Our source code for EACL2021 workshop: Meme Classification for Tamil Language. We took first place in this task finally!๐ฅณ
Updated: Source code is released!๐คฉ
I will release the code very soon.
โโโ MyLoss.py # Impelmentation of some loss function
โโโ README.md
โโโ __init__.py
โโโ args.py # declare some argument
โโโ ckpt
โย ย โโโ README.md
โโโ data # store data
โย ย โโโ README.md
โโโ gen_data.py # generate Dataset
โโโ install_cli.sh # install required package
โโโ logfile # store logfile during training
โโโ main.py # train model
โโโ model.py # define model
โโโ multimodal_attention.py # Implentation of multimodal attention layer
โโโ pred_data
โย ย โโโ README.md
โโโ preprocessing.py # preprocess the data
โโโ pretrained_weights # store pretrained weights of resnet and xlm-roberta
โย ย โโโ README.md
โโโ run.sh # run model
โโโ train.py # define training and validation loop
Use the following command so that you can install all of required packages:
sh install_cli.sh
The first step is to preprocess the data. Just use the following command:
python3 -u preprocessing.py
The second step is to train our model. Use the following command:
nohup sh run.sh > run_log.log 2>&1 &
The final step is inference after training. Use the following command:
nohup python3 -u inference.py > inference.log 2>&1 &
Congralutions! You have got the final results!๐คฉ
If you use our code, please indicate the source.