Cadene / Cadene/pretrained-models.pytorch

What parameters should I use to reproduce the pre-training process of ResNet18

Open
#205 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
9.1k
Forks
1.8k
PR merge metrics
No merged PRs in 30d

Description

I use sgd 0.01, and scheduled 30, 60, 90 epoches with lr decay rate 0.1, momentum is set at 0.9 with nesterov enabled, but I can not get the results as good as directly downloaded model, which is 8% less in top-1. Can the owner give me some tips on how to train the pre-trained model?

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

No files, tests, or entry points are mentioned. Start by reviewing the repository's ResNet18 training and pretrained-model documentation, then compare the reported SGD settings with the documented training procedure; done would require a documented, reproducible explanation for the top-1 accuracy gap.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, pytorch
Domain
machine-learning
Issue type
Bug
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
10/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.