songlei00/easytorch
基于Python的numpy实现的简易深度学习框架，包括自动求导、优化器、layer等的实现。
This project helps Python developers learn the core concepts behind deep learning frameworks like PyTorch by providing a simplified, NumPy-based implementation. It takes in raw numerical data and model architectures, allowing you to train neural networks and output predictions. This is for software developers, data scientists, or students who want to understand the underlying mechanics of deep learning, from automatic differentiation to optimizers and layers.
No commits in the last 6 months.
Use this if you are a Python developer or student who wants to grasp how deep learning frameworks work under the hood without the complexity of production-grade libraries.
Not ideal if you need a high-performance deep learning framework for large-scale production applications or research with complex models.
Stars
78
Forks
3
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Apr 17, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/songlei00/easytorch"
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, ...)