COGMEN; Official Pytorch Implementation

COntextualized GNN based Multimodal Emotion recognitioN

Used for my Graduation Project

Requirements

• We use PyG (PyTorch Geometric) for the GNN component in our architecture. RGCNConv and TransformerConv

• We use comet for logging all our experiments and its Bayesian optimizer for hyperparameter tuning.

• For textual features we use SBERT.

Installations

• Install PyTorch Geometric

• Install Comet.ml

• Install SBERT

Preparing datasets for training

    python preprocess.py --dataset="iemocap_4"

Training networks

    python train.py --dataset="iemocap_4" --modalities="atv" --from_begin --epochs=55

Run Evaluation

    python eval.py --dataset="iemocap_4" --modalities="atv"