atharvaaalok/deepfusion
A highly modular and customizable Deep Learning framework.
This tool helps deep learning engineers and researchers build neural networks with very explicit control over every part of the network architecture. It allows you to define neural network components like data, operations, and entire networks, specifying how they connect. You put in your desired network structure, and it produces a working, customizable neural network ready for training and analysis.
No commits in the last 6 months. Available on PyPI.
Use this if you need fine-grained control to design and debug unique neural network architectures or complex training procedures.
Not ideal if you prefer high-level frameworks for standard deep learning tasks without needing to dive deep into component-level definitions.
Stars
25
Forks
2
Language
Python
License
MIT
Category
Last pushed
May 23, 2024
Commits (30d)
0
Dependencies
4
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/atharvaaalok/deepfusion"
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, ...)