Image Captioning Using CNN And LSTM

My client needed building model to describe the image , i built this model by merging CNN & LSTM models in one model called a CNN-RNN model .i use a deep convolutional neural network to extract the visual image features and Semantic features are extracted from the semantic tagging model. Visual features from CNN and semantic features from tagging model are concatenated and feed as the input to a Long-Short-Term Memory (LSTM) network, which then generates captions.