fostiropoulos/ablator
Model Ablation Tool-Kit for Deep Learning Model
ABLATOR streamlines the process of evaluating how different parts of a deep learning model contribute to its overall performance. It takes in various model configurations and hyperparameters, then automatically runs multiple experiments in parallel, producing performance metrics and visualizations. This tool is for machine learning researchers and practitioners who build and optimize complex neural networks.
No commits in the last 6 months.
Use this if you need to systematically test how changes to your deep learning model's architecture or training settings impact its performance across many experiments.
Not ideal if you are not working with deep learning models or only need to run a few simple, sequential experiments.
Stars
39
Forks
33
Language
Python
License
GPL-3.0
Category
Last pushed
Dec 20, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/fostiropoulos/ablator"
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, ...)