relaxxpls/image-captioning

Image Captioning using CNN + LSTM AutoEncoder Models trained on the Common Objects in Context aka COCO dataset.

Image Captioning

Image Captioning using CNN and LSTM based Encoder Decoder architecture trained on the Common Objects in Context aka COCO dataset.

Paper

• Show, Attend and Tell: Neural Image Caption Generation with Visual Attention

Dataset

• MS COCO 2014 (Common Objects in Context)