MadryLab / Imagenetmultilabel
Licence: mit
Fine-grained ImageNet annotations
Stars: ✭ 22
Labels
Projects that are alternatives of or similar to Imagenetmultilabel
Intro Python
Python pour Statistique et Science des Données -- Syntaxe, Trafic de Données, Graphes, Programmation, Apprentissage
Stars: ✭ 21 (-4.55%)
Mutual labels: jupyter-notebook
Deeplearning tutorial
Deep Learning Tutorial in Python with Keras library
Stars: ✭ 21 (-4.55%)
Mutual labels: jupyter-notebook
Boston Housing Prices
🏠 Predict the selling price of a new home in Boston, Massachusetts area
Stars: ✭ 21 (-4.55%)
Mutual labels: jupyter-notebook
Servenet
Service Classification based on Service Description
Stars: ✭ 21 (-4.55%)
Mutual labels: jupyter-notebook
Word2vec Workshop
word2vec workshop - a conceptual introduction and practical application
Stars: ✭ 21 (-4.55%)
Mutual labels: jupyter-notebook
Movie recommender
MovieLens based recommender system.使用MovieLens数据集训练的电影推荐系统。
Stars: ✭ 914 (+4054.55%)
Mutual labels: jupyter-notebook
Pytorch Examples
MNIST Clasification with Pytorch
Stars: ✭ 21 (-4.55%)
Mutual labels: jupyter-notebook
Techtalks
Slides and Supplementary Material of the past TechTalks at the Karlsruhe Machine Learning, Statistics and AI Meetup
Stars: ✭ 21 (-4.55%)
Mutual labels: jupyter-notebook
Notebook playground
Notebooks for playing around with datasets etc.
Stars: ✭ 21 (-4.55%)
Mutual labels: jupyter-notebook
Glo4030 Labs
Laboratoires du cours GLO-4030/GLO-7030
Stars: ✭ 21 (-4.55%)
Mutual labels: jupyter-notebook
Osgeolive Notebooks
Repository for OSGeo-Live Jupyter Notebooks
Stars: ✭ 21 (-4.55%)
Mutual labels: jupyter-notebook
Pytorch Struct
Fast, general, and tested differentiable structured prediction in PyTorch
Stars: ✭ 913 (+4050%)
Mutual labels: jupyter-notebook
Fine-grained annotations for the ImageNet validation set
This is the data collected for our paper "From ImageNet to Image Classification: Contextualizing Progress on Benchmarks" (preprint, blog).
Parsing the annotations
Our annotations are available as pandas
dataframes in data/annotations_{contains,classify}_task.pkl
. These dataframes included both the raw data collected (after quality control), as well as the aggregate quantities we computed for our analysis. The rest of the files in data
contain auxiliary information.
The easiest way to navigate these files is by running the jupyter notebook (basic_data_loading.ipynb
) which loads all files, providing an explanation for each field.
Citation
@inproceedings{tsipras2020imagenet,
title={From ImageNet to Image Classification: Contextualizing Progress on Benchmarks},
author={Dimitris Tsipras and Shibani Santurkar and Logan Engstrom and Andrew Ilyas and Aleksander Madry},
booktitle={ArXiv preprint arXiv:2005.11295},
year={2020}
}
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].