This is the code of master's thesis which contains my previous two work (MAAC and FeatureCut).

1. Clone this repository: https://github.com/Vancause/KAMA_AC.git
2. Install pytorch >=1.8.0
3. Use pip to install dependencies: pip install -r requirements.txt

• Download the Clotho dataset for DCASE2021 Automated Audio Captioning challenge. And how to prepare training data and setup coco caption, please refer to Dcase2020 BUPT team's
• Enter the audio_tag directory.
• Firstly, run python generate_word_list.py to create words list word_list_pretrain_rules.p and tagging words to indexes of embedding layer TaggingtoEmbs.
• Then run python generate_tag.py to generate audioTagName_{development/validation/evaluation}_fin_nv.pickle and audioTagNum_{development/validation/evaluation}_fin_nv.pickle

• Download the dataset from https://github.com/XinhaoMei/ACT.
• Generate the .npy files through running generate_audiocaps_files.py

The training configuration is saved in the hparams.py and you can reset it to your own parameters.

• Run python run_newtransformer.py to train the KAMA-AC-T model.
• Run python run_lstm.py to train the KAMA-AC-L model.
• In the files run_lstm.py or run_newtransformer.py, you can modify hyper-parameters directly to run the ablations.

• Run python run_featurecut.py to train the KAMA-AC-L model.
• In the files run_lstm.py or run_newtransformer.py, you can modify hyper-parameters directly to run the ablations