Project-MONAI / Project-MONAI/MONAI

Wrong default value for conv1_t_stride in ResNet __init__

Open
#7,572 3 comments 1 reaction 0 assignees View on GitHub

Nobody has claimed this yet.

community
Dominant language
Python
Stars
8.7k
Forks
1.6k
Avg merge
5d 1h
Merged PRs (30d)
20

Description

During the implementation for ResNetEncoder for FlexibleUNet, I encountered a bug related to the default value for conv1_t_stride in ResNet.__init__. Upon investigation, it became evident that the default value should be 2 instead of 1 .

Also, stride for the first convolution is 2 in the MedicalNet repository. So I suppose all 3D pretrained ResNet models for classification at this moment work not as intended.

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 in monai/networks/nets/resnet.py at ResNet.init, specifically the conv1_t_stride default. Compare the current default with the MedicalNet ResNet implementation and inspect how 3D pretrained ResNet models consume it. Done means the default and affected model behavior match the intended first-convolution stride.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, pytorch
Domain
machine-learning
Issue type
Bug
Difficulty
2/5
Estimated time
1-3 hours
Activity status
Stale
Clarity
Clearly specified
Newbie friendliness
48/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.