Link to dataset - https://s3.us-west-1.wasabisys.com/dphi/public-datasets/Data%20Sprint%2080%20Sports%20Genre%20Identification/Sports_Identification.zip

The dataset features 100 different classes of Sports Activities. The dataset contains about 9500 labelled images including the validation images. Each image belongs to only one sports category and are saved in separate folders of the labelled classes

From the above link you will be able to download a zip file named ‘Sports_Identification.zip’. After you extract this zip file, you will get four files:

Train - contains all the images that are to be used for training your model. In this folder you will find 100 folders’ which contain the images of the respective sports categories
Test - contains 4500 images of sports categories. For these images you are required to make predictions as the respective class names.
Testing_set.csv - this is the order of the predictions for each image that is to be submitted on the platform. Make sure the predictions you download are with their image’s filename in the same order as given in this file.
sample_submission: This is a csv file that contains the sample submission for the data sprint.

Saving Prediction File & Sample Submission

You can find more details on how to save a prediction file here: https://discuss.dphi.tech/t/how-to-submit-predictions/548

Etc. Note that the header name should be ‘label’ else it will throw an evaluation error.

Notebook submission: You should submit a CSV file with a header row and the sample submission can be found below:

Data Sprint 104 - Theme Identification of Sports

Challenge Starts

Registration Ends

Challenge Ends