janosh/tensorboard-reducer
Reduce multiple PyTorch TensorBoard runs to new event (or CSV) files.
When training multiple machine learning models or ensembles, this tool helps you combine and analyze their performance metrics. It takes individual experiment logs (like those from PyTorch's TensorBoard) and computes statistical summaries, outputting a cleaner, aggregated view of your models' behavior. This is useful for machine learning researchers and data scientists who need to compare models or understand performance variations.
Available on PyPI.
Use this if you have multiple TensorBoard log directories from different training runs and want to reduce them into a single, statistically aggregated view (e.g., mean, standard deviation) for easier analysis and comparison.
Not ideal if you are working exclusively with TensorFlow event files or only need to view individual experiment logs without aggregation.
Stars
76
Forks
4
Language
Python
License
MIT
Category
Last pushed
Jan 05, 2026
Commits (30d)
0
Dependencies
4
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/janosh/tensorboard-reducer"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
pytorch/pytorch
Tensors and Dynamic neural networks in Python with strong GPU acceleration
keras-team/keras
Deep Learning for humans
Lightning-AI/torchmetrics
Machine learning metrics for distributed, scalable PyTorch applications.
Lightning-AI/pytorch-lightning
Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.
lanpa/tensorboardX
tensorboard for pytorch (and chainer, mxnet, numpy, ...)