samrere/pytortto
deep learning from scratch. uses numpy/cupy, trains in GPU, follows pytorch API
This project offers a deep learning framework built from scratch using NumPy and CuPy, designed for those who want to understand the inner workings of models without the complexity of a full-fledged library. You input your datasets and model architectures, and it outputs trained deep learning models and gradients, providing a clear view into each computational step. This is ideal for deep learning researchers and students who are focused on pedagogical exploration rather than raw performance.
No commits in the last 6 months.
Use this if you are a deep learning student or researcher who wants to learn how frameworks like PyTorch handle operations, backpropagation, and memory management by implementing a full-featured framework yourself.
Not ideal if you need to train large-scale production models quickly, as its primary goal is educational insight, not speed or cutting-edge features.
Stars
21
Forks
1
Language
Python
License
MIT
Category
Last pushed
Sep 05, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/samrere/pytortto"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
digantamisra98/Mish
Official Repository for "Mish: A Self Regularized Non-Monotonic Neural Activation Function" [BMVC 2020]
Sentdex/nnfs_book
Sample code from the Neural Networks from Scratch book.
itdxer/neupy
NeuPy is a Tensorflow based python library for prototyping and building neural networks
vzhou842/cnn-from-scratch
A Convolutional Neural Network implemented from scratch (using only numpy) in Python.
nicklashansen/rnn_lstm_from_scratch
How to build RNNs and LSTMs from scratch with NumPy.