100+ datasets found
  1. T

    stanford_dogs

    • tensorflow.org
    • huggingface.co
    Updated Jan 13, 2023
    + more versions
    Share
    FacebookFacebook
    TwitterTwitter
    Email
    Click to copy link
    Link copied
    Close
    Cite
    (2023). stanford_dogs [Dataset]. https://www.tensorflow.org/datasets/catalog/stanford_dogs
    Explore at:
    Dataset updated
    Jan 13, 2023
    Description

    The Stanford Dogs dataset contains images of 120 breeds of dogs from around the world. This dataset has been built using images and annotation from ImageNet for the task of fine-grained image categorization. There are 20,580 images, out of which 12,000 are used for training and 8580 for testing. Class labels and bounding box annotations are provided for all the 12,000 images.

    To use this dataset:

    import tensorflow_datasets as tfds
    
    ds = tfds.load('stanford_dogs', split='train')
    for ex in ds.take(4):
     print(ex)
    

    See the guide for more informations on tensorflow_datasets.

    https://storage.googleapis.com/tfds-data/visualization/fig/stanford_dogs-0.2.0.png" alt="Visualization" width="500px">

  2. P

    Stanford Dogs Dataset

    • paperswithcode.com
    Updated Feb 25, 2021
    Share
    FacebookFacebook
    TwitterTwitter
    Email
    Click to copy link
    Link copied
    Close
    Cite
    (2021). Stanford Dogs Dataset [Dataset]. https://paperswithcode.com/dataset/stanford-dogs
    Explore at:
    Dataset updated
    Feb 25, 2021
    Description

    The Stanford Dogs dataset contains 20,580 images of 120 classes of dogs from around the world, which are divided into 12,000 images for training and 8,580 images for testing.

  3. P

    Tsinghua Dogs Dataset

    • paperswithcode.com
    Updated Sep 30, 2020
    + more versions
    Share
    FacebookFacebook
    TwitterTwitter
    Email
    Click to copy link
    Link copied
    Close
    Cite
    Ding-Nan Zo; Song-Hai Zhang; Tai-Jiang M; Min Zhang (2020). Tsinghua Dogs Dataset [Dataset]. https://paperswithcode.com/dataset/tsinghua-dogs
    Explore at:
    Dataset updated
    Sep 30, 2020
    Authors
    Ding-Nan Zo; Song-Hai Zhang; Tai-Jiang M; Min Zhang
    Description

    Tsinghua Dogs is a fine-grained classification dataset for dogs, over 65% of whose images are collected from people's real life. Each dog breed in the dataset contains at least 200 images and a maximum of 7,449 images, basically in proportion to their frequency of occurrence in China, so it significantly increases the diversity for each breed over existing dataset. Furthermore, Tsinghua Dogs annotated bounding boxes of the dog’s whole body and head in each image, which can be used for supervising the training of learning algorithms as well as testing them.

  4. c

    Stanford Dogs Dataset

    • cubig.ai
    Updated Oct 12, 2024
    Share
    FacebookFacebook
    TwitterTwitter
    Email
    Click to copy link
    Link copied
    Close
    Cite
    CUBIG (2024). Stanford Dogs Dataset [Dataset]. https://cubig.ai/store/products/524/stanford-dogs-dataset
    Explore at:
    Dataset updated
    Oct 12, 2024
    Dataset authored and provided by
    CUBIG
    License

    https://cubig.ai/store/terms-of-servicehttps://cubig.ai/store/terms-of-service

    Measurement technique
    Synthetic data generation using AI techniques for model training, Privacy-preserving data transformation via differential privacy
    Description

    1) Data Introduction • The Stanford Dogs dataset is a high-resolution image dataset consisting of 17 representative dog breeds, including Maltese, Shih Tzu, Afghan Hound, Irish Wolfhound, Saluki, Scottish Deerhound, Sealyham Terrier, Airedale, Tibetan Terrier, Bernese Mountain Dog, Entlebucher, Basenji, Pug, Leonberger, Great Pyrenees, Samoyed, and Pomeranian.

    2) Data Utilization (1) Characteristics of the Stanford Dogs Dataset: • The dataset is well-suited for capturing subtle visual differences between dog breeds with similar appearances and can be effectively used for fine-grained breed classification and image recognition experiments.

