Download Latest Version v8.4.201 - _ultralytics 8.4.201_ Up to 15x faster PIL plotting across all tasks (#27014) source code.zip (3.7 MB)
Home / v8.4.198
Name Modified Size InfoDownloads / Week
Parent folder
sbom.spdx.json 2026-11-02 736.2 kB
README.md 2026-11-02 3.2 kB
v8.4.198 - _ultralytics 8.4.198_ Save NumPy float64 values as numbers in YAML files (#26993) source code.tar.gz 2026-11-02 2.8 MB
v8.4.198 - _ultralytics 8.4.198_ Save NumPy float64 values as numbers in YAML files (#26993) source code.zip 2026-11-02 3.7 MB
Totals: 4 Items   7.2 MB 0

🌟 Summary

Ultralytics 8.4.198 makes training settings and YAML files more reliable, alongside fixes to downloads, dataset errors, and documentation. No model architecture or pretrained-weight changes are included.

πŸ“Š Key Changes

  • NumPy learning rates now save correctly in YAML β€” The main change converts np.float64 values to ordinary numeric values when writing YAML. Training arguments such as sweep-generated learning rates can now be saved and reused from args.yaml.
  • More robust YAML parsing β€” Fixes handling of block-scalar indentation, whitespace-only lines, and nodes written on their own lines, bringing the built-in parser closer to YAML conventions.
  • Improved download and dataset errors β€” Downloads now identify themselves with an Ultralytics User-Agent, helping avoid some servers rejecting requests. Missing classification datasets now produce a clear file-not-found error instead of a confusing failed-download message.
  • More dependable training and logging β€” Updates the minimum supported versions of ultralytics-thop and ultralytics-platform; also suppresses a Triton warning that could appear during profiling.
  • Clearer documentation β€” Explains how relative project paths are resolved and standardizes how metrics such as mAP and depth accuracy are written across docs and benchmark tables.

🎯 Purpose & Impact

  • πŸ” Reuse training configurations more easily: NumPy-based hyperparameter sweeps no longer produce YAML values that reload as strings and fail validation.
  • 🧰 Fewer confusing failures: YAML parsing, downloads, and missing-dataset handling are more predictable.
  • πŸ“š Easier to follow guidance and compare results: Consistent metric labels and clarified path behavior reduce ambiguity.
  • βœ… No model migration needed: These updates improve tooling and documentation rather than changing model behavior.

What's Changed

Full Changelog: https://github.com/ultralytics/ultralytics/compare/v8.4.197...v8.4.198

Source: README.md, updated 2026-11-02