Skip to content

ML Application · Python

steel-defect-classifier-railcompute

What it is

This repository provides a trained ResNet-18 model and inference scripts for classifying six types of steel surface defects. It showcases the use of the RailCompute autonomous training platform to identify and correct a data leakage issue in the NEU-DET dataset.

Scored at80b10f915 Nov 2026Changes since

Merit describes the code at this commit. Later pushes count once the owner rescans. How merit is scored

Distribution based on AI work

1 / 2
Computer Vision: 26.7%Machine Learning: 23.3%AI Agents: 20.0%Data Science: 16.7%MLOps: 13.3%
  • Computer Vision27%
  • Machine Learning23%
  • AI Agents20%
  • Data Science17%
  • MLOps13%

Each field's share of the project's AI work, as scoring counts it. It ranks in the field it is most about.

What the judge found

Read from the project's code at its scored commit.

Strengths3

  • Clear documentation of the training process and identified pitfalls.
  • Runnable inference scripts with pre-trained weights provided.
  • Demonstrates practical application of an autonomous training platform (RailCompute).

Limitations

The owner keeps this project's limitations private.

Around it on the Computer Vision board

Whole board
  1. 17background-subtractionEducational Implementation · Jupyter Notebook42.1/100ImplementationPop Alexandru
  2. 18, shared rankarc_baselineCompetition Solution41.4/100ImplementationSimon Strandgaard
  3. 18, shared ranksteel-defect-classifier-railcomputeML Application · Python41.4/100ImplementationAditya Ray
  4. 20face-lock-promptsEducational Implementation41.1/100Implementationkarims
  5. 21Multi-Task-RailML Application · Jupyter Notebook38.1/100ExplorationSuceveanu Mircea Dan Sandu

More from Aditya Ray