TJEDC - Tom and Jerry Emotion Detection Challenge
Hidden🕵️ Introduction
We all remember Tom and Jerry and the immense happiness their misadventures brought in our lives. Now you are required to build a model that detects emotions of the characters in a video frame from our most-loved show. Build a model that detects the emotion
of the character present in each frame.
💾 Dataset
The dataset consists of two parameters—
Frame_ID
that indicates the frame of the videoEmotion
that categorizes the emotion of the primary character into different labels:angry(0)
,happy(1)
,sad(2)
,surprised(3)
, orUnknown(4)
. The number in brackets is the encoding of the emotion.
📁 Files
train.csv
- (1941
samples) File that should be used for training by the user.test.csv
- (275
samples) File that will be used for actual evaluation for the leaderboard score.Note:- This is not the final test set. -train.zip
- Contains the images corresponding totrain.csv
file -test.zip
- Contains the images corresponding totest.csv
file
🚀 Submission
- Prepare a csv containing header as
emotion
and predicted emotion as0/1/2/3/4
with name assubmission.csv
. - Sample submission format available at
./data/sample_submission.csv
.
Make your first submission here 🚀 !!
🖊 Evaluation Criteria
During evaluation F1 score and Accuracy will be used to test the efficiency of the model
📱 Contact
📚 References
- https://blog.keras.io/building-powerful-image-classification-models-using-very-little-data.html
- https://www.analyticsvidhya.com/blog/2019/10/building-image-classification-models-cnn-pytorch/
Participants

















































Leaderboard
01 |
![]() |
1.000 |
02 |
![]() |
1.000 |
03 |
![]() |
1.000 |
04 |
![]() |
1.000 |
05 |
![]() |
1.000 |