    (2) Applications of the Stanford Dogs Dataset: • Dog Classification Model Development: It can be used to develop artificial intelligence models that automatically classify dog species by learning the visual features of various dog species. • Detailed Image Recognition Study: It can be used for research in the field of fine-grained visual categorization that distinguishes minute differences between dog species with similar appearance.

  5. R

    Stanford Dogs Dog Breed Dataset

    • universe.roboflow.com
    zip
    Updated Jan 8, 2024
    Share
    FacebookFacebook
    TwitterTwitter
    Email
    Click to copy link
    Link copied
    Close
    Cite
    Iliescu Mihail Doirn (2024). Stanford Dogs Dog Breed Dataset [Dataset]. https://universe.roboflow.com/iliescu-mihail-doirn/stanford-dogs-dataset-dog-breed
    Explore at:
    zipAvailable download formats
    Dataset updated
    Jan 8, 2024
    Dataset authored and provided by
    Iliescu Mihail Doirn
    License

    CC0 1.0 Universal Public Domain Dedicationhttps://creativecommons.org/publicdomain/zero/1.0/
    License information was derived automatically

    Variables measured
    Dogs Bounding Boxes
    Description

    Stanford Dogs Dataset Dog Breed

    ## Overview
    
    Stanford Dogs Dataset Dog Breed is a dataset for object detection tasks - it contains Dogs annotations for 20,491 images.
    
    ## Getting Started
    
    You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.
    
      ## License
    
      This dataset is available under the [Public Domain license](https://creativecommons.org/licenses/Public Domain).
    
  6. cats_vs_dogs

    • huggingface.co
    • tensorflow.org
    • +1more
    Updated May 23, 2024
    + more versions
    Share
    FacebookFacebook
    TwitterTwitter
    Email
    Click to copy link
    Link copied
    Close
    Cite
    Microsoft (2024). cats_vs_dogs [Dataset]. https://huggingface.co/datasets/microsoft/cats_vs_dogs
    Explore at:
    CroissantCroissant is a format for machine-learning datasets. Learn more about this at mlcommons.org/croissant.
    Dataset updated
    May 23, 2024
    Dataset authored and provided by
    Microsofthttp://microsoft.com/
    License

    https://choosealicense.com/licenses/unknown/https://choosealicense.com/licenses/unknown/

    Description

    Dataset Card for Cats Vs. Dogs

      Dataset Summary
    

    A large set of images of cats and dogs. There are 1738 corrupted images that are dropped. This dataset is part of a now-closed Kaggle competition and represents a subset of the so-called Asirra dataset. From the competition page:

    The Asirra data set Web services are often protected with a challenge that's supposed to be easy for people to solve, but difficult for computers. Such a challenge is often called a CAPTCHA… See the full description on the dataset page: https://huggingface.co/datasets/microsoft/cats_vs_dogs.

  7. P

    Cats and Dogs Dataset

    • paperswithcode.com
    Share
    FacebookFacebook
    TwitterTwitter
    Email
    Click to copy link
    Link copied
    Close
    Cite
    Cats and Dogs Dataset [Dataset]. https://paperswithcode.com/dataset/cats-vs-dogs
    Explore at:
    Description

    A large set of images of cats and dogs.

    Homepage: https://www.microsoft.com/en-us/download/details.aspx?id=54765

    Source code: tfds.image_classification.CatsVsDogs

    Versions:

    4.0.0 (default): New split API (https://tensorflow.org/datasets/splits) Download size: 786.68 MiB

    Source: https://www.tensorflow.org/datasets/catalog/cats_vs_dogs

  8. h

    stanford-dogs

    • huggingface.co
    Updated Dec 24, 2024
    + more versions
    Share
    FacebookFacebook
    TwitterTwitter
    Email
    Click to copy link
    Link copied
    Close
    Cite
    Andrew Mayes (2024). stanford-dogs [Dataset]. https://huggingface.co/datasets/amaye15/stanford-dogs
    Explore at:
    CroissantCroissant is a format for machine-learning datasets. Learn more about this at mlcommons.org/croissant.
    Dataset updated
    Dec 24, 2024
    Authors
    Andrew Mayes
    Description

    amaye15/stanford-dogs dataset hosted on Hugging Face and contributed by the HF Datasets community

