csiro-biomass-agentic-solution

KO | EN

gitlite — search

#javascript #php #ruby #python #java #erlang #c-sharp #jquery #game-engine #module #dotfiles #macos

csiro-biomass-agentic-solution

★ 33 Open GitHub ↗

5th place solution repository for Kaggle CSIRO Image2Biomass, including the experiment workflow used with Claude Code and Codex.

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# CSIRO Pasture Biomass Prediction — 5th Place Solution Repository

This repository contains the code used for my **5th place finish out of 3,803 teams (gold medal)** in the Kaggle competition [CSIRO - Image2Biomass Prediction](https://www.kaggle.com/competitions/csiro-biomass).

I participated by delegating almost all implementation work to Claude Code (Opus 4.5) and Codex (GPT-5.2 xhigh). I also wrote a blog post about that experience.

Blog post (Japanese): [Claude Code / CodexでKaggle金メダルを取った話](https://zenn.dev/chiman/articles/b233cc808d6af3)

## About This Repository

This repository intentionally preserves the code, configs, and analysis outputs I actually used during the competition without over-cleaning everything. The goal is to show what collaboration with coding agents looked like in practice.

### Notes

- `_CLAUDE.md` / `_AGENTS.md` are instruction files I used for coding agents during the competition. They are prefixed with `_` **to avoid unintended behavior in other people's environments**. Claude Code / Codex automatically read `CLAUDE.md` / `AGENTS.md` from the repository root and follow those instructions, so publishing them as-is could cause unexpected behavior when someone clones the repo. They are included here for reference only.
- The competition dataset (images and CSV files) is **not** included. Please download it from [Kaggle](https://www.kaggle.com/competitions/csiro-biomass/data).

## Why It Is Structured This Way

To let coding agents (Claude Code / Codex) iterate on experiments quickly, I used the following setup.

### Two-Level Structure: `EXP` + `child-exp`

- When I made a major pipeline change in `train.py`, I created a new `EXP` directory
- When I only changed parameters, loss, or model settings, I ran a new `child-exp` (YAML config) under the same `EXP`

This made it possible to give short, concrete instructions such as: "Create `child-exp003` under `EXP113` and change the loss to XX."

### Instruction Files for Coding Agents

- **`_CLAUDE.md`**: Instructions for Claude Code. It includes the correct evaluation function, common bug patterns, backward compatibility rules, and other guardrails. It grew to 430 lines as I kept adding lessons learned during the competition.
- **`_AGENTS.md`**: Instructions for Codex. It is a slimmed-down version of `CLAUDE.md` with an emphasis on guardrails such as "these changes tend to hurt LB."

### `EXP_SUMMARY.md` (Experiment History)

This file records CV, LB, success/failure, and notes for every experiment. I used it as a guardrail to prevent coding agents from repeatedly suggesting ideas that had already failed.

## Experiment Workflow

```text
1. Ask the coding agent to write experiment code
   -> Create EXP/{EXPNO}/config/child-{childexpno}.yaml

2. Run execute_train.ipynb on Google Colab
   -> Results are written to EXP/{EXPNO}/outputs/child-{childexpno}/
      |- oof_predictions.csv   # Out-of-fold predictions
      `- results.json          # CV scores

3. Submit with palla-csiro-inferece.ipynb on Kaggle Notebook
   -> Check the leaderboard score

4. Update EXP_SUMMARY.md
   -> Add experiment name, changes, CV, LB, success/failure, and notes
```

## Repository Layout

```text
.
|- _CLAUDE.md                  # Claude Code instruction file (reference only)
|- _AGENTS.md                  # Codex instruction file (reference only)
|- execute_train.ipynb         # Notebook for training on Google Colab
|- EXECUTE_TRAIN_README.md     # How to use execute_train.ipynb
|- palla-csiro-inferece.ipynb  # Notebook for inference and submission on Kaggle
|
|- EXP/
|  |- EXP_SUMMARY.md           # Full experiment log (CV, LB, success/failure, notes)
|  |- EXP060/                  # Main experiment line (EVA02-CLIP -> DINOv3)
|  |  |- train.py              # Training script
|  |  |- infer.py              # Inference script
|  |  |- config/               # Two representative child-exp configs
|  |  `- outputs/              # Experiment outputs (oof, results.json)
|  `- EXP113/                  # Final submission experiment (Private best: child-exp020)
|     |- train.py
|     |- infer.py
|     |- config/               # Six child-exp configs including the final submission setup
|     `- outputs/
|
|- docs/                       # Intentionally messy in places to preserve the real workflow
|  |- OVERVIEW.md              # Competition overview
|  |- DATASET.md               # Dataset description
|  |- Idea_Research/           # Idea notes, Gemini Deep Research results, etc.
|  `- papers/                  # Notes on reference papers
|
`- output/
   `- CV_LB/STATE_SEASON/      # CV-LB correlation analysis outputs generated by agents
```

## Key Files

| File | Description |
|------|-------------|
| `EXP/EXP_SUMMARY.md` | Full log of experiments, including both successes and failures. It functioned as the coding agent's "memory." |
| `_CLAUDE.md` | A 430-line instruction file that grew from repeated painful lessons during the competition. |
| `docs/Idea_Research/` | Raw idea notes, ranging from rough memos to Gemini Deep Research outputs. |
| `execute_train.ipynb` | Colab notebook for running training. You can launch an experiment by changing only the EXP name and child-exp name. |
| `palla-csiro-inferece.ipynb` | Kaggle notebook for inference and submission. |
| `output/CV_LB/STATE_SEASON/` | Example outputs from CV-LB correlation analysis. I intentionally left some of these analysis artifacts to show how I used coding agents for OOF analysis. |

## Detailed Solution Write-Ups

- [Speaker Deck: Competition Retrospective](https://speakerdeck.com/chihironakayama/cao-konhezhen-rifan-ri)
- [Kaggle Write-up: 5th Place Solution](https://www.kaggle.com/competitions/csiro-biomass/writeups/5th-place-solution)

### If You Want to See the Private-Best Code

My best Private LB setup was `EXP/EXP113/config/child-exp020.yaml` (DINOv3 Large, 864px, Private 0.66).

See:

- `EXP/EXP113/train.py` for training
- `EXP/EXP113/infer.py` for inference

## Experiment Environment

- **Code authoring**: Local Mac + Claude Code / Codex -> edited on Google Drive
- **Training**: Google Colab (A100 / L4)
- **Inference / submission**: Kaggle Notebooks

csiro-biomass-agentic-solution

Explore Similar Repositories

Was this content helpful?

Recent Feedback

Download README