knjcode/mxnet-finetuner
An all-in-one Deep Learning toolkit for image classification to fine-tuning pretrained models using MXNet.
This toolkit helps researchers and machine learning practitioners quickly train and evaluate custom image classification models. You provide a collection of images organized into folders representing different categories, and it outputs a fine-tuned model, along with performance graphs and confusion matrices. It's designed for anyone needing to classify images using deep learning, even with limited data.
106 stars. No commits in the last 6 months.
Use this if you need to adapt powerful existing image recognition models to classify your specific sets of images without starting from scratch.
Not ideal if you are looking to build deep learning models for tasks other than image classification, such as object detection or natural language processing.
Stars
106
Forks
8
Language
Jupyter Notebook
License
—
Category
Last pushed
Nov 02, 2018
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/knjcode/mxnet-finetuner"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
raghakot/keras-resnet
Residual networks implementation using Keras-1.0 functional API
titu1994/DenseNet
DenseNet implementation in Keras
liuzhuang13/DenseNet
Densely Connected Convolutional Networks, In CVPR 2017 (Best Paper Award).
BIGBALLON/cifar-10-cnn
Play deep learning with CIFAR datasets
bamos/densenet.pytorch
A PyTorch implementation of DenseNet.