  9. R

    Detection Of Stray Dogs Dataset

    • universe.roboflow.com
    zip
    Updated Feb 5, 2024
    Share
    FacebookFacebook
    TwitterTwitter
    Email
    Click to copy link
    Link copied
    Close
    Cite
    EMT (2024). Detection Of Stray Dogs Dataset [Dataset]. https://universe.roboflow.com/emt-ys6ow/detection-of-stray-dogs
    Explore at:
    zipAvailable download formats
    Dataset updated
    Feb 5, 2024
    Dataset authored and provided by
    EMT
    License

    Attribution 4.0 (CC BY 4.0)https://creativecommons.org/licenses/by/4.0/
    License information was derived automatically

    Variables measured
    Stray Dogs Bounding Boxes
    Description

    Detection Of Stray Dogs

    ## Overview
    
    Detection Of Stray Dogs is a dataset for object detection tasks - it contains Stray Dogs annotations for 305 images.
    
    ## Getting Started
    
    You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.
    
      ## License
    
      This dataset is available under the [CC BY 4.0 license](https://creativecommons.org/licenses/CC BY 4.0).
    
  10. h

    Cat_and_Dog

    • huggingface.co
    Updated Oct 2, 2023
    Share
    FacebookFacebook
    TwitterTwitter
    Email
    Click to copy link
    Link copied
    Close
    Cite
    Dowon Hwang (2023). Cat_and_Dog [Dataset]. https://huggingface.co/datasets/Bingsu/Cat_and_Dog
    Explore at:
    CroissantCroissant is a format for machine-learning datasets. Learn more about this at mlcommons.org/croissant.
    Dataset updated
    Oct 2, 2023
    Authors
    Dowon Hwang
    License

    https://choosealicense.com/licenses/cc0-1.0/https://choosealicense.com/licenses/cc0-1.0/

    Description

    Dataset Summary

    A dataset from kaggle with duplicate data removed.

      Data Fields
    

    The data instances have the following fields:

    image: A PIL.Image.Image object containing the image. Note that when accessing the image column: dataset[0]["image"] the image file is automatically decoded. Decoding of a large number of image files might take a significant amount of time. Thus it is important to first query the sample index before the "image" column, i.e. dataset[0]["image"]… See the full description on the dataset page: https://huggingface.co/datasets/Bingsu/Cat_and_Dog.

  11. h

    Stanford-Dogs

    • huggingface.co
    Updated Nov 20, 2024
    Share
    FacebookFacebook
    TwitterTwitter
    Email
    Click to copy link
    Link copied
    Close
    Cite
    Dong-Hyun Han (2024). Stanford-Dogs [Dataset]. https://huggingface.co/datasets/Donghyun99/Stanford-Dogs
    Explore at:
    CroissantCroissant is a format for machine-learning datasets. Learn more about this at mlcommons.org/croissant.
    Dataset updated
    Nov 20, 2024
    Authors
    Dong-Hyun Han
    Description

    Dataset Card for "Stanford-Dogs"

    This is a non-official Stanford-Dogs dataset for fine-grained Image Classification.
    If you want to download the official dataset, please refer to the here.

  12. R

    Activity Recognition On Dogs Dataset

    • universe.roboflow.com
    zip
    Updated Aug 15, 2023
    Share
    FacebookFacebook
    TwitterTwitter
    Email
    Click to copy link
    Link copied
    Close
    Cite
    activity recognition on dogs (2023). Activity Recognition On Dogs Dataset [Dataset]. https://universe.roboflow.com/activity-recognition-on-dogs/activity-recognition-on-dogs
    Explore at:
    zipAvailable download formats
    Dataset updated
    Aug 15, 2023
    Dataset authored and provided by
    activity recognition on dogs
    License

    Attribution 4.0 (CC BY 4.0)https://creativecommons.org/licenses/by/4.0/
    License information was derived automatically

    Variables measured
    Dogs Bounding Boxes
    Description

    Activity Recognition On Dogs

    ## Overview
    
    Activity Recognition On Dogs is a dataset for object detection tasks - it contains Dogs annotations for 707 images.
    
    ## Getting Started
    
    You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.
    
      ## License
    
      This dataset is available under the [CC BY 4.0 license](https://creativecommons.org/licenses/CC BY 4.0).
    
