SHARK
SHARK is a fast, modular, feature-rich open-source C++ machine learning library. It provides methods for linear and nonlinear optimization, kernel-based learning algorithms, neural networks, and various other machine learning techniques. It serves as a powerful toolbox for real-world applications as well as research. Shark depends on Boost and CMake. It is compatible with Windows, Solaris, MacOS X, and Linux. Shark is licensed under the permissive GNU Lesser General Public License. Shark provides an excellent trade-off between flexibility and ease-of-use on the one hand, and computational efficiency on the other. Shark offers numerous algorithms from various machine learning and computational intelligence domains in a way that they can be easily combined and extended. Shark comes with a lot of powerful algorithms that are to our best knowledge not implemented in any other library.
Learn more
NeuroIntelligence
NeuroIntelligence is a neural networks software application designed to assist neural network, data mining, pattern recognition, and predictive modeling experts in solving real-world problems. NeuroIntelligence features only proven neural network modeling algorithms and neural net techniques; software is fast and easy-to-use. Visualized architecture search, neural network training and testing. Neural network architecture search, fitness bars, network training graphs comparison. Training graphs, dataset error, network error, weights and errors distribution, neural network input importance. Testing, actual vs. output graph, scatter plot, response graph, ROC curve, confusion matrix. The interface of NeuroIntelligence is optimized to solve data mining, forecasting, classification and pattern recognition problems. You can create a better solution much faster using the tool's easy-to-use GUI and unique time-saving capabilities.
Learn more
DeePhi Quantization Tool
This is a model quantization tool for convolution neural networks(CNN). This tool could quantize both weights/biases and activations from 32-bit floating-point (FP32) format to 8-bit integer(INT8) format or any other bit depths. With this tool, you can boost the inference performance and efficiency significantly, while maintaining the accuracy. This tool supports common layer types in neural networks, including convolution, pooling, fully-connected, batch normalization and so on. The quantization tool does not need the retraining of the network or labeled datasets, only one batch of pictures are needed. The process time ranges from a few seconds to several minutes depending on the size of neural network, which makes rapid model update possible. This tool is collaborative optimized for DeePhi DPU and could generate INT8 format model files required by DNNC.
Learn more
Chainer
A powerful, flexible, and intuitive framework for neural networks. Chainer supports CUDA computation. It only requires a few lines of code to leverage a GPU. It also runs on multiple GPUs with little effort. Chainer supports various network architectures including feed-forward nets, convnets, recurrent nets and recursive nets. It also supports per-batch architectures. Forward computation can include any control flow statements of Python without lacking the ability of backpropagation. It makes code intuitive and easy to debug. Comes with ChainerRLA, a library that implements various state-of-the-art deep reinforcement algorithms. Also, with ChainerCVA, a collection of tools to train and run neural networks for computer vision tasks. Chainer supports CUDA computation. It only requires a few lines of code to leverage a GPU. It also runs on multiple GPUs with little effort.
Learn more