31 datasets found

NATS-Bench: Benchmarking NAS algorithms for architecture topology and size

A dataset for training machine learning models for routing congestion prediction

The dataset used in this paper is the MLPerf benchmark dataset.

The STMNIST dataset is a benchmark for image classification.

Mibench2 is a benchmark suite for embedded systems.

PROBEN1 is a set of neural network problems and benchmarking rules.

The set-asp-gauss dataset, a benchmark set for SAT solvers.

The SATLIB dataset, a collection of SAT instances and solvers.

The dataset used in the Time Leap Challenge for SAT-Solving, comparing old solvers on new hardware with modern solvers on old hardware.

The dataset used in the paper is the SuperGLUE benchmark, which includes 17 tasks: STS-B, MRPC, MNLI, QNL, QNLI, CoLA, SST-2, MRPC, GLUE, NLI, NQ, ReCoRD, ReCoRD-Sub,...

TinyML benchmarking with Fast Retargeting

A large benchmarking effort that includes a dataset repository curated for SR, as well as a benchmarking library designed to allow researchers to easily contribute methods.

Open Graph Benchmark: Datasets for machine learning on graphs.

The LFR benchmark is a collection of artificial networks with a known community structure.

A benchmark dataset for DNA language models, focusing on biologically meaningful tasks.

A large scale benchmark for uplift modeling.

The dataset used for benchmarking protein-ligand interaction prediction models.

The dataset used for benchmarking machine learning force fields (MLFF) and jet tagging.

The YCB object and model set is a benchmark for manipulation research, consisting of 15 object categories and 3D models.

Bighand2.2m benchmark: Hand pose dataset and state of the art analysis.