An open-source deep learning API and server written in C++ that supports multiple backends like PyTorch, TensorRT, and TensorFlow for training and inference.
DeepDetect is an open-source machine learning API and server written in C++11 that simplifies the integration of state-of-the-art deep learning into existing applications. It provides a high-level interface for both training and inference across various data types like images, text, and time series, with a focus on simplicity and performance. The server supports multiple backends, including Caffe, TensorFlow, PyTorch, and XGBoost, enabling diverse machine learning tasks such as classification, object detection, segmentation, and NLP.
Developers and engineers building production machine learning applications who need a unified, high-performance serving layer for multiple deep learning frameworks without database dependencies. It is also suitable for teams requiring easy deployment of models to embedded platforms like NVIDIA GPUs with TensorRT or ARM CPUs with NCNN.
Developers choose DeepDetect for its multi-backend support, which allows leveraging the best tools from various ML libraries through a single API, and its built-in similarity search using Annoy and FAISS for indexing predicted features. Its emphasis on simplicity, high performance on multicore CPUs and GPUs, and seamless integration into existing applications without external database dependencies make it stand out.
Deep Learning API and Server in C++14 support for PyTorch,TensorRT, Dlib, NCNN, Tensorflow, XGBoost and TSNE
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.