# 167th Place Solution with code

Thank you very much to the competition organizers at Kaggle, to Bengali.ai community for organizing the competition. Many thanks to everyone who discussed the competition on the Forum. With each competition, I have been learning a lot from the forum and notebook kernels. And finally congrats to all the winners and teams that participated in this competition! My solution summary is given below:
Dataset:
•   Image Size: 137x236 ( No preprocessing )
Augmentation:
•   CutMix
Model:
•   EfficientNet-B5 with three heads
![](assets/71cbe7b15d9ddf8cf96424f3.png)
Training:
•   5 fold Configuration
•   Data split on the basis of grapheme root labels
•   Loss: Cross Entropy Loss
•   Optimizer: Over9000
•   Scheduler: Reduce On Plateau
•   Gradient Accumulation
•   Batch Size 100
•   Initial Learning Rate 0.03
Inference:
•   Best Average recall checkpoints were used
•   Simple Average of the outputs from 5 folds
•   Inference kernel:
[https://www.kaggle.com/mohammadzunaed/efficientnet-b5-inference-kernel-pytorch?scriptVersionId=32245517](https://www.kaggle.com/mohammadzunaed/efficientnet-b5-inference-kernel-pytorch?scriptVersionId=32245517)
Things that did not work for me:
•   Preprocessing
•   GridMask, Cutout, AugMix
•   Label Smoothing Criterions
•   Single head instead of three heads
•   Activation functions and Convolutional layers in the heads
Github Link:
[https://github.com/Rafizunaed/Kaggle-Bengali.AI-Handwritten-Grapheme-Classification.git](https://github.com/Rafizunaed/Kaggle-Bengali.AI-Handwritten-Grapheme-Classification.git)