This competition is closed for submissions. Participants' selected code submissions were re-run by the host on a privately-held test set and the private leaderboard results have been finalized. Late submissions will not be opened, due to an inability to replicate the unique design of this competition.
This code competition's training set is not available directly on Kaggle, as its size is prohibitively large to train in Kaggle. Instead, it's strongly recommended that you train offline and load the externally trained model as an external dataset into Kaggle Notebooks to perform inference on the Test Set. Review Getting Started for more detailed information.
The full training set is just over 470 GB. We've made it available as one giant file, as well as 50 smaller files, each ~10 GB in size. You must accept the competition's rules to gain access to any of the links below.
Full dataset:
| all.zip (471.84 GB) |
Dataset split into smaller chunks:
A small sample training set has been made available below.
You'll also need the sample_submission.csv, as it indicates the IDs you'll be making predictions for.
The data is comprised of .mp4 files, split into compressed sets of ~10GB apiece. A metadata.json accompanies each set of .mp4 files, and contains filename, label (REAL/FAKE), original and split columns, listed below under Columns.
You will be predicting whether or not a particular video is a deepfake. A deepfake could be either a face or voice swap (or both). In the training data, this is denoted by the string "REAL" or "FAKE" in the label column. In your submission, you will predict the probability that the video is a fake.
metadata.json with labels. the full set of training videos is available through the links provided above.To understand the datasets available for this competition, review the Getting Started information.
filename - the filename of the videolabel - whether the video is REAL or FAKEoriginal - in the case that a train set video is FAKE, the original video is listed heresplit - this is always equal to "train".