Summary

In this chapter, we learned about how RNNs work and specifically the variant of LSTM in detail. Furthermore, we learned about leveraging CNNs and RNNs together as we passed an image through a pre-trained model to extract features and passed the features as time steps to the RNN to extract the words one at a time, in our image captioning use case. We then took the combination of CNNs and RNNs a step further, where we leveraged the CTC loss function to transcribe handwritten images. The CTC loss function helped in ensuring that we squash the same character coming from subsequent time steps into a single character and also in ensuring that all possible combinations of output are considered, and then we evaluated the loss based on the combination resulting in the ground truth. Finally, we learned about leveraging transformers to perform object detection using DETR, during which we also understood how transformers work and how they can be leveraged in the context of object detection...