apple/parameterized-transforms
torchvision-based transforms that provide access to parameterization
This tool helps machine learning engineers and researchers precisely control image augmentation in computer vision workflows. You provide an image, and it can either return an augmented image along with the exact parameters used for that change, or it can take an image and specific augmentation parameters to produce a custom augmented image. This allows for reproducible and fine-tuned data augmentation.
Use this if you need to understand or control the exact parameters of image transformations for data augmentation in your computer vision models.
Not ideal if you are looking for a simple, off-the-shelf image augmentation library without needing explicit control or access to transformation parameters.
Stars
16
Forks
2
Language
Python
License
Apache-2.0
Category
Last pushed
Dec 04, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/apple/parameterized-transforms"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Jittor/jittor
Jittor is a high-performance deep learning framework based on JIT compiling and meta-operators.
berniwal/swin-transformer-pytorch
Implementation of the Swin Transformer in PyTorch.
zhanghang1989/ResNeSt
ResNeSt: Split-Attention Networks
NVlabs/FasterViT
[ICLR 2024] Official PyTorch implementation of FasterViT: Fast Vision Transformers with...
ViTAE-Transformer/ViTPose
The official repo for [NeurIPS'22] "ViTPose: Simple Vision Transformer Baselines for Human Pose...