szymonmaszke/torchlayers
Shape and dimension inference (Keras-like) for PyTorch layers and neural networks
This tool helps machine learning engineers or researchers build neural networks in PyTorch more efficiently. You provide your network architecture and an example of the input data, and it automatically figures out the correct sizes and types for many common layers. This means less manual calculation and debugging of layer dimensions, allowing you to focus on the model's design.
570 stars. No commits in the last 6 months. Available on PyPI.
Use this if you are building neural networks in PyTorch and want to automatically infer layer input shapes and choose appropriate convolutional or batch normalization layers based on your input data.
Not ideal if you prefer to manually define every layer's dimensions and types, or if you are not working with PyTorch.
Stars
570
Forks
44
Language
Python
License
MIT
Category
Last pushed
Jun 13, 2022
Commits (30d)
0
Dependencies
1
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/szymonmaszke/torchlayers"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
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, ...)