onnx-runtime · ONNX Runtime is a performance-focused inference engine for ONNX (Open Neural Network Exchange) models.
Group: com.microsoft.onnxruntime - All Dependencies
onnx-runtime · ONNX Runtime is a performance-focused inference engine for ONNX (Open Neural Network Exchange) models.
onnx-runtime · The ONNX Runtime Mobile package is a size optimized inference library for executing ONNX (Open Neural Network Exchange) models on Android. This package is built from the open source inference engine but with reduced disk footprint targeting mobile platforms. To minimize binary size this library supports a reduced set of operators and types aligned to typical mobile applications. The ONNX model must be converted to ORT format in order to use it with this package. See https://onnxruntime.ai/docs/reference/ort-format-models.html for more details.
onnx-runtime · ONNX Runtime is a performance-focused inference engine for ONNX (Open Neural Network Exchange) models. This package contains the Android (aar) build of ONNX Runtime. It includes support for all types and operators, for ONNX format models. All standard ONNX models can be executed with this package. As such the binary size and memory usage will be larger than the onnxruntime-mobile package.
onnxruntime-extensions · ONNXRuntime-Extensions is a library for Android for pre- and post-processing.
onnxruntime-training · The onnxruntime-training android package is designed to efficiently train and infer a wide range of ONNX models on edge devices, such as mobile phones, tablets, and other portable devices with a focus on minimizing resource usage and maximizing accuracy.See https://github.com/microsoft/onnxruntime-training-examples/tree/master/on_device_training for more details.
onnxruntime-extensions · ONNXRuntime-Extensions is a library for pre- and post-processing.