RNNs are now central to many applications, from speech recognition to Computer Vision. Some examples are Image captioning, Visual Question Answering (VQA), autonomous driving, and even Lip reading. Thus, it would be of high interest that tiny-dnn incorporates these features. The proposed implementation makes use and extends the already existing graph representation to create input, and loss nodes that can represent sequences, and create new layers for RNNs, and LSTMs. All the new code and modifications will be unit tested and documented. Examples on video recognition will also be provided.



Pau Rodríguez


  • Taiga Nomi
  • Edgar Riba