Datasets
Browse state-of-the-art leaderboards by dataset and benchmark.
ImageNet is an image database organized according to the WordNet hierarchy, in which each node of the hierarchy is depicted by hundreds and thousands of images.
COCO is a large-scale object detection, segmentation, and captioning dataset.
LFW is a database of face photographs designed for studying the problem of unconstrained face recognition.
MegaFace is a large-scale public face recognition dataset containing 4.7 million photos of 672,000 distinct individuals.
Measuring Massive Multitask Language Understanding. A test to measure a text model's multitask accuracy.
Stanford Question Answering Dataset (SQuAD) is a reading comprehension dataset.
The CNN / DailyMail Dataset is an English-language dataset containing just over 300k unique news articles as written by journalists.
LibriSpeech is a corpus of approximately 1000 hours of 16kHz read English speech.
Common Voice is a massive, crowdsourced multilingual audio corpus for speech recognition.
The 14th Community Wide Experiment on the Critical Assessment of Techniques for Protein Structure Prediction.
The HumanEval dataset contains 164 hand-written programming problems.