  13. Stanford Dogs Sanitised and Cropped 128x128

    • kaggle.com
    zip
    Updated Apr 9, 2020
    Share
    FacebookFacebook
    TwitterTwitter
    Email
    Click to copy link
    Link copied
    Close
    Cite
    RobbinDG (2020). Stanford Dogs Sanitised and Cropped 128x128 [Dataset]. https://www.kaggle.com/robbindg/stanford-dogs-sanitised-and-cropped-128-x-128
    Explore at:
    zip(99098088 bytes)Available download formats
    Dataset updated
    Apr 9, 2020
    Authors
    RobbinDG
    License

    https://creativecommons.org/publicdomain/zero/1.0/https://creativecommons.org/publicdomain/zero/1.0/

    Description

    Context

    To practice the generation of images using deep learning, a starter dataset like the Stanford dogs could be utilised. For this purpose, this dataset suffers from flaws like unequal dimensions and 'useless' data surrounding the dogs in the images. This dataset is a resized and cropped version of all the original Stanford dogs.

    Content

    The dataset contains 2 directories: 'annotations' and 'images'. The annotations directory contains the original annotations from the Stanford dogs dataset. Evidently, the dimensions of the image and bbox are no longer valid. The images are the newly resized and cropped images.

  14. R

    New Dogs Dataset

    • universe.roboflow.com
    zip
    Updated May 27, 2025
    Share
    FacebookFacebook
    TwitterTwitter
    Email
    Click to copy link
    Link copied
    Close
    Cite
    THESIS (2025). New Dogs Dataset [Dataset]. https://universe.roboflow.com/thesis-rxpts/new-dogs-ox8tb
    Explore at:
    zipAvailable download formats
    Dataset updated
    May 27, 2025
    Dataset authored and provided by
    THESIS
    License

    Attribution 4.0 (CC BY 4.0)https://creativecommons.org/licenses/by/4.0/
    License information was derived automatically

    Variables measured
    Dog Bounding Boxes
    Description

    New Dogs

    ## Overview
    
    New Dogs is a dataset for object detection tasks - it contains Dog annotations for 2,520 images.
    
    ## Getting Started
    
    You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.
    
      ## License
    
      This dataset is available under the [CC BY 4.0 license](https://creativecommons.org/licenses/CC BY 4.0).
    
  15. Number of dogs in the U.S. 2000-2017

    • statista.com
    Updated Jan 12, 2024
    Share
    FacebookFacebook
    TwitterTwitter
    Email
    Click to copy link
    Link copied
    Close
    Cite
    Statista (2024). Number of dogs in the U.S. 2000-2017 [Dataset]. https://www.statista.com/statistics/198100/dogs-in-the-united-states-since-2000/
    Explore at:
    Dataset updated
    Jan 12, 2024
    Dataset authored and provided by
    Statistahttp://statista.com/
    Area covered
    United States
    Description

    How many dogs are there in the US? According to a pet owners survey, there were approximately 89.7 million dogs owned in the United States in 2017. This is an increase of over 20 million since the beginning of the survey period in 2000, when around 68 million dogs were owned in the United States.

    Why has this figure increased?

    The resident population of the United States has also increased significantly within this time period. It is, therefore, no surprise that the number of dogs owned in U.S. households has also increased, especially when considering that the household penetration rate for dog-ownership reached almost 50 percent in recent years.

    The dog food market in the United States

    The large number of dogs owned by Americans creates a lucrative market for pet food brands and retailers. Pedigree, the leading dry dog food name brand in the U.S., had sales amounting to around 550 million U.S. dollars in 2017. Pedigree also led the pack in the wet dog food category , with sales of around 240 million U.S. dollars in the same year.

