This is a basic implementation of DenseNet combined with LSTM, used for sequence modeling. Here, DenseNet is a CNN feature extractor that feeds the extracted features to LSTM network in sequence. The network predicts 4 corner landmarks of each image in sequence. Overall, its a regression network for image with CNN feature extractor and basic LSTM layer.
bidur-khanal / densenet-lstm Goto Github PK
View Code? Open in Web Editor NEWThis is an implementation of DenseNet Architecture combined with LSTM for sequence modeling.
License: MIT License