Animal10

## Overview

Animal10 is a dataset for object detection tasks - it contains Animal10 annotations for 357 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).

The Animal10N Training Set consists of 40,000 images of animals from 10 different classes. The images are labeled with the animal's class.

The Animal10N Test Set consists of 10,000 images of animals from 10 different classes. The images are labeled with the animal's class.

Dataset

This dataset was created by Allen_002

Contents

This data contains 3 files consisting of the model weights of Inception, Xception and ResNet152V2. All the three models were trained on the Animal 10 classification dataset. Out of which, ResNet152V2 performed the best with 93% Training Accuracy and 92% Testing Accuracy with the lowest loss among all and converged to the solution the fastest. The other models are still not bad and they performed roughly close to it, around 91% accuracy in both training and testing part. That's why I have included both of them. If you can, check them out. The models predictions and the model itself is available in the Notebook associated with this data set.

Hello everyone!

This is the dataset I have used for my matriculation thesis.

It contains about 28K medium quality animal images belonging to 10 categories: dog, cat, horse, spyder, butterfly, chicken, sheep, cow, squirrel, elephant.

I have used it to test different image recognition networks: from homemade CNNs (~80% accuracy) to Google Inception (98%). It could simulate a smart gallery for a researcher (like a biologist).

All the images have been collected from "google images" and have been checked by human. There is some erroneous data to simulate real conditions (eg. images taken by users of your app).

The main directory is divided into folders, one for each category. Image count for each category varies from 2K to 5 K units.