  16. WhichDog: A crowdsourced dataset including candidate set-based labelling

    • zenodo.org
    zip
    Updated Sep 23, 2022
    Share
    FacebookFacebook
    TwitterTwitter
    Email
    Click to copy link
    Link copied
    Close
    Cite
    Iker Beñaran-Muñoz; Iker Beñaran-Muñoz; Jerónimo Hernández-González; Jerónimo Hernández-González; Aritz Pérez; Aritz Pérez (2022). WhichDog: A crowdsourced dataset including candidate set-based labelling [Dataset]. http://doi.org/10.5281/zenodo.7100698
    Explore at:
    zipAvailable download formats
    Dataset updated
    Sep 23, 2022
    Dataset provided by
    Zenodohttp://zenodo.org/
    Authors
    Iker Beñaran-Muñoz; Iker Beñaran-Muñoz; Jerónimo Hernández-González; Jerónimo Hernández-González; Aritz Pérez; Aritz Pérez
    License

    Attribution 4.0 (CC BY 4.0)https://creativecommons.org/licenses/by/4.0/
    License information was derived automatically

    Description

    A dataset with crowdsourced labels for aggregation and supervised classification.
    It contains 400 images of dogs from the Stanford Dogs dataset (http://vision.stanford.edu/aditya86/ImageNetDogs/). Images of dogs that belong to 32 different breeds (classes) are included. Annotators were asked to provide two types of labelling: full labelling (each labeler is allowed to provide a single label for each image) and candidate labelling (each labeler is allowed to provide a set of candidate labels for each image). It includes a total of 61227 annotations (30628 full and 30599 candidate) obtained from a set of 1028 different labelers.

    The labels were collected through the online crowdsourcing platform Amazon mTurk thanks to funds provided by the Basque Government through the Elkartek program (KK-2018/00071). The assignments were designed as sequences of 64 images that were given to the annotators. Each image in the sequence was provided together with a specific subset of possible labels (with the number of options ranging from 4 to 32), and a instruction for the annotator to perform a specific type of labelling (full or candidate). Each labeler performed at least one assignment. Not all the labelers completed the 64 annotations in their assignments.

    The file 'whichdog.zip' contains a folder ('images') with the 400 images of dogs, a text file ('breed_names.txt') that indicates the names of the different breeds and their assigned label (a number in the interval from 0 to 31) and a CSV file ('whichdog_all_annots.csv') that contains the information about the annotations. Each row of the CSV file represents a single annotation, and each column shows:
    - image_id: ID number of the image.
    - is_candidate: indicates whether the requested labelling is full (0) or candidate (1).
    - labeler_id: ID number of the labeler.
    - time: time employed by the labeler to perform the annotation.
    - answer: label or set of labels provided by the labeler as annotation.
    - options: subset of possible labels shown to the labeler.
    - assignment_id: ID number of the assignment
    - sequence_point: number that indicates the point of the sequence of images of the assignment in which the annotation was provided.
    - class: ground truth label of the image.

  17. s

    Canine atopic dermatitis datasets

    • figshare.scilifelab.se
    • researchdata.se
    bin
    Updated Jan 15, 2025
    Share
    FacebookFacebook
    TwitterTwitter
    Email
    Click to copy link
    Link copied
    Close
    Cite
    Katarina Tengvall (2025). Canine atopic dermatitis datasets [Dataset]. http://doi.org/10.17044/scilifelab.21287139.v1
    Explore at:
    binAvailable download formats
    Dataset updated
    Jan 15, 2025
    Dataset provided by
    Uppsala University
    Authors
    Katarina Tengvall
    License

    Attribution 4.0 (CC BY 4.0)https://creativecommons.org/licenses/by/4.0/
    License information was derived automatically

    Description

    The datasets consists of genotype data from dogs in plink format.

    ATOPYK2 plink files contains genotype data from five dog breeds with and without atopic dermatitis. The ATOPYK2 datafiles were used for imputation. These are pre-QC:ed with the following plink settings --maf 0.001 --geno 0.05 --mind 0.05

    We recommend a second qc before doing the imputation. The imputation was then run per chromosome so for redoing the imputation, as was done in the publication to which this data is connected, use the following plink code:

    plink --bfile ATOPYK2 --chr $chrN --make-bed --dog --allow-no-sex --keep-allele-order --maf 0.001 --geno 0.2 --out 'ATOPYK.chr'$chrN

    The final datasets after imputation are datasets split breed wise and in plink format. These sets are QC:ed, and relatedness filtered. The "covar"-file includes fixed effects, these are different between depending on what covariates were significantly affecting the trait (atopic dermatitis) in each breed. These datasets are named GR (golden retriever), LR (labrador retriever), GSD (german shepherd) and WHWT (west highland white terrier). (Boxers are in the ATOPYK2 files but not used for final analyses, hence no breed specific datafile for boxer are included).

