fabprezja/deep-fast-vision
A Python library for rapid prototyping of deep transfer learning vision models.
This tool helps data scientists and machine learning engineers quickly build and evaluate deep learning models for image classification tasks. You provide your image datasets, choose a pre-trained model architecture, and the tool automates many of the complex setup steps. What comes out is a trained image classification model, along with performance metrics, validation curves, and confusion matrices to understand its effectiveness.
No commits in the last 6 months.
Use this if you need to rapidly prototype and iterate on deep transfer learning models for computer vision problems without getting bogged down in boilerplate code.
Not ideal if you need extremely fine-grained, manual control over every single aspect of your deep learning model architecture and training process from scratch.
Stars
13
Forks
1
Language
Python
License
MIT
Category
Last pushed
Nov 15, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/fabprezja/deep-fast-vision"
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, ...)