Data description

The dataset features 9 different classes of ships. The dataset contains about 1000+ images including the validation images. Each image has only one Ship category and are saved in separate folders of the labelled classes

The dataset can be downloaded from the given link: https://s3.us-west-1.wasabisys.com/dphi/public-datasets/Data_Sprint_101_Vessel_Image_Identification/Dockship.zip

From the above link you will be able to download a zip file named 'Dockship.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.
Training_set.csv - this csv file has contains the labels for the training images
test - contains 300 images. For these images you are required to make predictions
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 submit are with their image’s filename in the same order as given in this file.

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

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

filename	label
Image_1.jpg	gondola
Image_2.jpg	sailboat
Image_3.jpg	cruise_ship
Image_4.jpg	buoy
Image_5.jpg	ferry_boat
Image_6.jpg	sailboat

.

.

Etc.

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

Notebook Submission

Steps to follow to submit your notebook:

Data Sprint 101 - Vessel Image Identification

Challenge Starts

Registration Ends

Challenge Ends