not contain any weights:

import onnx
from onnx import numpy_helper

model = onnx.load('MaskRCNN-10.onnx')
init = model.graph.initializer
print("There are {} weights in the model.".format(len(init)))

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 examining MaskRCNN-10.onnx and the ONNX model-loading snippet in the issue. Confirm whether the distributed artifact contains graph initializers, then compare it with the repository’s other pretrained model assets. Done means the Mask-RCNN artifact is a usable pretrained model with weights and the reported initializer check succeeds.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
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.