Deepboof
| Project Name | Stars | Downloads | Repos Using This | Packages Using This | Most Recent Commit | Total Releases | Latest Release | Open Issues | License | Language |
|---|---|---|---|---|---|---|---|---|---|---|
| Pytorch | 64,630 | 146 | 11 hours ago | 23 | August 10, 2022 | 11,508 | other | C++ | ||
| Tensors and Dynamic neural networks in Python with strong GPU acceleration | ||||||||||
| Digits | 4,047 | 3 years ago | 614 | other | HTML | |||||
| Deep Learning GPU Training System | ||||||||||
| Neuralart | 2,352 | 6 years ago | 6 | mit | Lua | |||||
| An implementation of the paper 'A Neural Algorithm of Artistic Style'. | ||||||||||
| Deepframeworks | 2,077 | 6 years ago | 17 | |||||||
| Evaluation of Deep Learning Frameworks | ||||||||||
| Multipathnet | 1,361 | 4 years ago | 23 | other | Lua | |||||
| A Torch implementation of the object detection network from "A MultiPath Network for Object Detection" (https://arxiv.org/abs/1604.02135) | ||||||||||
| Texture_nets | 1,109 | 5 years ago | 41 | apache-2.0 | Lua | |||||
| Code for "Texture Networks: Feed-forward Synthesis of Textures and Stylized Images" paper. | ||||||||||
| Crepe | 829 | 4 years ago | 2 | bsd-3-clause | Lua | |||||
| Character-level Convolutional Networks for Text Classification | ||||||||||
| Resnet 1k Layers | 740 | 6 years ago | 1 | Lua | ||||||
| Deep Residual Networks with 1K Layers | ||||||||||
| Graph_transformer_networks | 694 | 2 months ago | 12 | Jupyter Notebook | ||||||
| Graph Transformer Networks (Authors' PyTorch implementation for the NeurIPS 19 paper) | ||||||||||
| Awesome_deep_learning_interpretability | 645 | a month ago | 2 | mit | ||||||
| 深度学习近年来关于神经网络模型解释性的相关高引用/顶会论文(附带代码) | ||||||||||
DeepBoof is a Java library for running deep neural networks trained using other projects (e.g. Torch and Caffe) with a focus on processing image data. Additional tools include visualization and network training. Image processing is done using BoofCV. While it has been designed to work with Torch and Caffe it does not depend either library for its core functionality.
Installation
Gradle is used to build DeepBoof and will automatically download all dependencies.
Running
To get started classifying images simply load the Gradle project into you favorite IDE (probably IntelliJ or Eclipse) and run ExampleClassifyVggCifar10. This example downloads the network and testing data, then starts the classifier.
Alternatively, you can just build and run any example from the command-line using Gradle directly:
gradle exampleRun -Pwhich=ExampleClassifyCifar10TestSet
Future Work
DeepBoof is in an early state of development. The following are areas it needs the most improvement in:
- Support for Caffe models (already started)
- Native implementations of functions
- GPU implementations of functions
