Two-Way Feature Extraction Using Sequential and Multimodal Approach for Hateful Meme Classification

Table 1

Some of the best results obtained while training the model using the multimodal approach.

No. of epochs	Optimizer	Batch size	Validation accuracy
10	RMSProp	32	0.51
8	Adadelta	16	0.53
6	Adamax	8	0.55