This dataset for the doodle recognition challenge consists of 9 different classes and each image belongs to a
unique
class.
The main
train
directory contains 9 folders, each having 700 grayscale images of 360x360 resolution. The directory structure has been simplified for classification i.e. the folder names in the train directory correspond to class name of all the doodles inside the folder.
File descriptions
train.zip
- the training dataset
test.zip
- the test set
sampleSubmission.csv
- a sample submission file in the correct format