rai's repositories
mlmodelscope
MLModelScope is an open source, extensible, and customizable platform to facilitate evaluation and measurement of ML models within AI pipelines.
go-tensorrt
Go binding to TensorRT C API to do inference with pre-trained model in Go
tensorflow-go-examples
Examples of using TensorFlow Go API for different Deep Learning models
tensorflow
TensorFlow agent for MLModelScope
dlframework
Common code for all deep learning predictors used by MLModelScope
dockerfile-builder
The aim of D4P is to enrich the PowerPC container ecosystem by providing both a platform for developers to create docker containers, and for PowerPC community to find docker images. We have already built and published over 200 docker images using this platform, and they are available both in the D4P's image catalog or accessible through the C3SR center's Docker Hub link.
evaluation
Evaluation tools for model performance / accuracy for MLModelScope
trims_mxnet
run using https://github.com/rai-project/trims-tools
cudnn_scope
Benchmark cuDNN for different Deep Learning layers.
onnx_examples
ONNX model inference using different backend frameworks
pytorch_dlperf_opt
Tensors and Dynamic neural networks in Python with strong GPU acceleration
tensorrt_samples
Samples from TensorRT installation