  18. Cat and Dog

    • kaggle.com
    zip
    Updated Apr 26, 2018
    Share
    FacebookFacebook
    TwitterTwitter
    Email
    Click to copy link
    Link copied
    Close
    Cite
    SchubertSlySchubert (2018). Cat and Dog [Dataset]. https://www.kaggle.com/tongpython/cat-and-dog
    Explore at:
    zip(228487605 bytes)Available download formats
    Dataset updated
    Apr 26, 2018
    Authors
    SchubertSlySchubert
    License

    https://creativecommons.org/publicdomain/zero/1.0/https://creativecommons.org/publicdomain/zero/1.0/

    Description

    This dataset is for running the code from this site: https://becominghuman.ai/building-an-image-classifier-using-deep-learning-in-python-totally-from-a-beginners-perspective-be8dbaf22dd8.

    This is how to show a picture from the training set: display(Image('../input/cat-and-dog/training_set/training_set/dogs/dog.423.jpg'))

    From the test set: display(Image('../input/cat-and-dog/test_set/test_set/cats/cat.4453.jpg'))

    See an example of using this dataset. https://www.kaggle.com/tongpython/nattawut-5920421014-cat-vs-dog-dl

  19. R

    Object Detection Cat And Dogs Dataset

    • universe.roboflow.com
    zip
    Updated Sep 25, 2023
    Share
    FacebookFacebook
    TwitterTwitter
    Email
    Click to copy link
    Link copied
    Close
    Cite
    Cats and Dogs Detection (2023). Object Detection Cat And Dogs Dataset [Dataset]. https://universe.roboflow.com/cats-and-dogs-detection/object-detection-cat-and-dogs/model/1
    Explore at:
    zipAvailable download formats
    Dataset updated
    Sep 25, 2023
    Dataset authored and provided by
    Cats and Dogs Detection
    License

    Attribution 4.0 (CC BY 4.0)https://creativecommons.org/licenses/by/4.0/
    License information was derived automatically

    Variables measured
    Animals Bounding Boxes
    Description

    Object Detection Cat And Dogs

    ## Overview
    
    Object Detection Cat And Dogs is a dataset for object detection tasks - it contains Animals annotations for 659 images.
    
    ## Getting Started
    
    You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.
    
      ## License
    
      This dataset is available under the [CC BY 4.0 license](https://creativecommons.org/licenses/CC BY 4.0).
    
  20. h

    dogs

    • huggingface.co
    Updated Sep 22, 2024
    Share
    FacebookFacebook
    TwitterTwitter
    Email
    Click to copy link
    Link copied
    Close
    Cite
    Raphael Damasceno Rocha de Moraes (2024). dogs [Dataset]. https://huggingface.co/datasets/mdrapha/dogs
    Explore at:
    CroissantCroissant is a format for machine-learning datasets. Learn more about this at mlcommons.org/croissant.
    Dataset updated
    Sep 22, 2024
    Authors
    Raphael Damasceno Rocha de Moraes
    Description

    mdrapha/dogs dataset hosted on Hugging Face and contributed by the HF Datasets community

Share
FacebookFacebook
TwitterTwitter
Email
Click to copy link
Link copied
Close
Cite
(2023). stanford_dogs [Dataset]. https://www.tensorflow.org/datasets/catalog/stanford_dogs

stanford_dogs

Explore at:
8 scholarly articles cite this dataset (View in Google Scholar)
Dataset updated
Jan 13, 2023
Description

The Stanford Dogs dataset contains images of 120 breeds of dogs from around the world. This dataset has been built using images and annotation from ImageNet for the task of fine-grained image categorization. There are 20,580 images, out of which 12,000 are used for training and 8580 for testing. Class labels and bounding box annotations are provided for all the 12,000 images.

To use this dataset:

import tensorflow_datasets as tfds

ds = tfds.load('stanford_dogs', split='train')
for ex in ds.take(4):
 print(ex)

See the guide for more informations on tensorflow_datasets.

https://storage.googleapis.com/tfds-data/visualization/fig/stanford_dogs-0.2.0.png" alt="Visualization" width="500px">

Search
Clear search
Close search
Google apps
Main menu